Using Counter-propagation Neural Network for Digital Audio Watermarking
|
|
- Nathaniel Hensley
- 5 years ago
- Views:
Transcription
1 Usng Counter-propagaton Neural Network for Dgtal Audo Watermarkng Chuan-Yu Chang and Wen-Chh Shen Graduate School of Computer Scence and Informaton Engneerng Natonal Yunln Unversty of Scence & Technology Doulou, Yunln, Tawan Abstract Recently, the watermarkng s an mportant technque to protect copyrght, whch allows authentc watermark to be hdden n multmeda such as dgtal mage, vdeo and audo. Watermarkng has been developed to protect dgtal meda llegal reproductons and modfcatons. Tradtonally, watermarkng requre complex procedures to embed and to extract watermark, such as randomzng the watermark, choose postons to embed and extract the watermark, embed the randomzed watermark nto the orgnal audo and extracted the watermark from the specfc postons. Therefore, n ths paper, we propose a scheme called Counter-propagaton Neural Network (CNN) for dgtal audo watermarkng. Dfferent from the tradtonal methods, the watermark s embedded n the synapses of CNN nstead of the orgnal audo sgnal. The expermental results show that the has capabltes of robustness, mperceptblty and authentcty. Keywords: Dgtal watermark, Counter-propagaton neural network, Audo nformaton hdng.. Introducton The rapd growng of computer network and multmeda technologes makes t easer to access dgtal meda. Therefore, t s urgent to protect copyrght pracy. To tackle the copyrght protects problem, many dgtal watermarkng schemes have been proposed[-4]. The watermarkng technque embeds owner s nformaton nto dgtal meda and provdes the correspondng authentcaton mechansm. Therefore, the dgtal watermarkng should has capabltes of robustness, mperceptblty and authentcty. Smlarly, the audo watermarkng should be naudble or statstcal nvsble to prevent unauthorzed detecton and removal. In general, the audo watermarkng technques can be classfed nto two groups, embeddng watermark n tme doman and embeddng watermark n frequency doman, dependng on the processng doman of the host audo n whch the watermark s embedded. In tme doman, the pre-maskng and post-maskng effect of tme doman s used to mplement audo watermarkng. Le et al. [8] proposed a method, whch based on the relatve energy relatons between adjacent sample sectons, to embed dgtal watermarks nto a host audo sgnal n the tme doman. However, ther method cannot resst four types of attacks, such as the AAC compresson, WMA compresson, Ampltude compresson and resamplng. In frequency doman, Jong et al. [6] proposed a watermark embeddng scheme accomplshes the perceptual transparency after watermark embeddng by explotng the maskng effect of the human audtory system (HAS). Lee et al. [7] proposed a dgtal audo watermarkng technque n the cepstrum doman. They nsert a dgtal watermark nto the cepstral components of the audo sgnal usng a technque analogous to spread spectrum communcatons, hdng a narrow hand sgnal n a wdeband channel. Recently, neural networks, wth ther features of fault tolerance and potental for adaptve tranng, have been proposed as alternatve approaches. Yang et al. [4] proposed an artfcal neural network-based scheme for watermarkng of audo sgnals. They use a mult-layer perceptron (MLP) to estmate the watermark scalng factor (WSF) ntellgently from the knowledge of host audo sgnal. Despte that, all the mentoned methods [4,6,7,8] were lack of robustness n audo watermarkng. In addton, the tradtonal methods need complex embeddng and correspondng extracton procedures. Therefore, n ths paper we proposed a specfc counter-propagaton neural network (CNN) for audo watermarkng. Dfferent from the tradtonal methods, the watermark s embedded n the synapses of CNN nstead of the orgnal audo sgnal. Therefore, the qualty of the watermarked audo s almost same as the orgnal audo sgnal. In addton, because of the watermark s stored n the synapses, most of the attacks are not degrade the qualty of the extracted watermark mage. The CNN substtutes the complex embeddng and correspondng extracton procedure. The expermental results show that the proposed CNN does not need complex embeddng and correspondng extracton procedure. Furthermore, the has capabltes of robustness, mperceptblty and authentcty. The remander of ths paper s organzed as follows. Secton shows the preprocessng of
2 orgnal audo sgnal. The archtecture of the CNN and the algorthm of embeddng, and extractng method are shown n Secton 3. Secton 4 summarzes the expermental results. Fnally, conclusons are gven n the Secton 5.. Preprocessng of orgnal audo sgnal In order to resst the malcously attacks, the orgnal audo sgnal s frstly segmented nto several non-overlappng frames wth frame sze of N. The synchronzaton code sequence s ntalzed the startng pont poston [8]. Ths assumpton wll be volated when an attacker tres to crop the sgnal or nsert redundancy n the front end. The audo energy s usng to evaluate the adequate frame to embed watermark, the energy of each frame s calculated as: n E ( k ) = n = s( ), k =,,..., N () where E(k) denotes the energy of frame k, and the s() represents the magntude of audo sgnal and n s the number of frame sze. The canddate frames set X (k) s obtaned by threshold of energy. The threshold s to search the poston of the non-quet sound segment, and sutable embeddng the watermark. The qualty of the extracted watermark s hghly dependng on the preprocessng procedure. Fgure shows the schematc dagram of the preprocessng. After the preprocessng, each canddate frame data X can be represented as a vector form: X = { x, x,..., x n} () where n s the length of canddate frames. Orgnal Audo Frame segmentaton Synchronzaton code E(n)>T Fgure.The schematc dagram of the preprocessng. False True Canddate Frame X(n) 3. Counter-propagaton neural network for audo watermarkng The tradtonal watermarkng methods requre complex embeddng and correspondng extracton procedures. In ths paper, a counter-propagaton neural network-based (CNN) audo watermarkng method s proposed. The proposed watermarkng method ntegrated the embeddng and extracton procedure nto a counter-propagaton neural network. Fgure shows the archtecture of the CNN. The CNN s conssts of n nput neurons to represent the length of canddate frame data, N hdden neurons to represent the total pxels of the watermark mage and m output neurons to represent the gray value of the watermark mage. In order to ensure that the proposed CNN has capablty of embeddng and extractng watermarks, the canddate frame data and the correspondng watermark are used to tran the CNN. After the network s evoluton, the watermark s embedded nto the synapses between the hdden layer and output layer. Audo Data X x x xn Input layer Fgure. The archtecture of the counter-propagaton neural network for watermarkng. There are two sets of weghts that are adjusted wth two dfferent learnng algorthms, the Konhones s self-organzng learnng and the Grossberg s supervsed learnng. In the frst stage, weghts W connectng the canddate frame data X and the hdden layer are traned usng Kohonen s self-organzng learnng rule, and acheve the goal to classfy tranng pattern to hdden layer. In the second stage, the weghts between the hdden layer and the output layer are traned usng Grossberg s learnng algorthm. The nput canddate frame vector X s fully connected to the neurons n hdden layer wth weghts W. W = w, w,..., } (3) where w j, w, w N,n Konhones s layer z z zn Hdden layer {,, w N, n denotes the weght between j-th neuron and nput x, =,,..., n. Accordngly, the total nput of the j-th neuron s defned as: / Extracted Watermark Y u, u m,n Grossberg s layer n Z j = ( x w j, ), j =,,..., N (4) = whch represents the total dstance between the nput X and the weghts of the j-th hdden neuron. After the dstances are computed, a wnner-takes-all mechansm s appled to the neurons n the hdden layer to fnd the wnner neuron unt to update weghts n the konhones s layer [5]. The wnner of the hdden neuron H * s defned as: H* = mn Z j, j =,,..., N (5) accordngly, the weghts between the nput layer and wnner neuron n hdden layer s update by: y y ym Output layer
3 ( x w ( )) wh *, ( k + ) = wh *, ( k) + η ( k) H*, k (6) where η(k) s learnng rate. In addton, the learnng rate η(k) s decreased gradually durng the tranng epoch k. The learnng functon η(k) can be specfed as follows: k η ( k ) = η ( 0 ) exp (7) k 0 where η (0) s ntal learnng rate, k 0 s a postve constant. The output of the CNN can be represented as vector form: Y = y, y,..., y } (8) { m where m s the bt length of watermark mage n bnary representaton. Each output neuron receves all the output of hdden neurons wth weghts U. U = u, u,..., } (9) where {,, u m, N u l, j denotes the weght between the j-th neuron n hdden layer and the l-th output neuron. Thus, the output of the -th neuron n the output layer s obtaned as y = N j= u Z, j j (0) Snce the WTA, only the wnng neuron H * n the hdden layer has output value one. Thus, the output of the -th output neuron can be smpled as: y = () * u,h Therefore, only the weghts connectng the wnnng neuron n the hdden layer wth the neurons n the output layer wll be updated. Accordngly, the weghts n the output layer of the CNN are updated as: u * ( k + ) = u * + η ( k) ( desre y ( )) () k l, H l, H l l where desre l s pxel value of the watermark mage. The learnng functon η(k) s calculated by Eq (7). In addton, the nstantaneous output error ξ q s defned as: m ξ = y desre (3) q l= l l Thus, the total error of the CNN s defned as N ξ = ξ (4) total q= q where N denotes the total pxels of the watermark mage. 3. Embeddng algorthm The watermark embeddng approach s summarzed as follows: Input: The canddate frame data X. Output: The watermark mage wll be embedded nto the synapse (W, U) of the converged CNN. Step.Arbtrarly assgns the ntal weghts to W and U. Step.Use Eq. (4) to calculate the output of each hdden neuron. Step 3.Use Eq. (5) to fnd the wnner neuron. Step 4.Update the weghts W accordng to Eq. (6). Step 5.Use Eq. () to update weght U. Step 6.Use Eq. (4) to calculate the output error of CNN. If ξ total s less than a predefned threshold value, stop tranng. Otherwse, go to Step. 3. Extractng algorthm To extract watermark from the traned CNN descrbed n Secton 3., the watermark extractng approach s summarzed as follows: Input: The canddate frame data X. Output: watermarked mage Y. Step.Use Eq. (4), Eq. (5) to calculate the output of the wnner neuron n hdden layer. Step.Use Eq.(8) and Eq.() to obtan the graylevel (n bnary) of the watermark mage Y. 4. Expermental results To show the proposed CNN has good capablty for audo watermarkng, four experments are presented to demonstrate robustness, mperceptblty and authentcty. In our experments, 6bts mono-track audo musc wth samplng rate 44. khz was used for smulaton. We selected three dfferent types of song from the database randomly. Fgures 3(a-c) show the orgnal audo wave of female snger, male snger and chorus, respectvely. Fgures 4 (a-b) show the 3 3 bnary rabbt mage and the 3 3 grayscale YUNTECH watermark mage, respectvely. In order to evaluate the robustness of the Le s method [8] and the proposed CNN method, two publc doman software: GoldWave and ImTOO are used to attack the watermarked audos. Eght types of attack are performed to attack the watermarked audos: Type : MP3 compresson, compress audo sgnal to 8k bt/s (wav->mp3->wav). Type : AAC compresson, compress audo sgnal to 8k bt/s (wav->aac->wav), MPEG-. Type 3: WMA compresson, compress audo sgnal to 8k bt/s (wav->wma->wav). Type 4: Ampltude compresson, multpler 6 db Type 5: Smoother flter. Type 6: Resamplng (44kHz->kHz ->44kHz). Type 7: Remove nose (clearly audble). Type 8: Slence reducton, reducton -48 db. The Normalzed Correlaton (NC) s used to evaluate the smlarty measurement of extracted
4 bnary watermark, whch can be represented as: P (, j ) P (, j ) (5) j NC = [ P (, j ) ] j where P (, j ) and P (, j ) represent the bt value of (,j)-th pxel of orgnal watermark and extracted watermark mage, respectvely. The Peak Sgnal to Nose Rato (PSNR) s used to evaluate the qualty of watermarked audo, whch can be represented as: PSNR ( db ) = 0 log 0 X peak (6) σ e where s defned as: σ e M ( X ( ) Z() M = σ e = ) (7) where M s the length of the host audo, X () s the magntude of host audo at tme. Smlarly, Z() denotes the magntude of watermarked audo at tme. X peak denotes the squared peak value of host audo. The hgher PSNR means that the watermarked audo s more smlar to the orgnal audo. frame N s 300. The ntal d of the Le s method [8] s set to The bnary rabbt watermark s embedded nto three orgnal audos. In order to evaluate the robustness of Le s method, the eght knds of attacks were appled to the watermarked audos. Fgures 5-7 show the extracted watermarks of the female snger, male snger, and chorus snger that suffered from eght dfferent type attacks. Obvously, Le s method cannot extract the complete watermark from varous attacks, such as AAC, WMA, Ampltude compresson, and resamplng result n messy pattern. In other words, the hded watermark has been destroyed by varous attacks. Fgure 5. The extracted watermarks of the watermarked audo by female snger (a) (b) Fgure 6. The extracted watermarks of the watermarked audo by male snger (c) Tme ( sec.) Fgure 3. Orgnal Audo Sgnals, (a) female snger, (b) male snger, (a) chorus snger. (a) (b) Fgure 4. Watermark mages, (a) bnary Rabbt mage (b) gray scale YUNTECH logo mage. 4. Experment : Robust testng for Le s method In ths experment, the watermark mage s a 3 3 bnary rabbt mage and the sze of audo Fgure 7. The extracted watermarks of watermarked audo chorus snger. Table. NC and bt error of extracted watermark from dfferent type of attack wth watermarked audo by Le s method NC of extracted bt error(3x3 bt) watermark female male chorus female male chorus Table shows the NC values and the bt error of Type
5 the extracted watermarks. From Table, the NC values are between 0.54 to The low NC values ndcate that the Le s method was unable to resst type (,3,4,6) attacks. 4. Experment : Robust testng for Fgure 8. The extracted watermarks of watermarked audo female snger. Fgure 9. The extracted watermarks of watermarked audo male snger. Fgure 0. The extracted watermarks of watermarked audo chorus snger. Table. NC and bt error of extracted watermark from dfferent type of attack wth watermarked audo by proposed CNN method NC of extracted bt error(3x3 bt) watermark Type female male chorus female male chorus In ths evaluaton, the ntal learnng rate η s set to.35. The number of neuron s 3 3 (sze of watermark mage). The threshold value of was establshed to termnate tranng. In order to evaluate the robustness of, eght knds of attacks are appled to degrade the watermarked audo. Fgures 8-0 show the extracted watermarks of watermarked audo that suffered from the same attacks as the prevous experment. Obvously, all the watermarks are extracted completely by usng CNN. Table shows the NC value and the bt error of extracted watermarks. It ndcates the proposed method s robust and beng able to resst eght attacks. 4.3 Experment 3: Imperceptblty for To show the mperceptblty of the proposed method, a bnary rabbt watermark and a gray scale Yuntech logo mage are embedded nto the three songs, respectvely. However, only a bnary rabbt watermark s embedded nto the three songs n Le s method. Table 3 shows the PSNR values of the watermarked audos by Le s and the proposed method. The average PSNR value of the Le s method s about 3dB. On the other hand, the PSNR values of the are all nfnte. The nfnte PSNR values llustrate that the watermarked audo sgnal s the same as the orgnal audos. Ths s because of the watermark s embedded n the synapses of CNN nstead of the orgnal audo sgnal; therefore, the qualty of the watermarked audo s almost same as the orgnal audo sgnal. It ndcates the s able to mperceptblty. Fgure (a-c) shows the extracted correspondng watermarks. These fgures show that the proposed method s capable of embeddng/extractng gray level watermark nto/from audo. Table 3. PSNR of watermarked audo by Le s method and the female male chorus Watermarked bnary mage by Le s method Watermarked bnary mage by Watermarked graylevel mage by 3.88dB 30.9dB 33.4dB (a) (b) (c) Fgure. The extracted watermarks from attack-free female, male and chorus snger, respectvely. 4.4 Experment 4: Authentcty testng In ths experment, we use raw audo, audo wthout embedded watermark, to test authentcty of the proposed CNN and Le s method. Fgure (a-c) and Fgure 3(a-c) show the extracted watermarks
6 from Le s and the, respectvely. Obvously, both Fg. and Fg. 3 are not legal watermark mages. These expermental results show that the proposed CNN can not extract legal watermark from the raw orgnal audo. Therefore, the has ablty to extract correspondng watermark from watermarked audos, but not from unmarked audos. (a) (b) (c) Fgure. The extracted watermarks of Fg. (a-c) for Le s method. (a) (b) (c) Fgure 3. The extracted watermarks of Fg. 3(a-c) for. 5. Conclusons In ths paper, we proposed a counter-propagaton neural network (CNN) for audo watermarkng. Dfferent from the tradtonal methods, the watermark s embedded n the synapses of CNN nstead of the orgnal audo. Therefore, the qualty of the watermarked audo s almost same as the orgnal audo. The proposed CNN does not need the orgnal audo to extract the watermark. In addton, because of the watermark s stored n the synapses, most of the attacks could not degrade the qualty of the extracted watermark mage. Thus, the proposed CNN has capablty to resst varous attacks. The watermark embeddng procedure and extractng procedure s ntegrated nto the proposed CNN. Therefore, the s smple than tradtonal methods. The expermental results show that the has good capabltes of robustness, mperceptblty and authentcty. IEEE Int. Conf. on Networkng, Sensng and Control, pp , 005. [3] Cvejc, N, Seppanen, T., Increasng robustness of LSB audo steganography usng a novel embeddng method, Pro. of the IEEE Int. Conf. on Infor. Tech.: Codng and Computng, Vol, pp ,.004. [4] Hujuan Yang, Patra, J.C., Chan, C.W., An artfcal neural network-based scheme for robust watermarkng of audo sgnals, Proc. of the IEEE Int.l Conf. on Acou., Spe., and Sg., Vol, pp , 00. [5] Fredrc M. Ham and Ivca Kostanc, Prncples of Neurocomputng for Scence & Engneerng, McGraw-Hll, Sngapore, 00. [6] Jong Won Seok and Jn Woo Hong, Audo watermarkng for copyrght protecton of dgtal audo data, Elec. Let., Vol 37, pp. 60-6, 00. [7] Sang-Kwang Lee and Yo-Sung Ho, Dgtal Audo Watermarkng n the Cepstrum Doman, Proc. of the IEEE Trans. on Con. Elect., Vol 46, pp , Aug [8] Wen-Nung Le and L-Chun Chang, "Robust and hgh-qualty tme-doman audo watermarkng subject to psychoacoustc maskng," Proc.of the IEEE nt. Symp. on Crc. and Sys., pp.45-48, 00. Acknowledgement Ths work was supported by the Natonal Scence Councl, Tawan, R.O.C. under Grants NSC 9-3-E References [] Arttameeyanant, P., Kumhom, P., Chamnongtha, K., "Audo watermarkng for Internet," Proc. of the IEEE Int. Conf. on Indust. Tech., Vol, pp , 00. [] Chuan-Yu Chang, Sheng-Jyun Su, "The applcaton of a full counterpropagaton neural network to mage watermarkng," Proc. of the
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 informationHybrid 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 informationA 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 informationSemi-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 informationImprovement 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 informationOutline. Self-Organizing Maps (SOM) US Hebbian Learning, Cntd. The learning rule is Hebbian like:
Self-Organzng Maps (SOM) Turgay İBRİKÇİ, PhD. Outlne Introducton Structures of SOM SOM Archtecture Neghborhoods SOM Algorthm Examples Summary 1 2 Unsupervsed Hebban Learnng US Hebban Learnng, Cntd 3 A
More informationContent 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 informationData 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 informationMachine Learning 9. week
Machne Learnng 9. week Mappng Concept Radal Bass Functons (RBF) RBF Networks 1 Mappng It s probably the best scenaro for the classfcaton of two dataset s to separate them lnearly. As you see n the below
More informationClassifying Acoustic Transient Signals Using Artificial Intelligence
Classfyng Acoustc Transent Sgnals Usng Artfcal Intellgence Steve Sutton, Unversty of North Carolna At Wlmngton (suttons@charter.net) Greg Huff, Unversty of North Carolna At Wlmngton (jgh7476@uncwl.edu)
More informationA 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 informationA 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 informationKEYWORDS: 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 informationA 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 informationA 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 informationRobust 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 informationEnhanced 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 informationLearning 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 informationA 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 informationA 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 informationPerformance Analysis of Data Hiding in MPEG-4 AAC Audio *
TSINGHUA SCIENCE AND TECHNOLOGY ISSNll1007-0214ll07/21llpp55-61 Volume 14, Number 1, February 2009 Performance Analyss of Data Hdng n MPEG-4 AAC Audo * XU Shuzheng ( ) **, ZHANG Peng ( ), WANG Pengjun
More informationInformation 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 informationIdentify 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 informationRobust 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 informationAn 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 informationA Robust Webpage Information Hiding Method Based on the Slash of Tag
Advanced Engneerng Forum Onlne: 2012-09-26 ISSN: 2234-991X, Vols. 6-7, pp 361-366 do:10.4028/www.scentfc.net/aef.6-7.361 2012 Trans Tech Publcatons, Swtzerland A Robust Webpage Informaton Hdng Method Based
More informationEnhanced 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 informationResearch and Application of Fingerprint Recognition Based on MATLAB
Send Orders for Reprnts to reprnts@benthamscence.ae The Open Automaton and Control Systems Journal, 205, 7, 07-07 Open Access Research and Applcaton of Fngerprnt Recognton Based on MATLAB Nng Lu* Department
More informationResearch 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 informationSubspace 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 informationTerm Weighting Classification System Using the Chi-square Statistic for the Classification Subtask at NTCIR-6 Patent Retrieval Task
Proceedngs of NTCIR-6 Workshop Meetng, May 15-18, 2007, Tokyo, Japan Term Weghtng Classfcaton System Usng the Ch-square Statstc for the Classfcaton Subtask at NTCIR-6 Patent Retreval Task Kotaro Hashmoto
More informationRobust 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 informationDeep 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 informationCluster 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 informationHigh 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 informationThe Research of Support Vector Machine in Agricultural Data Classification
The Research of Support Vector Machne n Agrcultural Data Classfcaton Le Sh, Qguo Duan, Xnmng Ma, Me Weng College of Informaton and Management Scence, HeNan Agrcultural Unversty, Zhengzhou 45000 Chna Zhengzhou
More informationAn Improved Neural Network Algorithm for Classifying the Transmission Line Faults
1 An Improved Neural Network Algorthm for Classfyng the Transmsson Lne Faults S. Vaslc, Student Member, IEEE, M. Kezunovc, Fellow, IEEE Abstract--Ths study ntroduces a new concept of artfcal ntellgence
More informationPerformance Assessment and Fault Diagnosis for Hydraulic Pump Based on WPT and SOM
Performance Assessment and Fault Dagnoss for Hydraulc Pump Based on WPT and SOM Be Jkun, Lu Chen and Wang Zl PERFORMANCE ASSESSMENT AND FAULT DIAGNOSIS FOR HYDRAULIC PUMP BASED ON WPT AND SOM. Be Jkun,
More informationA 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 informationTsinghua 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 informationAn 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 informationVirtual Machine Migration based on Trust Measurement of Computer Node
Appled Mechancs and Materals Onlne: 2014-04-04 ISSN: 1662-7482, Vols. 536-537, pp 678-682 do:10.4028/www.scentfc.net/amm.536-537.678 2014 Trans Tech Publcatons, Swtzerland Vrtual Machne Mgraton based on
More informationFast Feature Value Searching for Face Detection
Vol., No. 2 Computer and Informaton Scence Fast Feature Value Searchng for Face Detecton Yunyang Yan Department of Computer Engneerng Huayn Insttute of Technology Hua an 22300, Chna E-mal: areyyyke@63.com
More informationParallelism 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 informationA 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 informationThe 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 informationLecture 5: Multilayer Perceptrons
Lecture 5: Multlayer Perceptrons Roger Grosse 1 Introducton So far, we ve only talked about lnear models: lnear regresson and lnear bnary classfers. We noted that there are functons that can t be represented
More informationRobust and Reversible Relational Database Watermarking Algorithm Based on Clustering and Polar Angle Expansion
Robust and Reversble Relatonal Database Watermarkng Algorthm Based on Clusterng and Polar Angle Expanson Zhyong L, Junmn Lu and Wecheng Tao College of Informaton Scence and Engneerng, Hunan Unversty, Changsha,
More informationShape-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 informationArticle Reversible Dual-Image-Based Hiding Scheme Using Block Folding Technique
Artcle Reversble Dual-Image-Based Hdng Scheme Usng Block Foldng Technque Tzu-Chuen Lu, * and Hu-Shh Leng Department of Informaton Management, Chaoyang Unversty of Technology, Tachung 4349, Tawan Department
More informationA PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION
1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute
More informationIAJIT 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 informationShape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram
Shape Representaton Robust to the Sketchng Order Usng Dstance Map and Drecton Hstogram Department of Computer Scence Yonse Unversty Kwon Yun CONTENTS Revew Topc Proposed Method System Overvew Sketch Normalzaton
More informationBrushlet 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 informationA 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 informationTN348: 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 informationOutline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1
4/14/011 Outlne Dscrmnatve classfers for mage recognton Wednesday, Aprl 13 Krsten Grauman UT-Austn Last tme: wndow-based generc obect detecton basc ppelne face detecton wth boostng as case study Today:
More informationAdaptive 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 informationClassifier 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 informationFace Recognition Based on SVM and 2DPCA
Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty
More informationMULTISPECTRAL 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 informationResearch 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 informationEdge 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 informationRelated-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 informationKOHONEN'S SELF ORGANIZING NETWORKS WITH "CONSCIENCE"
Kohonen's Self Organzng Maps and ther use n Interpretaton, Dr. M. Turhan (Tury) Taner, Rock Sold Images Page: 1 KOHONEN'S SELF ORGANIZING NETWORKS WITH "CONSCIENCE" By: Dr. M. Turhan (Tury) Taner, Rock
More informationIMPLEMENTATION 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 informationFace Recognition Based on Neuro-Fuzzy System
IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.9 No.4, Aprl 2009 39 Face Recognton Based on Neuro-Fuzzy System Nna aher Makhsoos, Reza Ebrahmpour and Alreza Hajany Department of
More informationReal-time Motion Capture System Using One Video Camera Based on Color and Edge Distribution
Real-tme Moton Capture System Usng One Vdeo Camera Based on Color and Edge Dstrbuton YOSHIAKI AKAZAWA, YOSHIHIRO OKADA, AND KOICHI NIIJIMA Graduate School of Informaton Scence and Electrcal Engneerng,
More informationA 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 informationBootstrapping Color Constancy
Bootstrappng Color Constancy Bran Funt and Vlad C. Carde * Smon Fraser Unversty Vancouver, Canada ABSTRACT Bootstrappng provdes a novel approach to tranng a neural network to estmate the chromatcty of
More informationComparison Study of Textural Descriptors for Training Neural Network Classifiers
Comparson Study of Textural Descrptors for Tranng Neural Network Classfers G.D. MAGOULAS (1) S.A. KARKANIS (1) D.A. KARRAS () and M.N. VRAHATIS (3) (1) Department of Informatcs Unversty of Athens GR-157.84
More informationVol. 5, No. 3 March 2014 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved.
Journal of Emergng Trends n Computng and Informaton Scences 009-03 CIS Journal. All rghts reserved. http://www.csjournal.org Unhealthy Detecton n Lvestock Texture Images usng Subsampled Contourlet Transform
More informationDetection 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 informationUser 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 informationIMPACT OF RADIO MAP SIMULATION ON POSITIONING IN INDOOR ENVIRONTMENT USING FINGER PRINTING ALGORITHMS
IMPACT OF RADIO MAP SIMULATION ON POSITIONING IN INDOOR ENVIRONTMENT USING FINGER PRINTING ALGORITHMS Jura Macha and Peter Brda Unversty of Zlna, Faculty of Electrcal Engneerng, Department of Telecommuncatons
More informationSRBIR: Semantic Region Based Image Retrieval by Extracting the Dominant Region and Semantic Learning
Journal of Computer Scence 7 (3): 400-408, 2011 ISSN 1549-3636 2011 Scence Publcatons SRBIR: Semantc Regon Based Image Retreval by Extractng the Domnant Regon and Semantc Learnng 1 I. Felc Raam and 2 S.
More informationNovel 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 informationConvolutional interleaver for unequal error protection of turbo codes
Convolutonal nterleaver for unequal error protecton of turbo codes Sna Vaf, Tadeusz Wysock, Ian Burnett Unversty of Wollongong, SW 2522, Australa E-mal:{sv39,wysock,an_burnett}@uow.edu.au Abstract: Ths
More informationA Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems
A Unfed Framework for Semantcs and Feature Based Relevance Feedback n Image Retreval Systems Ye Lu *, Chunhu Hu 2, Xngquan Zhu 3*, HongJang Zhang 2, Qang Yang * School of Computng Scence Smon Fraser Unversty
More informationMusic/Voice Separation using the Similarity Matrix. Zafar Rafii & Bryan Pardo
Musc/Voce Separaton usng the Smlarty Matrx Zafar Raf & Bryan Pardo Introducton Muscal peces are often characterzed by an underlyng repeatng structure over whch varyng elements are supermposed Propellerheads
More informationFEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur
FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents
More informationDetermining 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 informationAn 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 informationHigh-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 informationQuantization Noise Power Injection In Subband Audio Coding Using Low Selectivity Filter Banks
Quantzaton Nose Power Injecton In Subband Audo Codng Usng Low Selectvty Flter Banks D. ARTÍNEZ -UÑOZ, N. RUIZ-REYES, P. VERA-CANDEAS, P.J. RECHE-LÓPEZ, J. CURPIÁN-ALONSO Departamento de Electrónca Unversdad
More informationDiscriminative Dictionary Learning with Pairwise Constraints
Dscrmnatve Dctonary Learnng wth Parwse Constrants Humn Guo Zhuoln Jang LARRY S. DAVIS UNIVERSITY OF MARYLAND Nov. 6 th, Outlne Introducton/motvaton Dctonary Learnng Dscrmnatve Dctonary Learnng wth Parwse
More informationInvariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm
Proceedngs of the 5th WSEAS Int. Conf. on Sgnal Processng, Robotcs and Automaton, Madrd, Span, February 5-7, 6 (pp4-45) Invarant Shape Obect Recognton Usng B-Splne, Cardnal Splne, and Genetc Algorthm PISIT
More informationPCA Based Gait Segmentation
Honggu L, Cupng Sh & Xngguo L PCA Based Gat Segmentaton PCA Based Gat Segmentaton Honggu L, Cupng Sh, and Xngguo L 2 Electronc Department, Physcs College, Yangzhou Unversty, 225002 Yangzhou, Chna 2 Department
More informationMachine Learning: Algorithms and Applications
14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of
More informationResearch Article Improved Encrypted-Signals-Based Reversible Data Hiding Using Code Division Multiplexing and Value Expansion
Securty and Communcaton Networks Volume 2018, Artcle ID 1326235, 9 pages https://do.org/10.1155/2018/1326235 Research Artcle Improved Encrypted-Sgnals-Based Reversble Data Hdng Usng Code Dvson Multplexng
More informationSimulation 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 informationConcurrent Apriori Data Mining Algorithms
Concurrent Apror Data Mnng Algorthms Vassl Halatchev Department of Electrcal Engneerng and Computer Scence York Unversty, Toronto October 8, 2015 Outlne Why t s mportant Introducton to Assocaton Rule Mnng
More informationAn Improved Image Segmentation Algorithm Based on the Otsu Method
3th ACIS Internatonal Conference on Software Engneerng, Artfcal Intellgence, Networkng arallel/dstrbuted Computng An Improved Image Segmentaton Algorthm Based on the Otsu Method Mengxng Huang, enjao Yu,
More informationContours Planning and Visual Servo Control of XXY Positioning System Using NURBS Interpolation Approach
Inventon Journal of Research Technology n Engneerng & Management (IJRTEM) ISSN: 2455-3689 www.jrtem.com olume 1 Issue 4 ǁ June. 2016 ǁ PP 16-23 Contours Plannng and sual Servo Control of XXY Postonng System
More informationEfficient Video Coding with R-D Constrained Quadtree Segmentation
Publshed on Pcture Codng Symposum 1999, March 1999 Effcent Vdeo Codng wth R-D Constraned Quadtree Segmentaton Cha-Wen Ln Computer and Communcaton Research Labs Industral Technology Research Insttute Hsnchu,
More informationParallel Inverse Halftoning by Look-Up Table (LUT) Partitioning
Parallel Inverse Halftonng by Look-Up Table (LUT) Parttonng Umar F. Sddq and Sadq M. Sat umar@ccse.kfupm.edu.sa, sadq@kfupm.edu.sa KFUPM Box: Department of Computer Engneerng, Kng Fahd Unversty of Petroleum
More informationAudio Content Classification Method Research Based on Two-step Strategy
(IJACSA) Internatonal Journal of Advanced Computer Scence and Applcatons, Audo Content Classfcaton Method Research Based on Two-step Strategy Sume Lang Department of Computer Scence and Technology Chongqng
More informationA CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION
A CALCULATION METHOD OF DEEP WEB ENTITIES RECOGNITION 1 FENG YONG, DANG XIAO-WAN, 3 XU HONG-YAN School of Informaton, Laonng Unversty, Shenyang Laonng E-mal: 1 fyxuhy@163.com, dangxaowan@163.com, 3 xuhongyan_lndx@163.com
More informationLocal Quaternary Patterns and Feature Local Quaternary Patterns
Local Quaternary Patterns and Feature Local Quaternary Patterns Jayu Gu and Chengjun Lu The Department of Computer Scence, New Jersey Insttute of Technology, Newark, NJ 0102, USA Abstract - Ths paper presents
More informationFuzzy 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