DWT-BAT Based Medical Image Watermarking For Telemedicine Applications

Size: px
Start display at page:

Download "DWT-BAT Based Medical Image Watermarking For Telemedicine Applications"

Transcription

1 DWT-BAT Based Medcal Image Watermarkng For Telemedcne Applcatons 1 N.Venkatram, 2 L.S.S.Reddy, 3 P.V.V.Kshore, 1 K.L.Unversty, Dept of E.C.M, KL Unversty, Vaddeswaram, Green Felds, GUNTUR, AP, INDIA 2 K.L.Unversty, Dept of C.S.E, KL Unversty, Vaddeswaram, Green Felds, GUNTUR, AP, INDIA 3 K.L.Unversty, Dept of E.C.E, KL Unversty, Vaddeswaram, Green Felds, GUNTUR, AP, INDIA ABSTRACT Medcal mages communcate mperatve nformaton to the doctors about a patent s health stuaton. Internet broadcasts these medcal mages to naccessble stes of the globe whch are nspected by specalst doctors. But data transmssons through unsecured web nvoke valdaton problems for any mage data. Medcal mages that are transmtted through the nternet must be watermarked wth patent pctures for substantaton by the doctors to ascertan the medcal mage. Medcal mages contan very susceptble nformaton connected to a patent s health. Watermarkng medcal mages necesstate attentve adjustments to protect the nformaton n the medcal mages wth patent mage watermarks. The medcal mages are used as an envelope mage n the watermarkng process whch s vsble on the network. These envelope medcal mages are watermarked wth patent mages n wavelet doman there by usng the BAT algorthm form optmzng the embeddng process for peak sgnal to nose rato(psnr) and normalzed cross correlaton coeffcent (ncc) values. The medcal mage envelope and letter nsde envelope.e. watermark mage are transformed nto wavelet doman and are mxed usng scalng factor alpha whch s termed as embeddng strength. BAT algorthm s an optmzaton algorthm specalzed n optmzng the values of peak-sgnal-to-nose rato for a partcular value of alpha, the embeddng watermark strength. Fnally these watermarked medcal mages are put on the network along wth the secret key that wll be used for extracton. At the recevng the embedded watermark s extracted usng 2DWT usng the embeddng strength value usng BAT algorthm. The robustness of the proposed watermarkng technques s tested wth varous attacks on the watermarked medcal mages. Peak-Sgnal-to-Nose ratos and Normalzed cross correlaton coeffcents are computed to accesses the qualty of the watermarked medcal mages and extracted patent mages. The results are produced for three types of medcal mages wth one patent mage watermarks usng sngle key by usng four wavelets (haar, db, symlets, bor) at four dfferent levels (1&2). Keywords: Medcal Image Watermarkng, Dscrete Wavelet Transform (DWT), Optmzaton algorthms, BAT algorthm, MRI, CT and Ultrasound Images, psnr and ncc. 1. INTRODUCTION Watermarkng dgtal multmeda Cox I J, Kllan et al (1997), M.D. Swanson et al (1998), Podlchuk et al (1998), Hartung et al(1999), contents has grown rapdly n the recent past wth the advances n nternet technology. Ths watermarkng functonalty s to hde nformaton, protect dgtal copyrghts and for content dentfcaton of multmeda contents exchanged over the nternet. Internet data travels through unprotected routng swtches all over the world. Hence watermarkng comes to the rescue for protectng multmeda data that s transmtted through these unsecured servers. Medcal mage watermarkng Haley.D et al(1999), Güler et al(2002), Haley et al (2002), Smth et al(2005) functons sgnfcantly n supportng a patent by conveyng hs nfrmty usng medcal mages through unsecured networks such as the nternet to expert doctors around the world. Ths practce helps to expand the possblty of dstantly statoned patents where no expert medcal doctor s accessble to ncrease ther probablty of endurance.

2 Traffckng medcal mages through unsecure nternet s prone to unwelcomed modfcaton to the senstve contents of the medcal mages. Medcal mages contan vulnerable nformaton whch s valuable related to the health of the patent. Medcal practtoner has to take supreme care to check that the mages are not meddled wth, before analysng the medcal mages downloaded from the unsecured nternet. For ths reason, authentcaton of medcal mages such as Ultrasound scans, MRI scans, x-ray and Computer Tomography (CT) scans has to be watermarked. The host medcal mage can be watermarked wth patent nformaton before transmttng on the nternet. At the physcan s end t has to de watermarked before proceedng for dagnostcs. Medcal cover mages are watermarked wth patent mage as watermark whch forms an nvsble detecton code. A medcal mage watermarkng s a perfectly hdden watermarkng pardgrams as proposed by Anand et al (1998). The applcaton of medcal mage watermarkng s towards telemedcne. In recent years medcal mage watermarkng s prmarly used to hde patent nformaton such as patent s name, age, gender whch can unquely dentfy a patent by Zan et al (2006). Ths patent related watermark nformaton s extracted to determne the authentcty of the medcal mages. As the extracted watermark from the medcal mage matches the patent data n the doctor s offce, t s proved that these medcal mages belong to a partcular patent n Navas(2007). There s a growng demand for applcatons related to watermarkng due to the ever ncreasng storage and sharng of dgtal meda contents around the world on the nternet. Watermarkng has nvaded every multmeda transmsson on the nternet such as text documents (Jall et al (2009)), mages (E.T. Ln et al (1999)) and even audo (Boney et al (1996)) and vdeo data watermarkng (Wolfgang et al (1999)). Varous dgtal mage watermarkng schemes are proposed and mplemented successfully by researchers around the world n an mage s spatal doman (Nkolads et al(1998)), transform doman (P.V.V.Kshore et al(2014)) along wth encrypton technques whch as robust (P.V.V.Kshore et al(2014)), sem-fragle (E.T. Ln et al (1999)) and some are fragle watermarkng schemes. The growng need for medcal mage watermarkng schemes s due to the usage of nternet to transfer medcal mages among expert doctors for advces and case studes. Medcal mages can and are savng human lves around the world. But wth sharng comes the fear of hackers. Hackers attack these medcal mages modfyng ther detals makng the medcal mage data msleadng to a doctor. Ths pont can be better proved by lookng at the orgnal and modfed medcal mages as shown n fgure 1 and fgure 2. Fgure 1(a). Orgnal MRI Bran mage Transmtted to the Doctor through nternet Fgure 1(b). Hacked MRI Bran mage Transmtted to the Doctor through nternet Fgure 2(a). Orgnal CT Bran mage Transmtted to the Doctor through nternet 2 Fgure 2(b). Hacked CT Bran mage Transmtted to the Doctor through nternet

3 Fgures 1(a) s the orgnal MRI mage of a patent. When a doctor at a remote locaton wants a second opnon about the dsease, he transmts t to another expert through nternet. Fgure 1(b) shows the modfed medcal mage by the hackers. Ths knd of modfcatons can sometmes cost a human lfe. Here there s a need to prevent medcal data from hackers and prove the authentcty of the medcal mages at the recevng doctor s end. Fgure 2 shows the orgnal and attacked CT bran mage. Coatreux et al (2000) enlghtened that dgtal watermarks should be consdered as a securty tool n order to protect medcal records. Gakoumak et al (2003) proposed a wavelet transform-based watermarkng, whch fulflls the strct requrements concernng the acceptable alteratons of medcal mages. The proposed scheme embeds numerous watermarks helpng dverse functonalty such as authentcaton contanng doctor s dgtal sgnature as a robust watermark, patent s personal and examnaton related data and a fragle watermark for data ntegrty control. Thus, they state that the watermarkng tool offers alternatves for dfferent ssues assocated wth medcal data management and dstrbuton. Ths research paper proposes to fnd whch wavelets are better for watermarkng medcal mages and up to what level of decomposton wll result n perfect watermarked mage. Irany et al (2011) proposes a hgh capacty reversble multple watermarkng scheme for medcal mages based on nteger-to-nteger wavelet transform and hstogram shftng. The novelty of the proposed scheme s that t uses a scalable locaton map and ncorporates effcent stoppng condtons on both wavelet levels and dfferent frequency subbands of each level to acheve hgh capacty payload embeddng, hgh perceptual qualty, and multple watermarkng capabltes. Results show that the proposed method attans hgh perceptual qualty n hgh capacty rates for the medcal mages. Lavanya et al (2012)proposed non regon of ntrest(nroi) based medcal mage watermarkng schemes[22] where the patent detals are embedded n non-roi regon of an mage. The encrypted mage s dvded nto non overlappng tles to dentfy regon of nterest and non-regon of nterest. In examnaton ste examner embeds patent detals n non-roi of encrypted mage usng a data-hdng key. Wth an encrypted mage contanng patent detals, a recever may frst defle and decrypt t usng the encrypton key, and the decrypted verson s smlar to the orgnal mage. Wakatan et al (2002), proposes a dgtal watermarkng technque by shunnng the deformaton of the mage data n ROI by embeddng watermark nto areas other than the ROI. Watermark mage s compressed by a progressve codng algorthm whch s used as the sgnature nformaton. The proposed method can detect the sgnature mage wth moderate qualty from a clpped mage ncludng the ROI. Furthermore, by dvdng the contour of the ROI nto several regons and embeddng the sgnature nformaton n the regons respectvely, the sgnature mage wth moderate qualty can be acqured from a clpped mage ncludng only part of the ROI. Ths research proposes to use wavelet transform and BAT algorthm proposed by X.-S. Yang (2010) and Xn-She Yang (2012) for medcal mage watermarkng. The medcal mage s transformed nto wavelet doman usng a 2D DWT. The type of mother wavelet and level of scalng are two parameters that are of nterest to look for whle applyng the algorthm. Watermark n ths case s a patent mage. Ths patent mage s embedded nto the medcal cover mage n transform doman. The extracton process s a nverse algorthm to embeddng process. From the watermark embeddng and extracton process two performance parameters are computed n the form of peak-sgnal-to-nose rato (psnr) and normalzed cross correlaton (ncc). Ths procedure of watermarkng gves unpredctable outcomes for medcal mages as cover mages wth out of bounds psnr and ncc values. These unpredctable results of watermarkng algorthm can be controlled usng optmzaton algorthms such genetc algorthm (GA), partcle swarm optmzaton (PSO) and ant colony optmzaton (ANO). Ths research uses BAT algorthm for optmzng the psnr and ncc values durng watermark embeddng and extracton process. The results of smulaton show a better performance of BAT algorthm over GA and non optmzaton watermarkng process for medcal mages wth patent mage as watermark[28]. 3

4 The rest of the paper s organzed as follows. Secton 2 gves a bref ntroducton of dscrete wavelet transform and BAT algorthm (Altrngham (1996)). Secton 3 deals wth the process of watermarkng. Secton 4 gves medcal mage dewatermarkng algorthm. Results and dscusson n secton 5 present nsghts nto the use of multresoluton wavelet transform wth BAT for medcal mage watermarkng. Fnally conclusons are made on the medcal mage watermarkng procedures n secton WAVELET THEORY AND BAT ALGORITHM Ths research proposes the use of two most popular technques used n data encrypton and mage processng n computer communcatons for copyrght protecton. The watermarkng of the encrypted patent mage watermark nto a medcal mage s accomplshed usng 2D dscrete wavelet transform. The amount of watermark requred for producng a nformaton preservng watermark s done usng optmzng the values of psnr and ncc wth the help of BAT algorthm. Ths secton provdes the bascs of DWT and BAT algorthm used for medcal mage watermarkng. 2.1 Dscrete Wavelet Transform M Wavelet transform s appled to decompose a medcal mage I ( x, y) nto varous levels of abstracton A H V D,,, and can be reconstructed perfectly wth fewer number of wavelet coeffcents wthout compromsng on vsual qualty n P.V.V.Kshore et al (2011, 2012, 2012). The structure of Wavelet transform provdes an multlevel decomposton on mages, wth each level correspondng to a lesser resoluton compared to the prevous level as shown n fgure 3. Ths mult resoluton analyss of 2D DWT permts to decompose an mage nto approxmate and detals coeffcents. The 2D dscrete wavelet transform dvdes the mage nto low frequency (L) and hgh frequency components (H) at level1 usng 4 decomposton flters{ll_d, LH_D, HL_D, HH_D}. M The 2D medcal mage I ( x, y) passes through low pass flter and a downsampler of level 2 to produce approxmate mage at level-1 wavelet decomposton. Smlarly 2D medcal mage I ( x, y) s appled to a hgh pass flter and downsampler to create detaled mage at level-1 wavelet decomposton. Further n level2 decomposton the low frequency nformaton s agan dvded nto four LL, LH,HL and HH coeffcents. The hgh frequency detaled components n level1 are ntact. The second level decomposton also uses same set of decomposton flters as level-1. The wavelet decomposton process s shown n the fgure 3. M Fgure 3: Wavelet Decomposton of an Ultrasound Medcal based on 2D Flter Dscrete Wavelet 4 Transform

5 The noton L 2 (R 2 M ), where R s a set of real numbers, denote the fnte energy functon I ( x, y ) n R 2 ; and x,y n R. In two dmenson wavelet transform, a 2D scalng functon ( xy, ), and three two dmensonal wavelets, H ( xy, ), V ( xy, ) and D ( xy, ) are produced as shown n fgure 3. The above functons represent gray level varatons along dfferent drectons such as horzontal varatons, vertcal varatons and dagonal varatons. The DWT of I ( x, y ) of sze M N s M1N1 1 M 0 0 MN m0 n0 W ( j, m, n) I ( x, y) ( j, m, n) (1) Where j, m, n, M, N are ntegers, = {H, V, D}, j0 s an arbtrary startng scale and the coeffcents W defne an approxmaton of f at scale j 0. M1N1 1 M ( 0,, ) (, ) j, m, n MN x0 y0 W j m n I x y (2) The coeffcents n the above equaton add horzontal, vertcal and dagonal detals as shown n fgure.3.8 for scales j j0. The j, m, n and j, m, n denote scaled and translated bass functons as shown below, j, m, n j /2 j ( x, y) 2 (2 x m,2 n 1) j /2 j j, m, n M ( x, y) 2 (2 x m,2 n 1) Gven W and W, I ( x, y ) s obtaned va nverse DWT as: M1N1 1 W j0 j IM W j W W 0 j MN m0 n0 j j0 Eq.4 produces a watermarked medcal mage n spatal doman. 2.2 BAT Algorthm (4) BAT algorthm s a heurstc search and optmzaton algorthm based on echolocaton behavor of bats was proposed by Xn-She Yang(2010). Bats use sonar type of processng called, echolocaton, to locate prey, to avod obstructon and navgate through the dark nghts. Bats lsten to the echo s that are receved from the surroundng objects by transmttng a very loud sound pulse. Dfferent speces of bats use sound pulses wth dfferent propertes such as short frequency modulated sound pulses or constant frequency sound pulses. Ths echolocaton behavor of bats s devsed to optmze a gven objectve functon as proposed by Xn-She Yang(2010) s called BAT Algorthm(BA). The startng pont n BAT based optmzaton algorthm s to defne a objectve functon f x. Intalze a few parameters such as bat populaton x ( 1 to n) and ntal veloctes of bats v. Intalze pulse max frequency f at x. Pulse frequency can vary n the range f 0, f 1 to n. For a partcular optmzaton functon the soluton space can be adjusted by selectng frequency range close to sphere of nterest. Fnally ntalze pulse rate and loudness L. By selectng teratons tr to a specfc count, new solutons are generated by adjustng the frequences. Ths means the bats try to reach ther target M (3) 5

6 locaton by adjustng ther frequences and computng ther veloctes and locatons at each new frequency. Ths computaton can be mathematcally modeled as mn max mn f f f f (5) Where 0,1 s a unformly dstrbuted random vector. * tr tr1 tr v v x x f (6) * Where vtr 1 s the ntal velocty of the bat populaton. x s the current global best soluton,.e. locaton of the target whch s located after comparng all the solutons among all the n bats. The fnal or next best locaton of the target can be updated usng the followng mathematcal model xtr xtr 1 vtr (7) From eqn(7) t can be seen that the locaton or soluton space s updated wth the bat updated velocty n each teraton v tr. vtr n turn s derved from bat frequences or wavelengths as vtr ftr or f tr. Intally bat frequences are randomly allocated between [ f, f ], whch can be chosen based on the objectve functon that s beng mnmzed. The above process provdes a soluton space contanng global best postons of the n bats target. A local best soluton can be generated locally for each bat usng random walk n o tr x x L (8) n x s the new locaton or soluton space that s produced from mn max o x, the old global soluton space usng a loudness updaton factor wth a random constant 1,1. Further updaton of loudness are done between teratons. L and pulse rate n L ntal loudness can be set as 1 and the fnal loudness that s to be fn reached s set as L 0 ndcatng that the bat has fnally reached ts target where t stops temporarly ts search process. The new loudness factor can be mathematcally modeled as tr tr1 L L (9) Where s a constant. The pulse rate s updated as ( ) 0 1 tr tr e (10) Where s a constant. For our expermentaton both the defned constants are gven values rangng from 0 to 0.7 based on varous medcal cover mages used for watermarkng. A seres of experments are to be conducted to fx the values of loudness Ltr and pulse rate tr. For watermarkng smulatons usng medcal mages as cover mages the value of loudness vares L 0.5,1.5 and pulse rate 0.2, WATERMARK EMBEDDEDING tr. Watermarkng s wavelet doman s not new to researchers. Our prevous work N.Venkatram et al (2014), used dscrete wavelet transform to watermark medcal mages. Fgure 4 shows the watermarkng technque used by N.Venkatram et al Ths medcal mage watermarkng usng wavelet transform s modfed n ths research paper as shown n fgure 5. The modfcaton s proposed usng BAT algorthm to optmze the values of psnr and ncc to produce a good embeddng strength for the watermark. Our technque s very robust to attacks whch wll be demonstrated usng smulatons n secton 5. Medcal Images of standard resoluton are watermarked wth ther analogous patent mage as watermark of slghtly lower resoluton of usng the followng steps. S1. Carry out n th level 2D Dscrete Wavelet Transform (DWT) on the Medcal Image (Cover Image) (N.Venkatram et al (2014)) and decompose n to followng sub-bands (LL, LH, HL, HH). Where n s the tr 6

7 number of levels a wavelet s supposed to be decomposed. In our research we tred wth four dfferent levels.e. n=1, 2, 3 and 4. S2. The watermark s embedded usng the formula Sub e W(, j) W (, j) 2 (2 w ( k) 1) (11) Where W(, j) s watermarked medcal mage wth encrypted patent mage. W (, j) s n th level wavelet subbands of medcal mage. s the rato of standard devaton of wavelet coeffcent block and the maxmum standard devaton of all the coeffcent blocks. s the fxed embeddng watermark strength whch wll be found usng BAT algorthm n ths paper. w ( k) s the encrypted patent mage at k th poston. S3. Assemble all the modfed sub-bands and apply nverse 2D Wavelet Transform (IDWT) and s formulated as WM ( n) I W (12) 1 Where n represents 4 sub-bands for n=1, LL, LH, HL, HH. s the watermarked medcal mage. The WM watermarked medcal mage I s obtaned whch contans patent mage as watermark. S4. Compute embedded psnr and ncc values usng the watermarked medcal mage and orgnal medcal mage from equatons 14 and 15 n secton 5. S5. Intalze BAT algorthm parameters as dscussed n secton 2.2. The value of s estmated usng BAT algorthm. Psnr and ncc are used as objectve functons for optmzaton. Psnr should have a mnmum value and ncc should have a maxmum value less than 1. Proposed watermarkng s shown n fgure 5. e Sub Fgure 4. Medcal Image Watermarkng n Wavelet Doman 7

8 BAT algorthm returns value of by optmzng the values of psnr and ncc for embeddng the patent mage watermark nto the medcal cover mage. The value of s updated n every teraton tll optmum values of psnr and ncc are not reached. The only constrant n usng an optmzaton technque for medcal mage watermarkng s the tme for smulaton, whch n ths case s acheved wth teratons ranged tr 15,36. as 4. WATERMARK EXTRACTION PROCESS WM The watermarked medcal mage I s sent dstantly through unsecured nternet servers to expert medcal doctors from remote parts of the world. At the doctor s place the system decouples the attacked watermarked medcal mage form the watermark for authentcaton. The followng extracton process s ncorporated at the doctor s sde to extract the encrypted watermark patent mage and decrypt the patent watermark mage. S1. The possbly attacked watermark medcal mage s treated wth 2D dscrete wavelet transform (DWT) and decomposed to n th level wth n sub-bands LL, LH, HL and HH. S2. Medcal mage s decoupled from the patent watermark mage usng the nverse expresson RM M ep 2( W (, j) W (, j)) I ( x, y) (2 ) 1 RM Where W (, j) s transformed the receved watermarked medcal mage at th and j th locaton. M W (, j) s the subbands of orgnal cover mage that s receved wth the transmtted watermarked mage. ep I ( x, y) s the recovered watermark patent mage. S3. Extracted watermark s a patent mage whch agan s accomplshed usng a precse value of. Ths value s estmated usng BAT algorthm by computng values from extracted psnr and ncc objectve functons. An optmum value of s obtaned for extracton of watermarked medcal mages. Fnally authentcaton of the medcal mage s dentfed by extracted patent mage. 5. RESULTS AND DISCUSSION The proposed watermarkng method s put nto operaton on MATLAB software wth three dfferent types of medcal mages whch are consdered as cover mages. MRI, CT and Ultrasound medcal (US) mages are used as cover mages of standard resoluton Watermark s a patent mage of resoluton Snce medcal mages are gray scale mages, t s ntended to consder grayscale patent mage as watermark. The dynamc standard devaton rato factor σ s used for watermarkng n our experments whch s computed from wavelet coeffcents. The other scalng factor s estmated usng BAT algorthm. The estmaton of optmum embeddng strength, for mnmum value of psnr and maxmum value of ncc s used to embedded the patent watermark n the medcal cover mage. The performance of the proposed medcal mage watermarkng s judged by computng peak sgnal to nose rato (psnr) and normalzed cross correlaton coeffcent (ncc). These parameters wll decde the robustness of the watermarkng method usng DWT watermarkng process by most of the researchers. Watermarkng of medcal mages s relatvely susceptble process as the medcal mages contan nformaton related to lfe changng scenaros of human subject. Corrupton of the orgnal medcal mage by watermarkng process should be wthn the acceptable confnes of human percepton. The vsual (13) 8

9 senstvty of the watermarked and extracted mages s mathematcally represented by calculatng psnr and ncc. The values of psnr and ncc values are refned usng BAT algorthm to produce a watermarked medcal mage that exactly mmcs the orgnal medcal mage before watermarkng. 5.1 Embedded Peak Sgnal to Nose Rato (psnr) Embedded psnr [29] s the measure of peak error between orgnal mage and watermarked mage and s computed usng the followng expresson 2 M MN max(max( I ( x, y) psnr 10log (14) 10 2 M MI I ( x, y) W xn ym M Where N and M represent mage resoluton. I ( x, y) s the orgnal medcal mage and W s the watermarked medcal mage. psnr s the peak sgnal to nose rato n db whch range between 40db to 60 db generally for good watermarkng. 5.2 Extracted Normalzed Cross Correlaton Coeffcent (ncc) Normalzed cross correlaton [29] s mostly used by pattern recognton research for measurng smlarty between a query mage and the mages from the database. The cross correlaton s normalzed by subtractng the mean and dvdng by standard devaton. Embedded normalzed cross correlaton coeffcent gves the measure of closeness between watermarked mage and orgnal medcal mage. M ncc xn ym M M I ( x, y) W ( x, y) 2 2 M M I ( x, y) W ( x, y) xn ym xn ym (15) The values of normalzed cross correlaton coeffcents (ncc) range from 0 to 1. Larger values of ncc are preferred for better watermarkng. Fgure 6 shows a patent s skull CT along wth ts 2D dscrete wavelet transform. 2D DWT decomposes the medcal mage usng db2 mother wavelet to level-1 decomposton. All the medcal mages used n ths research are acqured from radology department of NRI medcal college and Hosptal at Guntur, Andhra Pradesh, INDIA. Fgure 6(a) shows orgnal bran CT mage of a patent. Fgure 6(b) shows a decomposed CT medcal mage usng db2 wavelet. 9 (a) (b)

10 (a) (b) Journal of Engneerng Technology CT bran medcal mage( ) s used as cover mage for watermarkng n fgure 7(a) and lena mage s used as patent mage(64 64) n fgure 7(b). DWT-BAT watermarkng procedure proposed n ths research embeds watermark patent mage nto bran CT cover mage to produce a watermarked medcal mage as shown n fgure 7(c). Fgure 7(d) shows the extracted watermark of patent mage. Vsually fgure 7 shows that the watermarked mage and extracted mage match powerfully as per human vsual system. Fgure 7: (a) Bran CT Cover Image (b) Watermark Patent Image (c) CT Watermarked Medcal Image (d) Extracted Watermark patent mage Fgure 7 shows the robustness of DWT-BAT algorthm. Smlar results are acqured usng MRI bran mage, fgures 8 and 9, and Ultrasound (US) Medcal mages, fgures 10 and 11 as cover mages. 10

11 Fgure 9: (a) MRI Bran Cover Image (b) Watermark Patent Image (c) MRI Watermarked Medcal Image (d) Extracted RSA Encrypted Watermark (e) Decrypted Watermark patent Image Wth KEY (a) (b) Fgure 10: Dscrete Wavelet Transform of Level -1 usng db2 mother wavelet (a) Orgnal pregnant ultrasound (US) Medcal Image (b) ts 2D DWT 11

12 From fgure 11(c) t can vsually be observed that the watermarkng process proposed n ths paper has actually removed nose from the ultrasound mage. At ths pont we want to hghlght the use of optmzaton technque such as BAT algorthm for watermarkng. Fgure 12 shows the comparson of DWT-BAT proposed n ths research to other watermarkng technques used by us [] for medcal mage watermarkng. Fgure 12.Vsual Comparson of (d) DWT-BAT wth three other medcal mage watermarkng methods used by us prevously (a) Only DWT (b) RSA-DWT (c) LWT-SVD Performance of the watermarkng methods s also formulated usng equatons 14 and 15 n Table-I for the embedded watermark and orgnal medcal mage for all three dfferent medcal mages. The values are computed for all our prevously accomplshed methods. The data analyss hghlghts the effectveness of the DWT-BAT watermarkng method for medcal mage watermarkng wth patent mage as a payload. Table-1: Embedded psnr and ncc for Medcal Cover Images for varous watermarkng methods 12

13 Watermarkng Method Cover Medcal Image PSNR (db) DWT RSA-DWT LWT-SVD DWT-BAT NCC PSNR (db) NCC PSNR (db) NCC PSNR (db) MRI CT Ultrasound(US) Performance plots usng embedded psnr and ncc are plotted from table-1 n the fgures 13 and 14 respectvely. From the graphs t can be confrmed that DWT-BAT outperforms the other watermarkng methods usng medcal mages of varous types. NCC Fgure 13. Comparson graph for watermarkng methods wth DWT-BAT usng embedded psnr values Fgure 14. Comparson plot for watermarkng Methods wth DWT-BAT usng ncc values The performance analyss for extracton of watermark and the qualty of medcal cover mage are very smlar to that of embeddng process for all the watermarkng methods. In the extracton process also there s a clear dstncton shown by DWT-BAT watermarkng algorthm whch outperformed all other methods. Computng normalzed cross correlaton coeffcent form equaton 15 for the extracted watermark patent mages reveals the performance of the RSA-DWT medcal Image watermarkng process. The values are put up n Table-2. The watermarked medcal mages are transmtted through unsecured networks and are most lkely to be attacked from varous unlawful hackers. Hence to test the robustness of the watermarkng method proposed n ths paper, varous attacks are smulated. The total number of attacks smulated for testng our DWT-BAT proposed watermarkng algorthm s 12. Generally the ncc coeffcent for better watermark s somethng above 0.75[16]. For remarkably excellent correlaton the value of ncc should be around or 1. A value of zero for ncc ndcates a complete uncorrelaton between the orgnal cover mage and the watermarked mage. Table-2 ncc values are computed for db2 wavelet at level-1 of watermarked mage. Table 2: Comparson of Extracted watermarks Cover Images DWT RSA-DWT LWT-SVD DWT-BAT Attacks MRI CT US MRI CT US MRI CT US MRI CT US Mean Flterng Medan Flterng Rotaton (45 ) Rotaton (135 ) Rotaton (225 ) Rotaton (315 ) Gaussan Nose

14 (0.001) Gaussan Nose (0.005) Gaussan Nose (0.01) Salt & Pepper Nose( ) Shear [x=1,y= ] Crop(10 0,100) The watermarked medcal mage s subjected to twelve attack categores such as a 3 3 wndow mean flterng, a 3 3 wndow medan flterng, 45, 90, 135 and 180 rotaton, Gaussan nose and salt & pepper nose of nose denstes 0.001,0.005,0.01 and 0.1, shear attack wth [x=1,y=0] and fnally crop wth crop area [100,100]. Table-2 shows the robustness of DWT-BAT under these attacks. Plottng the extracted ncc values of the patent mage watermark for varous technques wth three sets of medcal cover mages wll reveal the extraordnary qualty of watermarks produced by proposed DWT-BAT watermarkng algorthm. Fgure 15 plots ncc values of extracted patent mage watermarks for 4 watermarkng procedures aganst attacks wth MRI cover mages. Smlar plots are produced n fgures 16 and 17 for CT and US medcal cover mages. Fnally fgure 18 shows the dynamc range varatons n extracted watermark ncc values for three medcal cover mages n four dfferent watermarkng algorthms. Fgure 15:Plot showng Extracted ncc values for MRI Medcal cover mages aganst varous attacks for 4 watermarkng algorthms Fgure 16:Plot showng Extracted ncc values for CT Medcal cover mages aganst varous attacks for 4 watermarkng algorthms 14

15 Fgure 18. Box plot showng dynamc range of extracted watermark ncc values From the box plot of fgure 18, t s observable that the extracted ncc values for the proposed DWT- BAT watermarkng algorthm have produced a small dynamc range compared to our prevously smulated watermarkng algorthms under attacks for medcal mage watermarkng. Ths shows that the proposed DWT-BAT watermarkng for medcal mages can wthstand attacks and reproduce better qualty extracted watermarks. Vsual analyss of the attacked watermarked mages wth ther extracted medcal cover mages and watermark patent mages are shown n fgures for three types of medcal cover mages.e. MRI, CT and US respectvely. 15

16 Fgure 20. Extracted Patent mages from US Watermarked Images wth db2 after (a) 3 3 wndow mean attack,(b) medan attack,(c)-(f) rotaton attacks,(g)-(j) nose attack, and (k) shows shear attacks and (l) crop attacks Fgure 21. Attacked watermarked CT Images(a)Mean (b) Medan (c)gaussan Nose(.001) (d) Gaussan Nose(0.005)(e) Gaussan Nose(.01) (f) Salt & Pepper Nose(.001) (g) Rotaton (45 0 ) (h) Rotaton (135 0 ) () Rotaton (225 0 ) (j) Rotaton (315 0 ) (k) Shear attack(x-1,y=0) (l) Crop attack (100,100) 16

17 Fgure 23. Attacked watermarked CT Images(a)Mean (b) Medan (c)gaussan Nose(.001) (d) Gaussan Nose(0.005)(e) Gaussan Nose(.01) (f) Salt & Pepper Nose(.001) (g) Rotaton (45 0 ) (h) Rotaton (135 0 ) () Rotaton (225 0 ) (j) Rotaton (315 0 ) (k) Shear attack(x-1,y=0) (l) Crop attack (100,100) Fgure 24. Extracted Patent mages from US Watermarked Images wth db2 after (a) 3 3 wndow mean attack,(b) medan attack,(c)-(f) rotaton attacks,(g)-(j) nose attack, and (k) shows shear attacks and (l) crop attacks From fgures 19,21 and 23, t can be observed that the attacked watermarked medcal mages usng DWT-BAT algorthm produces remarkably good medcal mages wthout loss of nformaton related to patents health. The watermarked medcal mages after attacks are very close to orgnal medcal mages n both vsual qualty and quanttatvely usng psnr and ncc values from table-2. Smlarly extracted watermark patent mages from attacked watermarked medcal mages wth proposed DWT-BAT algorthm are of good qualty as shown n fgures 20, 22 and 24. Ths DWT-BAT watermarkng algorthm was tested for varous decomposton levels of dscrete wavelet transform and varous mother wavelets. The vsual qualty of watermarked medcal mages and ther extractons are almost smlar to that obtaned usng db2 17

18 wavelet at level-1. Hence DWT-BAT watermarkng algorthm s ndependent of mother wavelet and level of decomposton of the wavelet. Comparng Nose attacked watermarked mages n DWT-BAT wth other watermarkng algorthms proposed by us for medcal mage watermarkng s shown n fgure 25. From fgure 25 t s clear that DWT- BAT has produced exceptonally good watermarked medcal mages than the remanng wavelet based medcal mage watermarkng algorthms. Fgure 25. Nose attacked watermarked medcal mages usng (a) DWT based (b) RSA-DWT based (c) LWT-SVD based and (d) DWT-BAT based algorthms 6. CONCLUSION A DWT-BAT medcal mage watermarkng algorthm was proposed n ths research paper. Three dfferent types of medcal mages such as MRI, CT and US are used as cover mages and a patent mage s used as watermark to load the medcal mage. Medcal mage s loaded wth patent mage n wavelet transform doman. The amount of load from watermark s optmzed by usng BAT algorthm. Ths process of watermarkng helps n retanng the qualty of the medcal mage. Ths s mportant n many telemedcne applcatons. Testng of the proposed DWT-BAT watermarkng procedure s accomplshed by smulatng varous possble attacks on watermarked mages when transported through nternet. Expermental results show that the DWT-BAT algorthm demonstrates superor protecton on unsecured networks compared to normal DWT based watermarkng algorthms proposed earler. The expermental results prove ths fact vsually and mathematcally n ths paper. The proposed method does not put constrants on the resoluton of the watermarks used. The DWT-BAT watermarkng algorthm s also ndependent of mother wavelet and wavelet decomposton level. 18

19 REFRENCES: Cox I J, Kllan J, Leghton F T and Shamoon T, Secure Spread Spectrum Watermarkng for Multmeda. IEEE Transacton on Image Processng, vol.6, no,12, pp (1997). M.D. Swanson, M. Kobayash and A.H. Tewfk "Multmeda Data Embeddng and Watermarkng Technologes", Proceedngs of the IEEE, vol. 86, no. 6, pp (1998). Podlchuk, Chrstne I., and Wenjun Zeng. "Image-adaptve watermarkng usng vsual models." IEEE Journal on Selected Areas n Communcatons, vol.16, no. 4,pp (1998). Hartung, Frank, and Martn Kutter. "Multmeda watermarkng technques."proceedngs of the IEEE, vol. 87, no. 7 pp (1999). Haley, D., P. Jacobs, J. Smpson, and S. Doze. "An assessment framework for telemedcne applcatons." Journal of Telemedcne and Telecare 5, no. 3,pp (1999). Güler, Nhal Fatma, and Elf Derya Übeyl. "Theory and applcatons of telemedcne." Journal of Medcal Systems 26, no. 3 (2002): Haley, Davd, Rsto Rone, and Arto Ohnmaa. "Systematc revew of evdence for the benefts of telemedcne." Journal of Telemedcne and Telecare 8, no. suppl 1 (2002): 1-7. Smth, Anthony C., M. Bensnk, N. Armfeld, J. Stllman, and L. Cattery. "Telemedcne and rural health care applcatons." Journal of postgraduate medcne 51, no. 4 (2005). Anand, Deepth, and U. C. Nranjan. "Watermarkng medcal mages wth patent nformaton." In Engneerng n Medcne and Bology Socety, Proceedngs of the 20th Annual Internatonal Conference of the IEEE, vol. 2, pp IEEE, 1998 Zan, Jasn M., and Abdul RM Fauz. "Medcal mage watermarkng wth tamper detecton and recovery." In Engneerng n Medcne and Bology Socety, EMBS'06. 28th Annual Internatonal Conference of the IEEE, pp IEEE, Navas, K. A., and M. Saskumar. "Survey of medcal mage watermarkng algorthms." In Proc. Internaton Conf. Scences of Electroncs, Technologes of Informaton and Telecommuncatons, pp Jall, Zunera, and Anwar M. Mrza. "A revew of dgtal watermarkng technques for text documents." In Informaton and Multmeda Technology, ICIMT'09. Internatonal Conference on, pp IEEE, E.T. Ln and E.J. Delp "A Revew of Data Hdng n Dgtal Images", Proceedngs of the Image Processng, Image Qualty, Image Capture Systems Conference, PICS \'99, pp Boney, Laurence, Ahmed H. Tewfk, and Khaled N. Hamdy. "Dgtal watermarks for audo sgnals." In Multmeda Computng and Systems, 1996., Proceedngs of the Thrd IEEE Internatonal Conference on, pp IEEE, Wolfgang, Raymond B., Chrstne I. Podlchuk, and Edward J. Delp. "Perceptual watermarks for dgtal mages and vdeo." Proceedngs of the IEEE 87, no. 7 (1999): Nkolads, Nkos, and Ioanns Ptas. "Robust mage watermarkng n the spatal doman." Sgnal processng 66, no. 3 (1998): N.Venkatram, L.S.S.Reddy, P.V.V.Kshore, Multresoluton Medcal Image Watermarkng for Telemedcne Applcatons, CT Internatonal Journal of Dgtal Image Processng, Vol(6),Issue 1, Jan 2014,pp6-15. N.Venkatram, L.S.S.Reddy, P.V.V.Kshore, RAS-DWT based medcal mage watermarkng for telemedcne applcatons Journal of Theoretcal and Appled Informaton Technology, An Internatonal Journal, Vol(65),Issue 2, July ISSN: E.T. Ln and E.J. Delp "A Revew of Fragle Image Watermarks", Proceedngs of the Multmeda and Securty Workshop at ACM Multmeda\'99, pp Coatreux, G., H. Matre, B. Sankur, Y. Rolland, and R. Collorec. "Relevance of watermarkng n medcal magng." In Informaton Technology Applcatons n Bomedcne, Proceedngs IEEE EMBS Internatonal Conference on, pp IEEE, Gakoumak, A., S. Pavlopoulos, and D. Koutours. "A medcal mage watermarkng scheme based on wavelet transform." In Engneerng n medcne and bology socety, Proceedngs of the 25th annual nternatonal conference of the IEEE, vol. 1, pp IEEE,

20 Irany, Behrang Mehrbany, Xn Cndy Guo, and Dmtros Hatznakos. "A hgh capacty reversble multple watermarkng scheme for medcal mages." In Dgtal Sgnal Processng (DSP), th Internatonal Conference on, pp IEEE, Lavanya, A., and V. Natarajan. "Watermarkng patent data n encrypted medcal mages." Sadhana 37.Part 6 (2012). Inoue, H., Myazak, A., Yamamoto, A., & Katsura, T. (1998, October). A dgtal watermark based on the wavelet transform and ts robustness on mage compresson. In Image Processng, ICIP 98. Proceedngs Internatonal Conference on (Vol. 2, pp ). IEEE. Wakatan, Akyosh. "Dgtal watermarkng for ROI medcal mages by usng compressed sgnature mage." In System Scences, HICSS. Proceedngs of the 35th Annual Hawa Internatonal Conference on, pp IEEE, X.-S. Yang, A New Metaheurstc Bat-Inspred Algorthm, n: Nature Inspred Cooperatve Strateges for Optmzaton (NISCO 2010) (Eds. J. R. Gonzalez et al.), Studes n Computatonal Intellgence, Sprnger Berln, 284, Sprnger, (2010). Xn-She Yang and Amr H. Gandom, Bat Algorthm: A Novel Approach for Global Engneerng Optmzaton, Engneerng Computatons, Vol. 29, Issue 5, pp (2012). Altrngham, J. D.: Bats: Bology and Behavour, Oxford Unvesty Press, (1996). Kshore, P. V. V., & Rajesh Kumar, P. (2012). A Vdeo Based Indan Sgn Language Recognton System (INSLR) Usng Wavelet Transform and Fuzzy Logc. Internatonal Journal of Engneerng & Technology ( ), 4(5). Kshore, P. V. V., & Kumar, P. R. (2012). A Model For Real Tme Sgn Language recognton System. Internatonal Journal of Advanced Research n Computer Scence and Software Engneerng, vol.2,(6). Kshore, P. V. V., Kumar, P. R., Kumar, E. K., & Kshore, S. R. C. (2011). Vdeo Audo Interface for Recognzng Gestures of Indan Sgn. Internatonal Journal of Image Processng (IJIP), 5(4), 479. N.Venkatram, L.S.S.Reddy, P.V.V.Kshore, Blnd Medcal Image Watermarkng wth LWT SVD for Telemedcne Applcaton, WSEAS Transactons on sgnal processng, Vol(10),Issue 2, June

Hybrid Non-Blind Color Image Watermarking

Hybrid Non-Blind Color Image Watermarking Hybrd Non-Blnd Color Image Watermarkng Ms C.N.Sujatha 1, Dr. P. Satyanarayana 2 1 Assocate Professor, Dept. of ECE, SNIST, Yamnampet, Ghatkesar Hyderabad-501301, Telangana 2 Professor, Dept. of ECE, AITS,

More information

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers

Content Based Image Retrieval Using 2-D Discrete Wavelet with Texture Feature with Different Classifiers IOSR Journal of Electroncs and Communcaton Engneerng (IOSR-JECE) e-issn: 78-834,p- ISSN: 78-8735.Volume 9, Issue, Ver. IV (Mar - Apr. 04), PP 0-07 Content Based Image Retreval Usng -D Dscrete Wavelet wth

More information

Key-Selective Patchwork Method for Audio Watermarking

Key-Selective Patchwork Method for Audio Watermarking Internatonal Journal of Dgtal Content Technology and ts Applcatons Volume 4, Number 4, July 2010 Key-Selectve Patchwork Method for Audo Watermarkng 1 Ch-Man Pun, 2 Jng-Jng Jang 1, Frst and Correspondng

More information

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Parallelism for Nested Loops with Non-uniform and Flow Dependences Parallelsm for Nested Loops wth Non-unform and Flow Dependences Sam-Jn Jeong Dept. of Informaton & Communcaton Engneerng, Cheonan Unversty, 5, Anseo-dong, Cheonan, Chungnam, 330-80, Korea. seong@cheonan.ac.kr

More information

A Binarization Algorithm specialized on Document Images and Photos

A Binarization Algorithm specialized on Document Images and Photos A Bnarzaton Algorthm specalzed on Document mages and Photos Ergna Kavalleratou Dept. of nformaton and Communcaton Systems Engneerng Unversty of the Aegean kavalleratou@aegean.gr Abstract n ths paper, a

More information

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration

Improvement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,

More information

Enhanced Watermarking Technique for Color Images using Visual Cryptography

Enhanced Watermarking Technique for Color Images using Visual Cryptography Informaton Assurance and Securty Letters 1 (2010) 024-028 Enhanced Watermarkng Technque for Color Images usng Vsual Cryptography Enas F. Al rawashdeh 1, Rawan I.Zaghloul 2 1 Balqa Appled Unversty, MIS

More information

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching A Fast Vsual Trackng Algorthm Based on Crcle Pxels Matchng Zhqang Hou hou_zhq@sohu.com Chongzhao Han czhan@mal.xjtu.edu.cn Ln Zheng Abstract: A fast vsual trackng algorthm based on crcle pxels matchng

More information

An Image Fusion Approach Based on Segmentation Region

An Image Fusion Approach Based on Segmentation Region Rong Wang, L-Qun Gao, Shu Yang, Yu-Hua Cha, and Yan-Chun Lu An Image Fuson Approach Based On Segmentaton Regon An Image Fuson Approach Based on Segmentaton Regon Rong Wang, L-Qun Gao, Shu Yang 3, Yu-Hua

More information

Identify the Attack in Embedded Image with Steganalysis Detection Method by PSNR and RGB Intensity

Identify the Attack in Embedded Image with Steganalysis Detection Method by PSNR and RGB Intensity Internatonal Journal of Computer Systems (ISSN: 394-1065), Volume 03 Issue 07, July, 016 Avalable at http://www.jcsonlne.com/ Identfy the Attack n Embedded Image wth Steganalyss Detecton Method by PSNR

More information

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision SLAM Summer School 2006 Practcal 2: SLAM usng Monocular Vson Javer Cvera, Unversty of Zaragoza Andrew J. Davson, Imperal College London J.M.M Montel, Unversty of Zaragoza. josemar@unzar.es, jcvera@unzar.es,

More information

A Hybrid Semi-Blind Gray Scale Image Watermarking Algorithm Based on DWT-SVD using Human Visual System Model

A Hybrid Semi-Blind Gray Scale Image Watermarking Algorithm Based on DWT-SVD using Human Visual System Model A Hybrd Sem-Blnd Gray Scale Image Watermarkng Algorthm Based on DWT-SVD usng Human Vsual System Model Rajesh Mehta r Scence & Engneerng, USICT Guru Gobnd Sngh Indrarprastha Unversty New Delh, Inda rajesh00ust@gmal.com

More information

Robust Watermarking for Text Images Based on Arnold Scrambling and DWT-DCT

Robust Watermarking for Text Images Based on Arnold Scrambling and DWT-DCT Internatonal Conference on Mechatroncs Electronc Industral and Control Engneerng (MEIC 015) Robust Watermarkng for Text Images Based on Arnold Scramblng and DWT-DCT Fan Wu College of Informaton Scence

More information

Semi-Fragile Watermarking Scheme for Authentication of JPEG Images

Semi-Fragile Watermarking Scheme for Authentication of JPEG Images Tamkang Journal of Scence and Engneerng, Vol. 10, No 1, pp. 5766 (2007) 57 Sem-Fragle Watermarkng Scheme for Authentcaton of JPEG Images Chh-Hung n 1 *, Tung-Shh Su 2 and Wen-Shyong Hseh 2,3 1 Department

More information

Information Hiding Watermarking Detection Technique by PSNR and RGB Intensity

Information Hiding Watermarking Detection Technique by PSNR and RGB Intensity www..org 3 Informaton Hdng Watermarkng Detecton Technque by PSNR and RGB Intensty 1 Neha Chauhan, Akhlesh A. Waoo, 3 P. S. Patheja 1 Research Scholar, BIST, Bhopal, Inda.,3 Assstant Professor, BIST, Bhopal,

More information

Cluster Analysis of Electrical Behavior

Cluster Analysis of Electrical Behavior Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School

More information

Digital Video Watermarking using Discrete Wavelet Transform and Principal Component Analysis

Digital Video Watermarking using Discrete Wavelet Transform and Principal Component Analysis Internatonal Journal of Wsdom Based Computng, Vol. 1 (2), August 2011 7 Dgtal Vdeo Watermarkng usng Dscrete Wavelet Transform and Prncpal Component Analyss Sanjana Snha, Prajnat Bardhan, Swarnal Pramanck,

More information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data A Fast Content-Based Multmeda Retreval Technque Usng Compressed Data Borko Furht and Pornvt Saksobhavvat NSF Multmeda Laboratory Florda Atlantc Unversty, Boca Raton, Florda 3343 ABSTRACT In ths paper,

More information

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points;

Subspace clustering. Clustering. Fundamental to all clustering techniques is the choice of distance measure between data points; Subspace clusterng Clusterng Fundamental to all clusterng technques s the choce of dstance measure between data ponts; D q ( ) ( ) 2 x x = x x, j k = 1 k jk Squared Eucldean dstance Assumpton: All features

More information

High Payload Reversible Data Hiding Scheme Using Difference Segmentation and Histogram Shifting

High Payload Reversible Data Hiding Scheme Using Difference Segmentation and Histogram Shifting JOURNAL OF ELECTRONIC SCIENCE AND TECHNOLOGY, VOL. 11, NO. 1, MARCH 2013 9 Hgh Payload Reversble Data Hdng Scheme Usng Dfference Segmentaton and Hstogram Shftng Yung-Chen Chou and Huang-Chng L Abstract

More information

IAJIT First Online Publication

IAJIT First Online Publication Content Protecton n Vdeo Data Based on Robust Dgtal Watermarkng Resstant to Intentonal and Unntentonal Attacks Mad Masoum and Shervn Amr Department of Electrcal Engneerng, Islamc Azad Unversty Qazvn Branch,

More information

Adaptive digital watermarking of images using Genetic Algorithm

Adaptive digital watermarking of images using Genetic Algorithm Adaptve dgtal watermarkng of mages usng Genetc Algorthm Bushra Skander, Muhammad Ishtaq, M. Arfan Jaffar, Muhammad Tarq, Anwar M. Mrza Department of Computer Scence, Natonal Unversty of Computer and Emergng

More information

IMPLEMENTATION OF QIM BASED AUDIO WATERMARKING USING HYBRID TRANSFORM OF SWT-DCT-SVD METHODS OPTIMIZED WITH GENETIC ALORITHM

IMPLEMENTATION OF QIM BASED AUDIO WATERMARKING USING HYBRID TRANSFORM OF SWT-DCT-SVD METHODS OPTIMIZED WITH GENETIC ALORITHM IMPLEMENTATION OF QIM BASED AUDIO WATERMARKING USING HYBRID TRANSFORM OF SWT-DCT-SVD METHODS OPTIMIZED WITH GENETIC ALORITHM Ryan Amnullah 1, Gelar Budman 2, Irma Saftr 3 1, 2, 3 FakultasTeknk Elektro,

More information

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION

CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION 24 CHAPTER 2 PROPOSED IMPROVED PARTICLE SWARM OPTIMIZATION The present chapter proposes an IPSO approach for multprocessor task schedulng problem wth two classfcatons, namely, statc ndependent tasks and

More information

Load Balancing for Hex-Cell Interconnection Network

Load Balancing for Hex-Cell Interconnection Network Int. J. Communcatons, Network and System Scences,,, - Publshed Onlne Aprl n ScRes. http://www.scrp.org/journal/jcns http://dx.do.org/./jcns.. Load Balancng for Hex-Cell Interconnecton Network Saher Manaseer,

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization Problem efntons and Evaluaton Crtera for Computatonal Expensve Optmzaton B. Lu 1, Q. Chen and Q. Zhang 3, J. J. Lang 4, P. N. Suganthan, B. Y. Qu 6 1 epartment of Computng, Glyndwr Unversty, UK Faclty

More information

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach Angle Estmaton and Correcton of Hand Wrtten, Textual and Large areas of Non-Textual Document Images: A Novel Approach D.R.Ramesh Babu Pyush M Kumat Mahesh D Dhannawat PES Insttute of Technology Research

More information

Shape-adaptive DCT and Its Application in Region-based Image Coding

Shape-adaptive DCT and Its Application in Region-based Image Coding Internatonal Journal of Sgnal Processng, Image Processng and Pattern Recognton, pp.99-108 http://dx.do.org/10.14257/sp.2014.7.1.10 Shape-adaptve DCT and Its Applcaton n Regon-based Image Codng Yamn Zheng,

More information

Related-Mode Attacks on CTR Encryption Mode

Related-Mode Attacks on CTR Encryption Mode Internatonal Journal of Network Securty, Vol.4, No.3, PP.282 287, May 2007 282 Related-Mode Attacks on CTR Encrypton Mode Dayn Wang, Dongda Ln, and Wenlng Wu (Correspondng author: Dayn Wang) Key Laboratory

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

Determining the Optimal Bandwidth Based on Multi-criterion Fusion Proceedngs of 01 4th Internatonal Conference on Machne Learnng and Computng IPCSIT vol. 5 (01) (01) IACSIT Press, Sngapore Determnng the Optmal Bandwdth Based on Mult-crteron Fuson Ha-L Lang 1+, Xan-Mn

More information

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields

A mathematical programming approach to the analysis, design and scheduling of offshore oilfields 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 A mathematcal programmng approach to the analyss, desgn and

More information

An Image Compression Algorithm based on Wavelet Transform and LZW

An Image Compression Algorithm based on Wavelet Transform and LZW An Image Compresson Algorthm based on Wavelet Transform and LZW Png Luo a, Janyong Yu b School of Chongqng Unversty of Posts and Telecommuncatons, Chongqng, 400065, Chna Abstract a cylpng@63.com, b y27769864@sna.cn

More information

The Codesign Challenge

The Codesign Challenge ECE 4530 Codesgn Challenge Fall 2007 Hardware/Software Codesgn The Codesgn Challenge Objectves In the codesgn challenge, your task s to accelerate a gven software reference mplementaton as fast as possble.

More information

A NEW AUDIO WATERMARKING METHOD BASED

A NEW AUDIO WATERMARKING METHOD BASED A NEW AUDIO WATERMARKING METHOD BASED ON DISCRETE COSINE TRANSFORM WITH A GRAY IMAGE Mohammad Ibrahm Khan 1, Md. Iqbal Hasan Sarker 2, Kaushk Deb 3 and Md. Hasan Furhad 4 1,2,3 Department of Computer Scence

More information

Edge Detection in Noisy Images Using the Support Vector Machines

Edge Detection in Noisy Images Using the Support Vector Machines Edge Detecton n Nosy Images Usng the Support Vector Machnes Hlaro Gómez-Moreno, Saturnno Maldonado-Bascón, Francsco López-Ferreras Sgnal Theory and Communcatons Department. Unversty of Alcalá Crta. Madrd-Barcelona

More information

The Research of Ellipse Parameter Fitting Algorithm of Ultrasonic Imaging Logging in the Casing Hole

The Research of Ellipse Parameter Fitting Algorithm of Ultrasonic Imaging Logging in the Casing Hole Appled Mathematcs, 04, 5, 37-3 Publshed Onlne May 04 n ScRes. http://www.scrp.org/journal/am http://dx.do.org/0.436/am.04.584 The Research of Ellpse Parameter Fttng Algorthm of Ultrasonc Imagng Loggng

More information

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters Proper Choce of Data Used for the Estmaton of Datum Transformaton Parameters Hakan S. KUTOGLU, Turkey Key words: Coordnate systems; transformaton; estmaton, relablty. SUMMARY Advances n technologes and

More information

S1 Note. Basis functions.

S1 Note. Basis functions. S1 Note. Bass functons. Contents Types of bass functons...1 The Fourer bass...2 B-splne bass...3 Power and type I error rates wth dfferent numbers of bass functons...4 Table S1. Smulaton results of type

More information

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility

Evaluation of an Enhanced Scheme for High-level Nested Network Mobility IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.15 No.10, October 2015 1 Evaluaton of an Enhanced Scheme for Hgh-level Nested Network Moblty Mohammed Babker Al Mohammed, Asha Hassan.

More information

Enhanced AMBTC for Image Compression using Block Classification and Interpolation

Enhanced AMBTC for Image Compression using Block Classification and Interpolation Internatonal Journal of Computer Applcatons (0975 8887) Volume 5 No.0, August 0 Enhanced AMBTC for Image Compresson usng Block Classfcaton and Interpolaton S. Vmala Dept. of Comp. Scence Mother Teresa

More information

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010 Smulaton: Solvng Dynamc Models ABE 5646 Week Chapter 2, Sprng 200 Week Descrpton Readng Materal Mar 5- Mar 9 Evaluatng [Crop] Models Comparng a model wth data - Graphcal, errors - Measures of agreement

More information

TN348: Openlab Module - Colocalization

TN348: Openlab Module - Colocalization TN348: Openlab Module - Colocalzaton Topc The Colocalzaton module provdes the faclty to vsualze and quantfy colocalzaton between pars of mages. The Colocalzaton wndow contans a prevew of the two mages

More information

Robust Video Watermarking Using Image Normalization, Motion Vector and Perceptual Information

Robust Video Watermarking Using Image Normalization, Motion Vector and Perceptual Information Robust Vdeo Watermarkng Usng Image ormalzaton, Moton Vector and Perceptual Informaton Cedllo-Hernández Antono 1, Cedllo-Hernández Manuel 1, akano-myatake Marko 1, García-Vázquez Mreya S. 2 1 Postgraduate

More information

Brushlet Features for Texture Image Retrieval

Brushlet Features for Texture Image Retrieval DICTA00: Dgtal Image Computng Technques and Applcatons, 1 January 00, Melbourne, Australa 1 Brushlet Features for Texture Image Retreval Chbao Chen and Kap Luk Chan Informaton System Research Lab, School

More information

X- Chart Using ANOM Approach

X- Chart Using ANOM Approach ISSN 1684-8403 Journal of Statstcs Volume 17, 010, pp. 3-3 Abstract X- Chart Usng ANOM Approach Gullapall Chakravarth 1 and Chaluvad Venkateswara Rao Control lmts for ndvdual measurements (X) chart are

More information

Detection of an Object by using Principal Component Analysis

Detection of an Object by using Principal Component Analysis Detecton of an Object by usng Prncpal Component Analyss 1. G. Nagaven, 2. Dr. T. Sreenvasulu Reddy 1. M.Tech, Department of EEE, SVUCE, Trupath, Inda. 2. Assoc. Professor, Department of ECE, SVUCE, Trupath,

More information

A Comparison between Digital Images Watermarking in Tow Different Color Spaces Using DWT2*

A Comparison between Digital Images Watermarking in Tow Different Color Spaces Using DWT2* A Comparson between Dgtal s ng n Tow Dfferent Color Spaces Usng DWT* Mehd Khall Natonal Academy of Scence of Armena Yerevan, Armena e-mal: khall.mehd@yahoo.com ABSTRACT A novel dgtal watermarkng for ownershp

More information

Research of Multiple Text Watermarks Technique in Electric Power System Texts

Research of Multiple Text Watermarks Technique in Electric Power System Texts Sensors & Transducers 203 by IFSA http://www.sensorsportal.com Research of Multple Text atermarks Technque n Electrc Power System Texts Xao-X XING, Qng CHEN, 2 Lan-X FU School of Optcal-Electrcal and Computer

More information

KEYWORDS: Digital Image Watermarking, Discrete Wavelet Transform, General Regression Neural Network, Human Visual System. 1.

KEYWORDS: Digital Image Watermarking, Discrete Wavelet Transform, General Regression Neural Network, Human Visual System. 1. An Adaptve Dgtal Image Watermarkng Based on Image Features n Dscrete Wavelet Transform Doman and General Regresson Neural Network Ayoub Taher Group of IT Engneerng, Payam Noor Unversty, Broujen, Iran ABSTRACT:

More information

High-Boost Mesh Filtering for 3-D Shape Enhancement

High-Boost Mesh Filtering for 3-D Shape Enhancement Hgh-Boost Mesh Flterng for 3-D Shape Enhancement Hrokazu Yagou Λ Alexander Belyaev y Damng We z Λ y z ; ; Shape Modelng Laboratory, Unversty of Azu, Azu-Wakamatsu 965-8580 Japan y Computer Graphcs Group,

More information

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches Proceedngs of the Internatonal Conference on Cognton and Recognton Fuzzy Flterng Algorthms for Image Processng: Performance Evaluaton of Varous Approaches Rajoo Pandey and Umesh Ghanekar Department of

More information

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1)

For instance, ; the five basic number-sets are increasingly more n A B & B A A = B (1) Secton 1.2 Subsets and the Boolean operatons on sets If every element of the set A s an element of the set B, we say that A s a subset of B, or that A s contaned n B, or that B contans A, and we wrte A

More information

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch

Deep learning is a good steganalysis tool when embedding key is reused for different images, even if there is a cover source-mismatch Deep learnng s a good steganalyss tool when embeddng key s reused for dfferent mages, even f there s a cover source-msmatch Lonel PIBRE 2,3, Jérôme PASQUET 2,3, Dno IENCO 2,3, Marc CHAUMONT 1,2,3 (1) Unversty

More information

A Secured Method for Image Steganography Based On Pixel Values

A Secured Method for Image Steganography Based On Pixel Values A Secured Method for Image Steganography Based On Pxel Values Tarun Gulat #, Sanskrt Gupta * # Assocate Professor, Electroncs and Communcaton Engneerng Department, MMEC, M.M.U., Mullana, Ambala, Haryana,

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images Internatonal Journal of Informaton and Electroncs Engneerng Vol. 5 No. 6 November 015 Usng Fuzzy Logc to Enhance the Large Sze Remote Sensng Images Trung Nguyen Tu Huy Ngo Hoang and Thoa Vu Van Abstract

More information

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline

Image Representation & Visualization Basic Imaging Algorithms Shape Representation and Analysis. outline mage Vsualzaton mage Vsualzaton mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and Analyss outlne mage Representaton & Vsualzaton Basc magng Algorthms Shape Representaton and

More information

A Lossless Watermarking Scheme for Halftone Image Authentication

A Lossless Watermarking Scheme for Halftone Image Authentication IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.6 No.2B, February 2006 147 A Lossless Watermarkng Scheme for Halftone Image Authentcaton Jeng-Shyang Pan, Hao Luo, and Zhe-Mng Lu,

More information

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices

Steps for Computing the Dissimilarity, Entropy, Herfindahl-Hirschman and. Accessibility (Gravity with Competition) Indices Steps for Computng the Dssmlarty, Entropy, Herfndahl-Hrschman and Accessblty (Gravty wth Competton) Indces I. Dssmlarty Index Measurement: The followng formula can be used to measure the evenness between

More information

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance

Tsinghua University at TAC 2009: Summarizing Multi-documents by Information Distance Tsnghua Unversty at TAC 2009: Summarzng Mult-documents by Informaton Dstance Chong Long, Mnle Huang, Xaoyan Zhu State Key Laboratory of Intellgent Technology and Systems, Tsnghua Natonal Laboratory for

More information

Robust Blind Video Watermark Algorithm in Transform Domain Combining with 3D Video Correlation

Robust Blind Video Watermark Algorithm in Transform Domain Combining with 3D Video Correlation JOURNAL OF MULTIMEDIA, VOL. 8, NO. 2, APRIL 2013 161 Robust Blnd Vdeo Watermark Algorthm n Transform Doman Combnng wth 3D Vdeo Correlaton DING Ha-yang 1,3 1. Informaton Securty Center, Bejng Unversty of

More information

An Influence of the Noise on the Imaging Algorithm in the Electrical Impedance Tomography *

An Influence of the Noise on the Imaging Algorithm in the Electrical Impedance Tomography * Open Journal of Bophyscs, 3, 3, 7- http://dx.do.org/.436/ojbphy.3.347 Publshed Onlne October 3 (http://www.scrp.org/journal/ojbphy) An Influence of the Nose on the Imagng Algorthm n the Electrcal Impedance

More information

Steganography System using Slantlet Transform

Steganography System using Slantlet Transform ISSN:43-6999 Journal of Inmaton Communcaton and Intellgence Systems (JICIS) Volume Issue February 06 Steganography System usng Slantlet Transm Ryadh Bassl Abduljabbar Abstract An approach hdng nmaton has

More information

EVALUATION OF THE PERFORMANCES OF ARTIFICIAL BEE COLONY AND INVASIVE WEED OPTIMIZATION ALGORITHMS ON THE MODIFIED BENCHMARK FUNCTIONS

EVALUATION OF THE PERFORMANCES OF ARTIFICIAL BEE COLONY AND INVASIVE WEED OPTIMIZATION ALGORITHMS ON THE MODIFIED BENCHMARK FUNCTIONS Academc Research Internatonal ISS-L: 3-9553, ISS: 3-9944 Vol., o. 3, May 0 EVALUATIO OF THE PERFORMACES OF ARTIFICIAL BEE COLOY AD IVASIVE WEED OPTIMIZATIO ALGORITHMS O THE MODIFIED BECHMARK FUCTIOS Dlay

More information

Solving two-person zero-sum game by Matlab

Solving two-person zero-sum game by Matlab Appled Mechancs and Materals Onlne: 2011-02-02 ISSN: 1662-7482, Vols. 50-51, pp 262-265 do:10.4028/www.scentfc.net/amm.50-51.262 2011 Trans Tech Publcatons, Swtzerland Solvng two-person zero-sum game by

More information

Reducing Frame Rate for Object Tracking

Reducing Frame Rate for Object Tracking Reducng Frame Rate for Object Trackng Pavel Korshunov 1 and We Tsang Oo 2 1 Natonal Unversty of Sngapore, Sngapore 11977, pavelkor@comp.nus.edu.sg 2 Natonal Unversty of Sngapore, Sngapore 11977, oowt@comp.nus.edu.sg

More information

5.0 Quality Assurance

5.0 Quality Assurance 5.0 Dr. Fred Omega Garces Analytcal Chemstry 25 Natural Scence, Mramar College Bascs of s what we do to get the rght answer for our purpose QA s planned and refers to planned and systematc producton processes

More information

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS

A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Proceedngs of the Wnter Smulaton Conference M E Kuhl, N M Steger, F B Armstrong, and J A Jones, eds A MOVING MESH APPROACH FOR SIMULATION BUDGET ALLOCATION ON CONTINUOUS DOMAINS Mark W Brantley Chun-Hung

More information

Analysis of Continuous Beams in General

Analysis of Continuous Beams in General Analyss of Contnuous Beams n General Contnuous beams consdered here are prsmatc, rgdly connected to each beam segment and supported at varous ponts along the beam. onts are selected at ponts of support,

More information

Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm

Vectorization of Image Outlines Using Rational Spline and Genetic Algorithm 01 Internatonal Conference on Image, Vson and Computng (ICIVC 01) IPCSIT vol. 50 (01) (01) IACSIT Press, Sngapore DOI: 10.776/IPCSIT.01.V50.4 Vectorzaton of Image Outlnes Usng Ratonal Splne and Genetc

More information

Lecture #15 Lecture Notes

Lecture #15 Lecture Notes Lecture #15 Lecture Notes The ocean water column s very much a 3-D spatal entt and we need to represent that structure n an economcal way to deal wth t n calculatons. We wll dscuss one way to do so, emprcal

More information

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method Internatonal Journal of Computatonal and Appled Mathematcs. ISSN 89-4966 Volume, Number (07), pp. 33-4 Research Inda Publcatons http://www.rpublcaton.com An Accurate Evaluaton of Integrals n Convex and

More information

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity

Corner-Based Image Alignment using Pyramid Structure with Gradient Vector Similarity Journal of Sgnal and Informaton Processng, 013, 4, 114-119 do:10.436/jsp.013.43b00 Publshed Onlne August 013 (http://www.scrp.org/journal/jsp) Corner-Based Image Algnment usng Pyramd Structure wth Gradent

More information

Data Hiding and Image Authentication for Color-Palette Images

Data Hiding and Image Authentication for Color-Palette Images Data Hdng and Image Authentcaton for Color-Palette Images Chh-Yang Yn ( 殷志揚 ) and Wen-Hsang Tsa ( 蔡文祥 ) Department of Computer & Informaton Scence Natonal Chao Tung Unversty 00 Ta Hsueh Rd., Hsnchu, Tawan

More information

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints Australan Journal of Basc and Appled Scences, 2(4): 1204-1208, 2008 ISSN 1991-8178 Sum of Lnear and Fractonal Multobjectve Programmng Problem under Fuzzy Rules Constrants 1 2 Sanjay Jan and Kalash Lachhwan

More information

Classifier Selection Based on Data Complexity Measures *

Classifier Selection Based on Data Complexity Measures * Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.

More information

An Optimal Algorithm for Prufer Codes *

An Optimal Algorithm for Prufer Codes * J. Software Engneerng & Applcatons, 2009, 2: 111-115 do:10.4236/jsea.2009.22016 Publshed Onlne July 2009 (www.scrp.org/journal/jsea) An Optmal Algorthm for Prufer Codes * Xaodong Wang 1, 2, Le Wang 3,

More information

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation Intellgent Informaton Management, 013, 5, 191-195 Publshed Onlne November 013 (http://www.scrp.org/journal/m) http://dx.do.org/10.36/m.013.5601 Qualty Improvement Algorthm for Tetrahedral Mesh Based on

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

Learning the Kernel Parameters in Kernel Minimum Distance Classifier Learnng the Kernel Parameters n Kernel Mnmum Dstance Classfer Daoqang Zhang 1,, Songcan Chen and Zh-Hua Zhou 1* 1 Natonal Laboratory for Novel Software Technology Nanjng Unversty, Nanjng 193, Chna Department

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS ARPN Journal of Engneerng and Appled Scences 006-017 Asan Research Publshng Network (ARPN). All rghts reserved. NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS Igor Grgoryev, Svetlana

More information

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION

Overview. Basic Setup [9] Motivation and Tasks. Modularization 2008/2/20 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Overvew 2 IMPROVED COVERAGE CONTROL USING ONLY LOCAL INFORMATION Introducton Mult- Smulator MASIM Theoretcal Work and Smulaton Results Concluson Jay Wagenpfel, Adran Trachte Motvaton and Tasks Basc Setup

More information

Wishing you all a Total Quality New Year!

Wishing you all a Total Quality New Year! Total Qualty Management and Sx Sgma Post Graduate Program 214-15 Sesson 4 Vnay Kumar Kalakband Assstant Professor Operatons & Systems Area 1 Wshng you all a Total Qualty New Year! Hope you acheve Sx sgma

More information

Analysis of Collaborative Distributed Admission Control in x Networks

Analysis of Collaborative Distributed Admission Control in x Networks 1 Analyss of Collaboratve Dstrbuted Admsson Control n 82.11x Networks Thnh Nguyen, Member, IEEE, Ken Nguyen, Member, IEEE, Lnha He, Member, IEEE, Abstract Wth the recent surge of wreless home networks,

More information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

User Authentication Based On Behavioral Mouse Dynamics Biometrics User Authentcaton Based On Behavoral Mouse Dynamcs Bometrcs Chee-Hyung Yoon Danel Donghyun Km Department of Computer Scence Department of Computer Scence Stanford Unversty Stanford Unversty Stanford, CA

More information

A New Approach For the Ranking of Fuzzy Sets With Different Heights

A New Approach For the Ranking of Fuzzy Sets With Different Heights New pproach For the ankng of Fuzzy Sets Wth Dfferent Heghts Pushpnder Sngh School of Mathematcs Computer pplcatons Thapar Unversty, Patala-7 00 Inda pushpndersnl@gmalcom STCT ankng of fuzzy sets plays

More information

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning Outlne Artfcal Intellgence and ts applcatons Lecture 8 Unsupervsed Learnng Professor Danel Yeung danyeung@eee.org Dr. Patrck Chan patrckchan@eee.org South Chna Unversty of Technology, Chna Introducton

More information

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1

A New Feature of Uniformity of Image Texture Directions Coinciding with the Human Eyes Perception 1 A New Feature of Unformty of Image Texture Drectons Concdng wth the Human Eyes Percepton Xng-Jan He, De-Shuang Huang, Yue Zhang, Tat-Mng Lo 2, and Mchael R. Lyu 3 Intellgent Computng Lab, Insttute of Intellgent

More information

Novel Fuzzy logic Based Edge Detection Technique

Novel Fuzzy logic Based Edge Detection Technique Novel Fuzzy logc Based Edge Detecton Technque Aborsade, D.O Department of Electroncs Engneerng, adoke Akntola Unversty of Tech., Ogbomoso. Oyo-state. doaborsade@yahoo.com Abstract Ths paper s based on

More information

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines

A Modified Median Filter for the Removal of Impulse Noise Based on the Support Vector Machines A Modfed Medan Flter for the Removal of Impulse Nose Based on the Support Vector Machnes H. GOMEZ-MORENO, S. MALDONADO-BASCON, F. LOPEZ-FERRERAS, M. UTRILLA- MANSO AND P. GIL-JIMENEZ Departamento de Teoría

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

Positive Semi-definite Programming Localization in Wireless Sensor Networks Postve Sem-defnte Programmng Localzaton n Wreless Sensor etworks Shengdong Xe 1,, Jn Wang, Aqun Hu 1, Yunl Gu, Jang Xu, 1 School of Informaton Scence and Engneerng, Southeast Unversty, 10096, anjng Computer

More information

Dynamic Code Block Size for JPEG 2000

Dynamic Code Block Size for JPEG 2000 Dynamc Code Block Sze for JPEG 2000 Png-Sng Tsa a, Yann LeCornec b a Dept. of Computer Scence, Unv. of Texas Pan Amercan, 1201 W. Unv. Dr., Ednburg, TX USA 78539-2999; b Sgma Desgns, Inc., 1778 McCarthy

More information

CS 534: Computer Vision Model Fitting

CS 534: Computer Vision Model Fitting CS 534: Computer Vson Model Fttng Sprng 004 Ahmed Elgammal Dept of Computer Scence CS 534 Model Fttng - 1 Outlnes Model fttng s mportant Least-squares fttng Maxmum lkelhood estmaton MAP estmaton Robust

More information

Research Article High Capacity Reversible Watermarking for Audio by Histogram Shifting and Predicted Error Expansion

Research Article High Capacity Reversible Watermarking for Audio by Histogram Shifting and Predicted Error Expansion e Scentfc World Journal, Artcle ID 656251, 7 pages http://dx.do.org/1.1155/214/656251 Research Artcle Hgh Capacty Reversble Watermarkng for Audo by Hstogram Shftng and Predcted Error Expanson Fe Wang,

More information

Feature Reduction and Selection

Feature Reduction and Selection Feature Reducton and Selecton Dr. Shuang LIANG School of Software Engneerng TongJ Unversty Fall, 2012 Today s Topcs Introducton Problems of Dmensonalty Feature Reducton Statstc methods Prncpal Components

More information

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition

Novel Pattern-based Fingerprint Recognition Technique Using 2D Wavelet Decomposition Mathematcal Methods for Informaton Scence and Economcs Novel Pattern-based Fngerprnt Recognton Technque Usng D Wavelet Decomposton TUDOR BARBU Insttute of Computer Scence of the Romanan Academy T. Codrescu,,

More information

Smoothing Spline ANOVA for variable screening

Smoothing Spline ANOVA for variable screening Smoothng Splne ANOVA for varable screenng a useful tool for metamodels tranng and mult-objectve optmzaton L. Rcco, E. Rgon, A. Turco Outlne RSM Introducton Possble couplng Test case MOO MOO wth Game Theory

More information

Mathematics 256 a course in differential equations for engineering students

Mathematics 256 a course in differential equations for engineering students Mathematcs 56 a course n dfferental equatons for engneerng students Chapter 5. More effcent methods of numercal soluton Euler s method s qute neffcent. Because the error s essentally proportonal to the

More information

A Hybrid Digital Image Watermarking based on Discrete Wavelet Transform, Discrete Cosine Transform, and General Regression Neural Network

A Hybrid Digital Image Watermarking based on Discrete Wavelet Transform, Discrete Cosine Transform, and General Regression Neural Network A Hybrd Dgtal Image Watermarkng based on Dscrete Wavelet Transform, Dscrete Cosne Transform, and General Regresson Neural Network Ayoub Taher ; ABSTRACT In ths paper, a new hybrd dgtal watermarkng technque

More information

Simulation Based Analysis of FAST TCP using OMNET++

Simulation Based Analysis of FAST TCP using OMNET++ Smulaton Based Analyss of FAST TCP usng OMNET++ Umar ul Hassan 04030038@lums.edu.pk Md Term Report CS678 Topcs n Internet Research Sprng, 2006 Introducton Internet traffc s doublng roughly every 3 months

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and

More information

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr)

Helsinki University Of Technology, Systems Analysis Laboratory Mat Independent research projects in applied mathematics (3 cr) Helsnk Unversty Of Technology, Systems Analyss Laboratory Mat-2.08 Independent research projects n appled mathematcs (3 cr) "! #$&% Antt Laukkanen 506 R ajlaukka@cc.hut.f 2 Introducton...3 2 Multattrbute

More information