We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors

Size: px
Start display at page:

Download "We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors"

Transcription

1 We ae IntechOpen, the wold s leadng publshe of Open Access books Bult by scentsts, fo scentsts 3, , Open access books avalable Intenatonal authos and edtos Downloads Ou authos ae among the 154 Countes delveed to OP 1% most cted scentsts 1.% Contbutos fom top 500 unvestes Selecton of ou books ndexed n the Book Ctaton Index n Web of Scence Coe Collecton (BKCI) Inteested n publshng wth us? Contact book.depatment@ntechopen.com Numbes dsplayed above ae based on latest data collected. Fo moe nfomaton vst

2 11 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues Lpng Hu 1, Hongwe Lu and Hongcheng Yn 1 1 Natonal Key Laboatoy of aget and Envonment Electomagnetc Scatteng and Radaton, Bejng Insttute of Envonmental Chaactestcs, Bejng, Natonal Key Laboatoy of Rada Sgnal Pocessng, Xdan Unvesty, X an, Chna 1. Intoducton In ecent yeas, ada Automatc aget Recognton (AR) based on taget synthetc apetue ada (SAR) mages has eceved moe and moe attentons. So fa, many lteatues based on SAR publc dataset ae eleased, whch focus on the SAR taget ecognton elated technques ncludng taget segmentaton, featue extacton, classfe desgn, and so on. A template matchng was poposed (Ross et al., 1998). Suppot Vecto achne (SV) has been appled to SAR AR (Zhao & Pncpe, 001; Byant & Gabe, 1999). he dawbacks of them ae that none of them have any pe-pocessng and featue extacton. Howeve, effcent pe-pocessng and featue extacton may help to mpove ecognton pefomance. Pncpal Component Analyss (PCA) s a classcal featue extacton technque. But when PCA s used fo mages featue extacton, D mage matces must be pevously tansfomed nto 1D mage vectos. hs usually leads to a hgh dmensonal vecto space, whee t s dffcult to evaluate the covaance matx accuately. o solve ths poblem, -dmensonal PCA (DPCA) fo mage featue extacton s poposed (Yang et al., 004). As opposed to PCA, DPCA constucts the covaance matx dectly usng D mage matces athe than 1D vectos, and evaluates the covaance matx moe accuately. oeove, the sze of the covaance matx s much smalle. A dawback of DPCA s that t only elmnates the coelatons between ows. So t needs moe featues, and ths wll lead to lage stoage equements and cost moe tme n classfcaton phase. o futhe compess dmenson of featues, two-stage DPCA s appled n ths chapte. he emande of ths chapte s oganzed as follows: n Secton, the SAR mages pepocessng method s descbed. DPCA s fst evewed, and two-stage DPCA s descbed n Secton 3. In Secton 4, classfes ae descbed. In Secton 5 and 6, expemental esults based on ovng and Statonay aget Acquston and Recognton (SAR) data and conclusons ae pesented.

3 00 Pncpal Component Analyss Engneeng Applcatons. SAR mage pe-pocessng he ognal SAR mages povded by SAR contan not only tagets of ou nteest, but also backgound cluttes, as shown n Fg. 1 (a). If tagets ae ecognzed based the ognal mages, cluttes would depess the system pefomance. hus, t s necessay to pe-pocess the ognal mages to segment tagets fom backgound cluttes..1 Logathmc tansfomaton We tansfom the ognal mages usng logathm conveson, whch can convet speckles fom multple model to addtonal model and make the mage hstogam moe sutable be appoxmated wth a Gaussan dstbuton. he logathmc tansfomaton s gven by xy xy G, 10lg F, (1) whee Fdenotes the magntude matx of the ognal SAR mage. Snce the logathm s not defned at 0, we add an abtay constant (fo example 0.001) to the ognal mage befoe the logathm. o ensue the pxel values to be nonnegatve, we add a coespondng constant (30).. Adaptve theshold segmentaton In ode to obtan the taget mage, the adaptve theshold segmentaton method s adopted. Fst of all, estmatng the mean and the vaance of the cuent mageg, fo each pxel x, y of G, a, a, 1, G, xy, B, xy, 0, else x y x y f x y c ac a Whee a, Bac denote the taget and the backgound espectvely, c can be obtaned statstcally fom tanng samples..3 ophologcal flte and geometc clusteng opeaton Due to the pesence of speckles, the esult of theshold segmentaton contans not only taget, but smalle objects nevtably, as shown n Fg. 1 (b). o emove these small objects and obtan smoothng the taget mage, mophologcal flte (Gonzalez &Woods, 00) and geometc clusteng opeaton (usman & Ke, 1996) ae adopted to a. ophologcal flte ams to smooth bounday, emove shap potusons, fll small concaves, emove small holes, jont gaps, and so on. In geneal, flteed mage a may also contan some non-taget egons, whch ae much smalle than taget tself, as shown n Fg. 1 (c). o emove small egons, we apply geometc clusteng opeaton: fstly, detect and label all the ndependent connected egons n a. hen, compute aeas fo each egon. he lagest egon s of ou nteest. In ths way, we obtan the esultng a, as shown n Fg. 1 (d). Ovelayng the esultng a on the logathmc mage G obtans taget ntensty. ()

4 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 01 (a) (b) (c) (d) Fg. 1. SAR mage pe-pocessng (takng 7 fo example). (a) Ognal mage, (b) Logathmc mage, (c) heshold segmented mage, (d) Result of the mophologcal flteng, (e) Result of geometc clusteng. (e)

5 0 Pncpal Component Analyss Engneeng Applcatons (a) (b) (c) (d) Fg.. SAR mage pe-pocessng (takng BR70 fo example). (a) Ognal mage, (b) Logathmc mage, (c) heshold segmented mage, (d) Result of the mophologcal flteng, (e) Result of geometc clusteng. (e)

6 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 03 (a) (b) (c) (d) Fg. 3. SAR mage pe-pocessng (takng BP fo example). (a) Ognal mage, (b) Logathmc mage, (c) heshold segmented mage, (d) Result of the mophologcal flteng, (e) Result of geometc clusteng. (e)

7 04 Pncpal Component Analyss Engneeng Applcatons.4 Image enhancement and nomalzaton Image enhancement (Gonzalez &Woods, 00) can weaken o elmnate some useless nfomaton and gve pomnence to some useful nfomaton, whch ams to enhance mage qualty by adoptng a cetan technology fo a specfc applcaton. Hee, we apply the powe-law tansfomaton to enhance the taget mage xy, xy, K H (3) wheeh,k denotes the fome and latte tansfomed mage espectvely, s an constant. In pactce, due to the dffeence of the dstance between a taget and ada, the ntensty of echoes dffes geatly. hus, t s necessay to nomalze the mage. Hee, a nomalzed method adopted s J xy, K x y xy, K xy, (4) whee J, K denotes the fome and latte nomalzed mage espectvely. Due to the uncetanty of taget locaton n a scene, -dmensonal fast Foue tansfom (DFF) s appled. Only half of the ampltude of Foue s used as nputs of featue extacton due to ts tanslaton nvaance and symmetc popety, so that t can decease the dmenson of samples and educe computaton. 3. Featue extacton Featue extacton s a key pocedue n SAR AR. If all pxels of an mage ae egaded as featues, ths would esult n lage equements, hgh computaton and pefomance loss. heefoe, t s necessay to extact taget featues. 3.1 Featue extacton based DPCA Suppose that we have pe-pocessed tanng samples m n I R, 1,,,. Cente them Ι II, whee I 1 1 I1, I,, I wth I s the mean of total tanng samples. Fo each centeed sample Ι, let poject t onto W by the followng lnea tansfomaton: A ΙW (5) whee the pojecton matx W R n satsfes: WW I, and I s dentty matx. Rec Let us econstuct the samplei : I I AW I ΙWW, the econstuct eo s Rec II. he optmal pojecton matx should mnmze the sum of the econstuct eos sum of all the tanng samples

8 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 05 W opt ag mn W Rec F ag mn I I ΙWW W ag mn IIWW Ι W ag mn W I I Ι ΙWW F F F (6) whee F denotes matx F-nom. We have t Ι ΙWW F Ι ΙWW Ι ΙWW 1 1 Ι ΙWW ΙWW Ι t 1 t ΙΙ ΙWW Ι ΙWW Ι ΙWW WW Ι 1 t ΙΙ ΙWW Ι ΙWW Ι ΙWW Ι 1 t ΙΙ t W ΙΙW 1 1 (7) So, equaton (6) s equvalent to the followng fomula W opt ag max W 1 W W ag max t W 1 ag maxt W t WIIIIW WGW t ΙΙ (8) wheegt 1 I I I I s the covaance matx of tanng samples. So, the optmal n pojecton matx Wopt w1, w,, w R ( n) wth 1,,, egenvectos ofg coespondng to the lagest egenvalues. t Fo each tanng magei, ts featue matx s w s the set of B y 1,, y IIW opt IIww 1,,, w IIwIIw 1,,, IIw R m (9)

9 06 Pncpal Component Analyss Engneeng Applcatons Gven an unknown samplei R mn, ts featue matxb : By,, y 1 IIW opt IIwIIw 1,,, IIw R m (10) 3. Featue extacton based two-stage DPCA DPCA only elmnates the coelatons between ows, but dsegads the coelatons between columns. So t needs moe featues. hs wll lead to lage stoage equements and cost much moe tme n classfcaton phase. o futhe compess the dmenson of featue matces, two-stage DPCA s appled n ths chapte. Its detaled mplementaton s descbed as follows (shown n Fg.4): DPCA tanspose DPCA Fg. 4. Illustaton of two-stage DPCA. (1) anng mages R m I n wth 1,,,, calculate G t by the secton 3.1, and then n obtan the ow pojecton matx W opt R 1 1 n. Compute featue matces m A I IW fo each tanng mage. opt R 1 () Regad the matces ZA 1,,, m DPCA and get the column pojecton matx m Featue matx of each tanng mage s obtaned as new tanng samples, epeat the couse of W. copt R BZW AW copt copt W I I W opt copt R 1 1,,, (11) Gven a unknown magei R mn, ts featue matxb : 4. Classfe desgn opt copt R 1 BW IIW (1) In ths chapte, the neaest neghbo classfe based Eucld dstance s used. Compute dstances of featue matces between unknown and all tanng samples. hen, the decson s that ths test belongs to the same class as the tanng sample, whch mnmzes the dstance.

10 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues Classfcaton based DPCA featues DPCA featues of tanng mage I and test I ae opt R 1,, B y y I IW m, 1,, m opt R whee m y I Iw R 1 m k k, y I Iw R 1 By y IIW k k, k 1,,,, 1,,,. Fom the expessons, we see that column vectos y k and y k of B and B deve fom the pojectons of I and I onto egenvecto w k coespondng to egenvalue k. heefoe, the dstance of featue matces between the test and th tanng mage s defned as d BB, y y (13) k k k1 4. Classfcaton based two-stage DPCA featues of a testi and tanng magei by two- Gven featue matces R 1 B and R 1 B stage DPCA. (1) Defnton Dstance along ow Featue matces R 1 B and R 1 B ae wtten the followng fom B x1, x,, x, k 1 1 B x1, x,, x, 1 x, x k ae ow vectos wth the dmenson of 1. Defne the dstance between the two featue matces () Defnton Dstance along column d 1 1 BB, x x (14) k1 k1 k1 1 Featue matces R 1 B and R 1 B ae wtten as B y,, 1 y, y k, yk ae ow vectos wth the dmenson of 1. Defne the dstance B,, y 1 y, (3) Defnton Dstance along ow and column d BB, y y (15) k k k 1 he dstance between the test and the th tanng mage s defned 5. Expemental esults,,, 1 dbb d BB d BB (16) Expements ae made based on the SAR publc elease database. hee ae thee dstnct types of gound vehcles: BP, BR70, and 7. Fg.5 gves the optcal mages of the thee classes of vehcles, and Fg.6 shows the SAR mages.

11 08 Pncpal Component Analyss Engneeng Applcatons hee ae seven seal numbes (.e., seven taget confguatons) fo the thee taget types: one BR70 (sn-c71), thee BP s (sn-c1, sn-9593, and sn-9566), and thee 7 s (sn-13, sn- 81, and sn-s7). Fo each seal numbe, the tanng and test sets ae povded, wth the taget sgnatues at the depesson angles 17 and 15, espectvely. he tanng and test datasets ae gven n able 1. he sze of taget mages s conveted nto by ou pe-pocessng descbed n secton. (a) BP (b) BR70 (c) 7 Fg. 5. Optcal mages of the thee types of gound vehcles. (a) BP (b) BR70 (c) 7 Fg. 6. SAR mages of the thee types of gound vehcles. anng set Numbe of samples estng set Numbe of samples BPsn-c1 196 BPsn BPsn BPsn BR70sn-c71 33 BR70sn-c sn sn sn sn-s7 191 able 1. anng and testng datasets.

12 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues he effects of logathm conveson and powe-law tansfomaton wth dffeent exponents on the ecognton ates n ou pe-pocessng method Let us llustate the effects of logathm conveson and powe-law tansfomaton wth dffeent exponents n ou pe-pocessng usng an mage of 7, shown n Fg.7. (a) (b) (c) (d) (e) (f) (g) (h) Fg. 7. he effects to mage qualty wth dffeent. (a) Ognal mage, (b) Logathmc mage, (c) Segmented bnay taget mage, (d) Segmented aget ntensty mage, (e) Enhanced mage wth, (f) Enhanced mage wth 3, (g) Enhanced mages wth 4, (h), Enhanced mages wth 5. Fom Fg.7 (a), we see that the total gay values ae vey low, and many detals ae not vsble. On the one hand, logathmc tansfomaton convets speckles fom multple to addtonal model and makes mage hstogam moe sutable be appoxmated wth a Gaussan dstbuton. On the othe hand, t enlages the gay values and eveals moe detals. Howeve, mage contast n the taget egon deceases as shown n Fg.7 (d). heefoe, t s necessay to enhance mage contast, whch can be accomplshed by powe-law tansfomaton wth 1. he values of coespondng to Fg.7 (e) ~ (h) ae, 3, 4, and 5. We note that as nceases fom to 4, mage contast s enhanced dstnctly. But when contnues to ncease, the esultng mage become dak and lose some detals. By compasons of these esultng mages, we thnk that the best mage enhancement esult s at takng 4 appoxmately.

13 10 Pncpal Component Analyss Engneeng Applcatons We use the 698 samples of BPsn-9563, BR70sn-c71, and 7sn-13 fo tanng, 973 mages of BPsn-9563, BPsn-9566, BR70sn-c71, 7sn-13, 7sn-81, and 7sn-s7 fo testng. he vaaton of ecognton pefomance wth of DPCA s gven n Fg. 8. We can see that DPCA obtans the hghest ecognton ate at 3.5 ( s equal to 3.5 by default). Fg. 8. Recognton ate wth dffeent. 5. Compasons of dffeent pe-pocessng methods In SAR ecognton system, pe-pocessng s an mpotant facto. Let us evaluate the pefomance of seveal pe-pocessng appoaches as follows. ethod 1: the ognal mages ae tansfomed by logathm. hen, half of the ampltudes of the -dmensonal fast Foue tansfom ae used as nputs of featue extacton. ethod : ovelayng the segmented bnay taget a on the ognal mage F gets taget mage, nomalze t. Half of the ampltudes of -dmensonal fast Foue tansfom ae used. ethod 3: ovelayng a on F obtans taget mage. Fst, enhance t usng powe-law tansfomaton wth an exponent 0.6. hen nomalze t. Half of the ampltudes of - dmensonal fast Foue tansfom ae used.

14 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 11 ethod 4: ovelayng a on the logathmc mage G obtans taget mage, nomalze t. Half of the ampltudes of -dmensonal fast Foue tansfom ae used. ethod 5 (ou pe-pocessng method n secton ): hat s, ovelayng a on G obtans taget mage. Fst, enhance t usng powe-law tansfomaton wth an exponent 3.5. hen nomalze t. Half of the ampltudes of -dmensonal fast Foue tansfom ae used. Fg. 9. Pefomances of DPCA wth fve pe-pocessng methods. We also use the 698 samples of BPsn-9563, BR70sn-c71, and 7sn-13 fo tanng, 973 mages of BPsn-9563, BPsn-9566, BR70sn-c71, 7sn-13, 7sn-81, and 7sn-s7 fo testng. he ecognton ates of DPCA wth these fve pe-pocessng methods ae gven n Fg. 9. We can see that the pefomance of method 1 s the wost, because t does not segment the taget fom backgound cluttes, whch dstub ecognton pefomances. Compang method 3 wth and 5 wth 4, we easly fnd that mage enhancement based on powe-law tansfomaton s vey effcent. he dffeence between method 3 and method 5 (ou pe-pocessng method) s that the fome s obtaned by ovelayng. a. on the ognal magef, and then enhanced by powe-law tansfomaton wth a factonal exponent 0.6. he latte s obtaned by ovelayng a on the logathm mageg, and then enhanced by powe-law tansfomaton

15 1 Pncpal Component Analyss Engneeng Applcatons wth an exponent 3.5. Due to the effects of logathm n ou method, the pefomance of method 5 (ou pe-pocessng method) s bette than that of method 3. All the fve expemental esults testfy that ou pe-pocessng method s vey effcent. 5.3 Compasons of DPCA and PCA o futhe evaluate ou featue extacton method, we also compae DPCA wth PCA. he flow chat of expements s gven n Fg.10. Fg. 10. Flow chat of ou SAR AR expements. Fo all the tanng and testng samples n able 1, Fg.11 gves the vaaton of ecognton ates of PCA wth featue dmensons, that s, the numbe of pncpal components. PCA acheves the hghest ecognton ate when the numbe of pncpal components (d) equal 85. Fg. 11. Vaaton of ecognton ates of PCA wth the numbe of pncpal components.

16 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 13 Fo all the tanng and testng samples n able 1, Fg.1 gves the vaaton of ecognton ates of DPCA wth the numbe of pncpal components. DPCA acheves the hghest ecognton ate when the numbe of pncpal components () equal 8. Fg. 1. Vaaton of ecognton ates of DPCA wth the numbe of pncpal components. able shows the hghest ecognton ates of PCA and DPCA. We see that the hghest ecognton pefomance of DPCA s slghtly bette than that of PCA. Hghest ecognton ate (dmenson of featue vectos o featue matces) PCA+NNC (85) DPCA+NNC (18 8) able. Compasons of the hghest ecognton ates of PCA and DPCA By Compang Fg.11 wth Fg.1, we fnd that ecognton pefomance of DPCA s bette than PCA. hs s due to the facts that -dmensonal mage matces must be tansfomed nto 1-dmensonal mage vectos when PCA used n mage featue extacton. he mage matx-to-vecto tansfomaton wll esult n some poblems: (1) hs wll destoy - dmensonal spatal stuctue nfomaton of mage matx, whch bngs on pefomance loss; () hs leads to a hgh dmensonal vecto space, whee t s dffcult to evaluate the covaance matx accuately and fnd ts egenvectos because the dmenson of the

17 14 Pncpal Component Analyss Engneeng Applcatons covaance matx s vey lage ( m nm n). DPCA estmates the covaance matx based on -dmensonal tanng mage matces, whch leads to two advantages: (1) -dmensonal spatal stuctue nfomaton of mage matx s kept vey well; () the covaance matx s evaluated moe accuately and the dmensonalty of the covaance matx s vey small ( n n). So, the effcency of DPCA s much geate than that of PCA. able 3 gves the computaton complexty and stoage equements of PCA and DPCA, n whch the stoage equements nclude two pats: the pojecton vectos and featues of all tanng samples ( 698, m18, n64, 8, l 0 ). Fom ths table, we see that although the stoage equements ae compaatve, the computaton complexty of DPCA s much smalle than that of PCA when seekng the pojecton vectos. So, we thnk that DPCA s much geate than PCA n computaton effcency. Sze of covaance matx Complexty of fndng pojecton vectos Complexty of fndng featues Stoage of featues PCA m nmn o d mn ,30 DPCA n n n 3 64 m n ,536 mn dd n m = =755,650 =715,64 able 3. Compasons of the computaton complexty and stoage equements of PCA and DPCA Fom able and able 3, we can conclude that DPCA s bette than PCA n computaton effcency and ecognton pefomance. Fom able, we also see that featue matx obtaned by DPCA s consdeably lage. hs may lead to massve memoy equements and cost too much tme n classfcaton phase. So, we poposed two-stage DPCA to educe featue dmensons. 5.4 Compasons of DPCA and two-stage DPCA DPCA only elmnates the coelatons between ows, but dsegads the coelatons between columns. he poposed two-stage DPCA can elmnate the coelatons between mages ows and columns smultaneously, thus educng featue dmensons damatcally and mpovng ecognton pefomances.

18 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 15 able 4 shows the hghest ecognton ates of DPCA and two-stage DPCA. able 5 gves the computaton complexty and stoage equements of DPCA and twostage DPCA. he stoage equements also nclude two pats: pojecton matces and featue matces of all tanng samples ( 698, m18, n64, 8, l 0, 1 1, ). Fom able 4, we see that two-stage DPCA acheves the hghest ecognton pefomance wth smalle featue matces. Fom able5, we fnd that the stoage equements of two-stage DPCA ae smalle than those of DPCA. Fom able 4 and able 5, we can conclude that two-stage DPCA s bette than DPCA n ecognton pefomance and stoage equements. Fom able 4, we also see that the esults of two-stage DPCA ae compaatve no matte how the dstance between two featues s defned and the ecognton pefomance of the way of the dstance along ow and column s slghtly bette. Recognton appoaches Recognton ate (featue dmenson) DPCA (18 8) wo-stage DPCA (Defnton Dstance along column) 97.1 (1 ) wo-stage DPCA (Defnton Dstance along ow) 97.3 (10 30) wo-stage DPCA (Defnton Dstance along ow and (1 ) column) able 4. Compasons of ecognton pefomances of DPCA and two-stage DPCA (%). Complexty of fndng pojecton vectos DPCA 3 n wostage DPCA m n Complexty of fndng featues m n ,536 nm m 1 1 = =13,096 Stoage of featues n m = =715,64 n m 1 1 = =187,856 able 5. Compasons of stoage equements of DPCA and wo-stage DPCA. 5.5 Compasons of DPCA and two-stage DPCA unde dffeent azmuth ntevals In some cases, we can obtan taget azmuth. Usng t, ecognton pefomances may be mpoved. Goup tanng samples wth equal ntevals fo each class wthn 0 ~ 360, then extact featues wthn the same azmuth ange fo the thee types of tanng samples n the phase of tanng. In the phase of testng, the test sample s chosen to be classfed n the coespondng azmuth ange accodng to ts azmuth. In ths expement, tanng samples of each class ae gouped wth equal ntevals by 180,90, 30 espectvely.

19 16 Pncpal Component Analyss Engneeng Applcatons Recognton esults of DPCA and two-stage DPCA unde dffeent azmuth ntevals ( 180, 90, and 30 ) ae gven n able 6. Fom t, we obtan that pefomances of the twostage DPCA method s bette than those of DPCA. oeove, two-stage DPCA s obust to the vaaton of azmuth. hs table futhe poves that two-stage DPCA combnng wth ou pe-pocessng method s effcent. Recognton appoaches DPCA wo-stage DPCA (Defnton Dstance along column) wo-stage DPCA (Defnton Dstance along ow) wo-stage DPCA (Defnton Dstance along ow and column) able 6. Pefomances of DPCA and two-stage DPCA unde dffeent azmuth ntevals (%) 5.6 Compasons of two-stage DPCA and methods n lteatues he ecognton ates of two-stage DPCA and methods n lteatues ae lsted n able 7. Recognton appoaches Recognton ate (featue dmenson) emplate matchng (Zhao & Pncpe, 001) SV (Byant & Gabe, 1999) 90.9 PCA+SV (Han et al., 003) KPCA+SV (Han et al., 003) KFD+SV (Han et al., 004) (D) PCA [9] combnng ou pe-pocessng (Defnton Dstance along ( 1) column) (D) PCA [9] combnng ou pe-pocessng (Defnton Dstance ( 1) along ow) (D) PCA [9] combnng ou pe-pocessng (Defnton Dstance ( 1) along ow and column) GDPCA [10] combnng ou pe-pocessng (Defnton Dstance ( 1) along column) GDPCA [10] combnng ou pe-pocessng (Defnton Dstance 97.3 (4 1) along ow) GDPCA [10] combnng ou pe-pocessng (Defnton Dstance ( 1) along ow and column) wo-stage DPCA (Defnton Dstance along column) 97.1 (1 ) wo-stage DPCA (Defnton Dstance along ow) 97.3 (10 30) wo-stage DPCA (Defnton Dstance along ow and column) (1 ) able 7. Pefomances of two-stage DPCA and seveal methods n lteatues (%) We see that pefomances of lteatues (Zhao et al., 001; Byant & Gabe, 1999) ae the wost, snce they do not have any pe-pocessng and featue extacton. Howeve, effcent pe-pocessng and featue extacton can help to mpove ecognton pefomances.

20 Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues 17 In lteatues (Han et al., 003; Han et al., 004), PCA, KPCA, o KFD s employed. hese featue extacton methods seek pojecton vectos based on 1-dmensonal mage vectos. In ou AR system, taget s fstly segmented to elmnate backgound cluttes. hen, enhanced by powe-law tansfomaton to stand out useful nfomaton and stengthen taget ecognton capablty. oeove, featue extacton s based on -dmensonal mage matces, so that the spatal stuctue nfomaton s kept vey well and the covaance matx s estmated moe accuately and effcently. heefoe, two-stage DPCA combnng wth ou poposed pe-pocessng method can obtan the best ecognton pefomance. By compasons of two-stage DPCA and the smla technques, such as (D) PCA (Zhang & Zhou, 005), GDPCA (Kong et al., 005), we can conclude that ou pe-pocessng method s vey effcent and two-stage DPCA s compaable to (D) PCA and GDPCA n pefomance and stoage equements. able 8 gves the esults of two-stage DPCA, and othe appoaches n lteatues unde dffeent azmuth ntevals. Fom t, we obtan that pefomances of ou method s bette than those of lteatues. hs table futhe valdates that two-stage DPCA combnng wth ou pe-pocessng method s the best. Recognton appoaches emplate matchng (Zhao & Pncpe, 001) SV (Byant & Gabe, 1999) PCA+SV (Han et al., 003) KPCA+SV (Han et al., 003) KFD+SV (Han et al., 004) (D) PCA (Zhang & Zhou, 005) combnng ou pepocessng (Defnton Dstance along column) (D) PCA (Zhang & Zhou, 005) combnng ou pepocessng (Defnton Dstance along ow) (D) PCA (Zhang & Zhou, 005) combnng ou pepocessng (Defnton Dstance along ow and column) GDPCA (Kong et al., 005) combnng ou pe-pocessng (Defnton Dstance along column) GDPCA (Kong et al., 005) combnng ou pe-pocessng (Defnton Dstance along ow) GDPCA (Kong et al., 005) combnng ou pe-pocessng (Defnton Dstance along ow and column) wo-stage DPCA (defne dstance along ow) wo-stage DPCA (defne dstance along column) wo-stage DPCA (defne dstance along ow and column) able 8. Pefomances of two-stage DPCA and seveal methods n lteatues unde dffeent azmuth ntevals (%) Fom ths table, we also see that ecognton pefomances of two-stage DPCA acheve the best unde the 180 azmuth ntevals.

21 18 Pncpal Component Analyss Engneeng Applcatons Howeve, wth the azmuth nteval deceasng, ecognton pefomances of two-stage DPCA become wose. hs s because numbe of tanng samples at ntevals becomes smalle; t s not useful fo estmatng the covaance matx exactly, thus esultng n ecognton pefomance loss. Whle n lteatues (Byant & Gabe, 1999; Han et al., 003; Han et al., 004), the classfe of SV s employed, ths s ft fo a small sample classfcaton. Compasons of two-stage DPCA and the (D) PCA and GDPCA methods unde dffeent azmuth ntevals, we thnk that ou pe-pocessng method s vey effcent and two-stage DPCA s compaable to (D) PCA and GDPCA. 6. Conclusons An effcent SAR pe-pocessng method s fst poposed to obtan tagets fom backgound cluttes, and two-stage DPCA s poposed fo SAR mage featue extacton n ths chapte. Compasons wth DPCA and othe appoaches pove that two-stage DPCA combnng wth ou pe-pocessng method not only deceases shaply featue dmensons, but also nceases ecognton ate. oeove, t s obust to the vaaton of taget azmuth, and deceases the pecson equements fo the estmaton of taget azmuth. 7. Refeences Byant,. & Gabe, F. (1999). SV Classfe appled to the SAR publc data set, SPIE, Vol. 371, No. 4, (Apl 1999), pp Gonzalez, R.C. & Woods R. E. (00) Dgtal Image Pocessng, Publshng House of Electoncs Industy, Bejng, Chna. Han, P.; Wu, R. B. & Wang, Z. H. (003). SAR Automatc aget Recognton based on KPCA Cteon, Jounal of Electoncs and Infomaton echnology, Vol. 5, No.10, (Octobe 003), pp Han, P.; Wu, R. B. & Wang, Z. H. (003). SAR aget Featue Extacton and Automatc Recognton Based on KFD Cteon, oden Rada, Vol. 6, No.7, (July 004), pp Kong, H.; Wang, L. & eoh, E. K. (005) Genealzed D Pncpal Component Analyss fo face mage epesentaton and ecognton, Neual Netwoks, Vol. 18, (005), pp usman, S. & Ke, D. (1996). Automatc Recognton of ISAR Shp Images, IEEE ansactons on Aeospace and Electonc Systems, Vol. 3, No. 4, (Octobe 1996), pp Ross,.; Woell, S. & Velten, V. (1998). Standad SAR AR evaluaton expement usng the SAR publc elease data set, SPIE, Vol.3370, No.4, (Apl 1998), pp Yang, J.; Zhang, D. & Fang, A. F. (004). wo-dmensonal PCA: a new appoach to appeaance-based face epesentaton and ecognton, IEEE ansactons on Patten Analyss and achne Intellgence, Vol. 6, No. 1, (Januay 004), pp Zhang, D. Q. & Zhou Z. H. (005). (D) PCA: wo-dectonal two-dmensonal PCA fo effcent face epesentaton and ecognton, Neuocomputng, Vol. 69, (005), pp Zhao, Q. & Pncpe, J. C. (001). Suppot Vecto achne fo SAR automatc taget ecognton, IEEE ansactons on Aeospace and Electonc Systems, Vol. 37, No., (Apl 001), pp

22 Pncpal Component Analyss - Engneeng Applcatons Edted by D. Panya Sanguansat ISBN Had cove, 30 pages Publshe Inech Publshed onlne 07, ach, 01 Publshed n pnt edton ach, 01 hs book s amed at asng awaeness of eseaches, scentsts and engnees on the benefts of Pncpal Component Analyss (PCA) n data analyss. In ths book, the eade wll fnd the applcatons of PCA n felds such as enegy, mult-senso data fuson, mateals scence, gas chomatogaphc analyss, ecology, vdeo and mage pocessng, agcultue, colo coatng, clmate and automatc taget ecognton. How to efeence In ode to coectly efeence ths scholaly wok, feel fee to copy and paste the followng: Lpng Hu, Hongwe Lu and Hongcheng Yn (01). Automatc aget Recognton Based on SAR Images and wo-stage DPCA Featues, Pncpal Component Analyss - Engneeng Applcatons, D. Panya Sanguansat (Ed.), ISBN: , Inech, Avalable fom: Inech Euope Unvesty Campus SeP R Slavka Kautzeka 83/A Rjeka, Coata Phone: +385 (51) Fax: +385 (51) Inech Chna Unt 405, Offce Block, Hotel Equatoal Shangha No.65, Yan An Road (West), Shangha, 00040, Chna Phone: Fax:

23 01 he Autho(s). Lcensee IntechOpen. hs s an open access atcle dstbuted unde the tems of the Ceatve Commons Attbuton 3.0 Lcense, whch pemts unestcted use, dstbuton, and epoducton n any medum, povded the ognal wok s popely cted.

Effectiveness evaluation of electronic warfare command and control system based on grey AHP method

Effectiveness evaluation of electronic warfare command and control system based on grey AHP method Avalable onlne www.jocp.com Jounal of hemcal and Phamaceutcal Reseach, 014, 6(7):535-54 Reseach Atcle ISSN : 0975-7384 ODEN(USA) : JPR5 Effectveness evaluaton of electonc wafae command and contol system

More information

Improved Methods on PCA Based Human Face Recognition for Distorted Images

Improved Methods on PCA Based Human Face Recognition for Distorted Images Poceedngs of the Intenatonal MultConfeence of Engnees and Compute Scentsts 016 Vol I,, Mach 16-18, 016, Hong Kong Impoved Methods on PCA Based Human Face Recognton fo Dstoted Images Buce Poon, M. Ashaful

More information

Recognizing Facial Expressions Based on Gabor Filter Selection

Recognizing Facial Expressions Based on Gabor Filter Selection Recognzng Facal Expessons Based on Gabo Flte Selecton Zang Zhang, Xaomn Mu, Le Gao School of Infomaton Engneeng Zhengzhou Unvest Zhengzhou, Chna Abstact Recognton of human emotonal state s an mpotant component

More information

Journal of Engineering Science and Technology Review 7 (1) (2014) Research of Anti-Noise Image Salient Region Extraction Method

Journal of Engineering Science and Technology Review 7 (1) (2014) Research of Anti-Noise Image Salient Region Extraction Method Jest Jounal of Engneeng Scence and echnology Revew 7 () (04) 43 47 JOURNAL OF Engneeng Scence and echnology Revew www.jest.og Reseach of Ant-Nose Image Salent Regon Extacton Method Bng XU,*, Shy XIE and

More information

Planar Curve Representation and Matching

Planar Curve Representation and Matching Plana Cuve Repesentaton and Matchng Mahe Al-Khayat and Fahad Kamanga Compute Scence and Engneeng Depatment Unvesty of Texas at Alngton Alngton, Texas 7609, USA [al-khay kamanga]@cse.uta.edu Abstact In

More information

FUNDAMENTALS OF RADIOMETRY

FUNDAMENTALS OF RADIOMETRY 1 FUNDAMENTALS OF RADIOMETRY Lectue 5 Radomety 2 Quanttatve measuement of the popetes of EM adaton nteacton wth matte o emsson fom t Radomety deals wth total EM adaton We extend the concept of adans n

More information

Volumetric Textures. Esteban W. Gonzalez Clua 1 Marcelo Dreux 2

Volumetric Textures. Esteban W. Gonzalez Clua 1 Marcelo Dreux 2 Volumetc Textues Esteban W. Gonzalez Clua 1 Macelo Deux 2 1 PUC-Ro - Depatment of Compute Scence Rua Maquês de São Vcente, 255, 22443-900, Ro de Janeo, RJ, Bazl esteban @nf.puc-o.b 2 PUC-RIO Mechancal

More information

Dual Tree Complex Wavelet Transform for Face Recognition Using PCA Algorithm

Dual Tree Complex Wavelet Transform for Face Recognition Using PCA Algorithm B.Dhamenda,INDIA / Intenatonal Jounal of Reseach and Computatonal echnology, Vol.5 Issue.4 ISSN: 0975-5662, Dec, 2013 www.jct.og Dual ee Complex Wavelet ansfom fo Face Recognton Usng PCA Algothm Dhamenda

More information

Risk assessment research for power transformer based on fuzzy synthetic evaluation

Risk assessment research for power transformer based on fuzzy synthetic evaluation Avalable onlne www.jocp.com Jounal of Chemcal and Phamaceutcal Reseach, 23, 5(2):62-68 Reseach Atcle ISSN : 975-7384 CODEN(USA) : JCPRC5 Rsk assessment eseach fo powe tansfome based on fuzzy synthetc evaluaton

More information

Graph Cut-based Automatic Segmentation of Lung Nodules using Shape, Intensity, and Spatial Features

Graph Cut-based Automatic Segmentation of Lung Nodules using Shape, Intensity, and Spatial Features Second Intenatonal Wokshop on -103- Gaph Cut-based Automatc Segmentaton of Lung Nodules ung Shape, Intenty, and Spatal eatues Xujong Ye, Gaeth Beddoe and Geg Slabaugh Medcght PLC, London, UK Abstact. Ths

More information

3D Head Tracking Based on Recognition and Interpolation Using a Time-Of- Flight Depth Sensor

3D Head Tracking Based on Recognition and Interpolation Using a Time-Of- Flight Depth Sensor 3D Head Tacng Based on Recognton and Intepolaton Usng a Tme-Of- Flght Depth Senso Salh Bua Götü 1 and Calo Tomas 1,2 1 Canesta Inc., 2 Due Unvesty bgotu@canesta.co tomas@cs.due.edu Abstact Ths pape descbes

More information

One-Dimensional Linear Local Prototypes for Effective Selection of Neuro-Fuzzy Sugeno Model Initial Structure

One-Dimensional Linear Local Prototypes for Effective Selection of Neuro-Fuzzy Sugeno Model Initial Structure One-Dmensonal Lnea Local Pototypes fo Effectve Selecton of euo-fuzzy Sugeno Model Intal Stuctue Jace Kabzńs Insttute of Automatc Contol, Techncal Unvesty of Lodz, Stefanowsego 8/22, 90 924 Lodz, Poland,

More information

arxiv: v1 [math.co] 21 Jan 2016

arxiv: v1 [math.co] 21 Jan 2016 PROOF OF BIJECTION FOR COMBINATORIAL NUMBER SYSTEM axv:60.05794v [math.co] Jan 06 ABU BAKAR SIDDIQUE, SAADIA FARID, AND MUHAMMAD TAHIR Abstact. Combnatoal numbe system epesents a non-negatve natual numbes

More information

A SAS Macro for Finding Optimal k-means Clustering in One Dimension with Size Constraints

A SAS Macro for Finding Optimal k-means Clustering in One Dimension with Size Constraints Pape SD-02 A SAS Maco fo Fndng Optmal k-means Clusteng n One Dmenson wth Sze Constants Fengao Hu, Geoga Regents Unvesty; Robet E. Johnson, Vandeblt Unvesty ABSTRACT Wang and Song (2011) poposed a k-means

More information

An Object Based Auto Annotation Image Retrieval System

An Object Based Auto Annotation Image Retrieval System Poceedngs of the 5th WSEAS Intenatonal Confeence on Telecommuncatons and Infomatcs, Istanbul, Tukey, May 27-29, 2006 (pp509-54) An Obect Based Auto Annotaton Image Reteval System Pe-Cheng Cheng, Been-Chan

More information

Enhance the Alignment Accuracy of Active Shape Models Using Elastic Graph Matching

Enhance the Alignment Accuracy of Active Shape Models Using Elastic Graph Matching Enhance the Algnment Accuacy of Actve Shape Models Usng Elastc Gaph Matchng Sanqang Zhao 1,, Wen Gao, Shguang Shan, Baoca Yn 1 1) Multmeda and Intellgent Softwae Technology Lab, Beng Unvesty of Technology,

More information

Real Time Face Recognition Using Polynomial Regression and Sub-region Color Component Distribution

Real Time Face Recognition Using Polynomial Regression and Sub-region Color Component Distribution Real Tme Face Recognton Usng Polynomal Regesson and Sub-egon Colo Component Dstbuton Manshanka Mondal, Md. Almas Hossan, Md. Matu Rahman, Kamul Hasan Talukde* Compute Scence and Engneeng Dscplne Khulna

More information

A Bayesian Approach toward Active Learning for Collaborative Filtering

A Bayesian Approach toward Active Learning for Collaborative Filtering A Bayesan Appoach towad Actve Leanng fo Collaboatve Flteng Rong Jn Depatment of Compute Scence and Engneeng Mchgan State Unvesty ong@cse.cmu.edu Abstact Collaboatve flteng s a useful technque fo eplotng

More information

Soochow University: Description and Analysis of the Chinese Word Sense Induction System for CLP2010

Soochow University: Description and Analysis of the Chinese Word Sense Induction System for CLP2010 Soochow Unvesty: Descpton and Analyss of the Chnese Wod Sense Inducton System fo CLP2010 Hua Xu Bng Lu Longhua Qan Guodong Zhou Natual Language Pocessng Lab School of Compute Scence and Technology Soochow

More information

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification TNN05-P485 Weghted Pecewse LDA fo Solvng the Small Sample Sze Poblem n Face Vefcaton Maos Kypeountas, Anastasos Tefas, Membe, IEEE, and Ioanns Ptas, Seno Membe, IEEE Abstact A novel algothm that can be

More information

Robust Proper Clustering Structure Fuzzy Modeling for Function Approximation

Robust Proper Clustering Structure Fuzzy Modeling for Function Approximation Robust Pope lusteng Stuctue Fuzzy Modelng fo Functon Appoxmaton hh-hng Hsao Depatment of Electcal Engneeng Kao Yuan Unvesty Kaohsung ounty,tawan RO hsao@ooneentustedutw Shun-Feng Su Depatment of Electcal

More information

Recognition of Shapes for Object Retrieval in Image Databases by Discrete Curve Evolution and Two Consecutive Primitive Edges

Recognition of Shapes for Object Retrieval in Image Databases by Discrete Curve Evolution and Two Consecutive Primitive Edges Poceedngs of the Intenatonal MultConfeence of Engnees and Compute Scentsts 009 Vol I IMECS 009 Mach 8-0 009 Hong Kong Recognton of Shapes fo Object Reteval n Image Databases by Dscete Cuve Evoluton and

More information

Efficient VLSI Implementation of Modified Dual Tree Discrete Wavelet Transform Based on Lifting Scheme

Efficient VLSI Implementation of Modified Dual Tree Discrete Wavelet Transform Based on Lifting Scheme Austalan Jounal of Basc and Appled Scences, 9(7) August 05, Pages: 58-66 ISSN:99-878 Austalan Jounal of Basc and Appled Scences Jounal home page: www.ajbasweb.com Effcent VLSI Implementaton of Modfed Dual

More information

Fuzzy Membership Function Based on Structural Information of Data Fang-Zhi ZHU a, Hui-Ru WANG b, Zhi-Jian ZHOU c,*

Fuzzy Membership Function Based on Structural Information of Data Fang-Zhi ZHU a, Hui-Ru WANG b, Zhi-Jian ZHOU c,* 06 Intenatona Confeence on Sevce Scence, Technoogy and Engneeng (SSTE 06 ISBN: 978--60595-35-9 Fuzzy Membeshp Functon Based on Stuctua Infomaton of Data Fang-Zh ZHU a, Hu-Ru WANG b, Zh-Jan ZHOU c,* Coege

More information

Hadoop based Feature Selection and Decision Making Models on Big Data

Hadoop based Feature Selection and Decision Making Models on Big Data Indan Jounal of Scence and Technology, Vol 9(0), DOI: 0.7485/jst/206/v90/88905, Mach 206 ISSN (Pnt) : 0974-6846 ISSN (Onlne) : 0974-5645 Hadoop based Featue Selecton and Decson Makng Models on Bg Data

More information

Supervised and Unsupervised Text Classification via Generic Summarization

Supervised and Unsupervised Text Classification via Generic Summarization Intenatonal Jounal of Compute Infomaton Systems and Industal Management Applcatons. ISSN 50-7988 Volume 5 (03) pp. 509-55 MIR Labs, www.mlabs.net/jcsm/ndex.html Supevsed and Unsupevsed Text Classfcaton

More information

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012

Journal of World s Electrical Engineering and Technology J. World. Elect. Eng. Tech. 1(1): 12-16, 2012 2011, Scienceline Publication www.science-line.com Jounal of Wold s Electical Engineeing and Technology J. Wold. Elect. Eng. Tech. 1(1): 12-16, 2012 JWEET An Efficient Algoithm fo Lip Segmentation in Colo

More information

Vol. 4, No. 6 June 2013 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved.

Vol. 4, No. 6 June 2013 ISSN Journal of Emerging Trends in Computing and Information Sciences CIS Journal. All rights reserved. Vol 4, No 6 June 03 ISSN 079-8407 Jounal Emegng Tends n Computng and Infomaton Scences 009-03 CIS Jounal All ghts eseved http://wwwcsjounalog Optmal Powe Dstbuton System Placement to Install the RTU wth

More information

Interactive NURBS Tutorial in Virtual Reality

Interactive NURBS Tutorial in Virtual Reality Inteacte NURBS Ttoal n Vtal Realty Eng 477 Poect Fa Octobe 10 2006 Edmond Nadle enadle@mch.ed 734 913-6970 Eng 477 Poect Fa Octobe 10 2006 Eng 477 Poect Fa Octobe 10 2006 NURBS Ces and Sfaces = Non-Unfom

More information

A QoS Scheme for a Congestion Core Network Based on Dissimilar QoS Structures in Smart-Phone Environments

A QoS Scheme for a Congestion Core Network Based on Dissimilar QoS Structures in Smart-Phone Environments Sensos 2010, 10, 10006-10013; do:10.3390/s101110006 OPEN ACCESS sensos ISSN 1424-8220 www.mdp.com/jounal/sensos Atcle A QoS Scheme fo a Congeston Coe Netwok Based on Dssmla QoS Stuctues n Smat-Phone Envonments

More information

Fault Tolerant Routing For Wireless Sensor Grid Networks

Fault Tolerant Routing For Wireless Sensor Grid Networks Fault oleant Routng Fo Weless Senso Gd etwoks Xn-ng Huang, Jng Deng 2, Jng a and Zeyu Wu Depatment of Electcal Engneeng 2 Depatment of Compute Scence Unvesty of ew Oleans, ew Oleans, A 7048, USA Abstact

More information

Some Image Processing Algorithms on a RAP with Wider Bus Networks

Some Image Processing Algorithms on a RAP with Wider Bus Networks Some Image Pocessng Algothms on a RAP wth Wde Bus Netwoks Shung-Shng Lee, Sh-Jnn Hong, Hong-Ren Tsa and Yu-Hua Lee Natonal Tawan Insttute of Technology Depatment of Electcal Engneeng 4, Secton 4, Kee-Lung

More information

Performance Evaluation of WDM LAN s with Propagation Delay Constraint Analysis

Performance Evaluation of WDM LAN s with Propagation Delay Constraint Analysis Pefomance Evaluaton of WD AN s wth Popagaton Dela Constant Analss IOANNI E. POUNOURAKI Depatment of Electcal & Compute Engneeng Natonal echncal Unvest of Athens 57 73 Zogaphou, Athens GREECE Abstact: -In

More information

FUZZY ARTMAP AND NEURAL NETWORK APPROACH TO ONLINE PROCESSING OF INPUTS WITH MISSING VALUES

FUZZY ARTMAP AND NEURAL NETWORK APPROACH TO ONLINE PROCESSING OF INPUTS WITH MISSING VALUES FUZZY ARTMAP AD EURAL ETWORK APPROACH TO OLIE PROCESSIG OF IPUTS WITH MISSIG VALUES F.V. elwamondo* and T. Mawala* * School of Electcal and Infomaton Engneeng, Unvesty of the Wtwatesand, Johannesbug, Pvate

More information

Performance Evaluation of Neighborhood Signature Techniques for Peer-to-Peer Search

Performance Evaluation of Neighborhood Signature Techniques for Peer-to-Peer Search Pefomance Evaluaton of Neghbohood gnatue Technques fo Pee-to-Pee each e L Wang-Chen Lee * Anand vasubamanam Depatment of Compute cence and Engneeng Pennsylvana tate Unvesty Unvesty Pak, PA 16802, UA E-al:

More information

Adjusting the Contact Surface of Forming Tools in Order to Compensate for Elastic Deformations during the Process

Adjusting the Contact Surface of Forming Tools in Order to Compensate for Elastic Deformations during the Process Adjustng the Contact Suface of Fomng Tools n Ode to Compensate fo Elastc Defomatons dung the Pocess Knut Goßmann, Hajo Weme, Andè Hadtmann, Las Pente, Sebastan Kechenbaue Insttute fo Machne Tools and Contol

More information

Refraction Ray Normal

Refraction Ray Normal Ray Nomal wave cests θ Bounday θ θ θ less dense, n1 moe dense, n2 (>n1) Moe Smply: θ θ Note: (Lght) Rays bend towads the nomal when gong fom a egon of low ndex of efacton to a egon of hgh ndex of efacton

More information

DATA DIMENSIONALITY REDUCTION METHODS FOR ORDINAL DATA

DATA DIMENSIONALITY REDUCTION METHODS FOR ORDINAL DATA DATA DIMENIONALITY REDUCTION METHOD FOR ORDINAL DATA Matn Pokop Hana Řezanková Abstact Fom questonnae suvey we fequently get data, the values ae expessed n odnal (e.g. Lket) scale. The questonnae contans

More information

Feature Extraction for Collaborative Filtering: A Genetic Programming Approach

Feature Extraction for Collaborative Filtering: A Genetic Programming Approach IJCSI Intenatonal Jounal of Compute Scence Issues Vol. 9 Issue 5 No Septembe 0 www.ijcsi.og 348 Featue xtacton fo Collaboatve Flteng: A Genetc Pogammng Appoach Deepa Anand Depatment of Compute Scence Chst

More information

Point-Cloud-to-Point-Cloud Technique on Tool Calibration for Dental Implant Surgical Path Tracking

Point-Cloud-to-Point-Cloud Technique on Tool Calibration for Dental Implant Surgical Path Tracking Pont-Cloud-to-Pont-Cloud Technque on Tool Calbaton fo Dental Implant Sugcal Path Tackng Auanuch Losakul, Jackt Suthakon and Chanja Snthanayothn Abstact Dental mplant s nomally used n posthetc dentsty.

More information

Face and Feature Tracking for Cursor Control

Face and Feature Tracking for Cursor Control Face and Featue Tackng fo Cuso Contol M Vkash Chauhan, D Tm Mos. Depatment of Computaton, UMIST, PO Box 88, Mancheste, M60 1QD, UK vkash@pueksmet.com and t.mos@co.umst.ac.uk Abstact A method of contollng

More information

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components

A Neural Network Model for Storing and Retrieving 2D Images of Rotated 3D Object Using Principal Components A Neual Netwok Model fo Stong and Reteving 2D Images of Rotated 3D Object Using Pncipal Components Tsukasa AMANO, Shuichi KUROGI, Ayako EGUCHI, Takeshi NISHIDA, Yasuhio FUCHIKAWA Depatment of Contol Engineeng,

More information

Advanced Algorithms for Location-Based Smart Mobile Augmented Reality Applications

Advanced Algorithms for Location-Based Smart Mobile Augmented Reality Applications Avalable onlne at www.scencedect.com Poceda Compute Scence 00 (2016) 000 000 www.elseve.com/locate/poceda The 13th Intenatonal Confeence on Moble Systems and Pevasve Computng (MobSPC 2016) Advanced Algothms

More information

Classification of Color Textures with Random Field Models and Neural Networks

Classification of Color Textures with Random Field Models and Neural Networks Classfcaton of Colo extues wth Rom Feld Models Neual Netwoks Olo J. Henez John Cook Mchael Gffn Cntha De Rama Mchael McGoven E-mal: {hene cook5 gffn deama mcgove4}@tcn.edu Depatment Electcal & Compute

More information

Research on Fast Reconstruction of Virtual Plant Leaves

Research on Fast Reconstruction of Virtual Plant Leaves Reseach on Fast Reconstucton of Vtual Plant Leaves Fang Ku Lu-Mng Shen 2 College of Infomaton Scence and Technology Hunan Agcultual Unvesty, Changsha, Chna fk@hunau.net Jng Song 2 College of Scence Hunan

More information

A Two-stage and Parameter-free Binarization Method for Degraded Document Images

A Two-stage and Parameter-free Binarization Method for Degraded Document Images A Two-stage and Paamete-fee Binaization Method fo Degaded Document Images Yung-Hsiang Chiu 1, Kuo-Liang Chung 1, Yong-Huai Huang 2, Wei-Ning Yang 3, Chi-Huang Liao 4 1 Depatment of Compute Science and

More information

A New Regularized Orthogonal Local Fisher Discriminant Analysis for Image Feature Extraction

A New Regularized Orthogonal Local Fisher Discriminant Analysis for Image Feature Extraction ZHONGFENG WANG et al: A NEW REGULARIZED ORHOGONAL LOCAL FISHER DISCRIMINAN A Ne Regulazed Othogonal Local Fshe Dscmnant Analyss fo Image Featue Extacton Zhongfeng WANG, Zhan WANG 2 dept. name of oganzaton,

More information

Constructing Service Semantic Link Network Based on the Probabilistic Graphical Model

Constructing Service Semantic Link Network Based on the Probabilistic Graphical Model Intenatonal Jounal of omputatonal Intellgence ystems, Vol. 5, No. 6 (Novembe, 2012), 1040-1051 onstuctng evce emantc Lnk Netwok Based on the Pobablstc Gaphcal odel ANPING ZHAO * ollege of ompute and Infomaton

More information

Dynamic Optimization of Structures Subjected to Earthquake

Dynamic Optimization of Structures Subjected to Earthquake IACSIT Intenatonal Jounal of Engneeng and Technology, Vol. 8, No. 4, August 06 Dynamc Optmzaton of Stuctues Subjected to Eathquake Aleza Lavae and Aleza Lohasb Abstact To educe the oveall tme of stuctual

More information

Controlled Information Maximization for SOM Knowledge Induced Learning

Controlled Information Maximization for SOM Knowledge Induced Learning 3 Int'l Conf. Atificial Intelligence ICAI'5 Contolled Infomation Maximization fo SOM Knowledge Induced Leaning Ryotao Kamimua IT Education Cente and Gaduate School of Science and Technology, Tokai Univeisity

More information

Comparing performance of SRAMT-LE vs other layered encoding schemes regarding TCP friendliness

Comparing performance of SRAMT-LE vs other layered encoding schemes regarding TCP friendliness Compang pefomance of SRAMT-LE vs othe layeed encodng schemes egadng TCP fendlness Chstos Bouas, Apostolos Gkamas Reseach Academc Compute Technology Insttute, 61 Rga Feaou St, GR-26221 Patas, Geece Compute

More information

COVERAGE BASED DENSITY ESTIMATION STRATEGY FOR VANET

COVERAGE BASED DENSITY ESTIMATION STRATEGY FOR VANET Intenatonal Jounal of Advanced Compute Technology (IJACT) ISSN:319-7900 COVERAGE BASED DENSITY ESTIMATION STRATEGY FOR VANET Chun-Chh Lo, Depatment of Compute Scence and Infomaton Engneeng, Natonal Cheng

More information

AN EXPLICIT GROWTH MODEL OF THE STEREO REGION GROWING ALGORITHM FOR PARALLEL PROCESSING

AN EXPLICIT GROWTH MODEL OF THE STEREO REGION GROWING ALGORITHM FOR PARALLEL PROCESSING Intenatonal Achves of Photogammety, Remote Sensng and Spatal Infomaton Scences, Vol. XXXVIII, Pat 5 AN EXPLICIT GROWTH MODEL OF THE STEREO REGION GROWING ALGORITHM FOR PARALLEL PROCESSING Dongoe Shn*,

More information

COMPARISON OF DIMENSIONALITY REDUCTION METHODS APPLIED TO ORDINAL DATA

COMPARISON OF DIMENSIONALITY REDUCTION METHODS APPLIED TO ORDINAL DATA The 7 th Intenatonal Days of tatstcs and Economcs, Pague, eptembe 19-21, 2013 COMPARION OF DIMENIONALITY REDUCTION METHOD APPLIED TO ORDINAL DATA Matn Pokop Hana Řezanková Abstact The pape deals wth the

More information

NODAL AND LOOP ANALYSIS TECHNIQUES. Develop systematic techniques to determine all the voltages and currents in a circuit NODE ANALYSIS

NODAL AND LOOP ANALYSIS TECHNIQUES. Develop systematic techniques to determine all the voltages and currents in a circuit NODE ANALYSIS NODAL AND LOOP ANALYSS TECHNQUES LEANNG GOALS NODAL ANALYSS LOOP ANALYSS Develop systematic techniques to determine all the voltages and currents in a circuit NODE ANALYSS One of the systematic ways to

More information

A Method for Privacy Preserving Mining of Association Rules based. on Web Usage Mining

A Method for Privacy Preserving Mining of Association Rules based. on Web Usage Mining 200 Intenatonal onfeence on Web Infomaton Systems and Mnng A Method fo Pvacy Pesevng Mnng of Assocaton Rules based on Web Usage Mnng Wang Yan Le Jajn Huang Dongme Gloous Sun School of Busness and Management

More information

Outlier Detection in 3D Coordinate Transformation with Fuzzy Logic

Outlier Detection in 3D Coordinate Transformation with Fuzzy Logic Acta Montanstca Slovaca Ročník 7 (22), číslo, -8 Outle Detecton n 3D Coodnate ansfomaton wth Fuzzy Logc Yasemn Ssman, Aslan Dlave 2 and Sebahattn Bektas Coodnate measuements nevtably contan outles that

More information

Efficient End-to-End Communication Services for Mixed Criticality Avionics Systems

Efficient End-to-End Communication Services for Mixed Criticality Avionics Systems 214 IEEE 22nd Intenatonal Symposum of Qualty of Sevce (IWQoS) Effcent End-to-End Communcaton Sevces fo Mxed Ctcalty Avoncs Systems Yng Fang Yu Hua Xue Lu McGll Unvesty Huazhong Unv. of Sc. and Tech. McGll

More information

Lecture # 04. Image Enhancement in Spatial Domain

Lecture # 04. Image Enhancement in Spatial Domain Digital Image Pocessing CP-7008 Lectue # 04 Image Enhancement in Spatial Domain Fall 2011 2 domains Spatial Domain : (image plane) Techniques ae based on diect manipulation of pixels in an image Fequency

More information

Manuscript Draft. Title: Lattice Boltzmann Model for Fast Level Set Algorithm Using the Multiple Kernel Fuzzy C-Means

Manuscript Draft. Title: Lattice Boltzmann Model for Fast Level Set Algorithm Using the Multiple Kernel Fuzzy C-Means Undestandng Compute Vson and Image Manuscpt Daft Manuscpt Numbe: CVIU-12-298 Ttle: Lattce Boltzmann Model fo Fast Level Set Algothm Usng the Multple Kenel Fuzzy C-Means Atcle Type: Regula Pape Keywods:

More information

Beyond a Simple Physically Based Blinn-Phong Model in Real-Time

Beyond a Simple Physically Based Blinn-Phong Model in Real-Time Pactcal Physcally Based Shadng n Flm and Game Poducton: Beyond a Smple Physcally Based Blnn-Phong Model n Real-Tme. Intoducton Yoshhau Gotanda t-ace, Inc. http://eseach.t-ace.com/ We pesented ou mplementaton

More information

Detection and Recognition of Alert Traffic Signs

Detection and Recognition of Alert Traffic Signs Detection and Recognition of Alet Taffic Signs Chia-Hsiung Chen, Macus Chen, and Tianshi Gao 1 Stanfod Univesity Stanfod, CA 9305 {echchen, macuscc, tianshig}@stanfod.edu Abstact Taffic signs povide dives

More information

Image Enhancement in the Spatial Domain. Spatial Domain

Image Enhancement in the Spatial Domain. Spatial Domain 8-- Spatial Domain Image Enhancement in the Spatial Domain What is spatial domain The space whee all pixels fom an image In spatial domain we can epesent an image by f( whee x and y ae coodinates along

More information

An Energy-Aware QoS Routing Protocol for Wireless Sensor Networks

An Energy-Aware QoS Routing Protocol for Wireless Sensor Networks An Enegy-Awae QoS Routng Potocol fo Weless Senso Netwoks Kemal Akkaya and Mohamed Youns Depatment of Compute Scence and Electcal Engneeng Unvesty of Mayland, Baltmoe County Baltmoe, MD 225 kemal youns@cs.umbc.edu

More information

Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective

Rigid Body Segmentation and Shape Description from Dense Optical Flow Under Weak Perspective , VOL. 19, NO. 2, FEBRUARY 1997 139 Rgd Body Segmentaton and Shape Descpton fom Dense Optcal Flow Unde Weak Pespectve Joseph Webe and Jtenda Malk Abstact We pesent an algothm fo dentfyng and tackng ndependently

More information

KANBAN DEVS MODELLING, SIMULATION AND VERIFICATION

KANBAN DEVS MODELLING, SIMULATION AND VERIFICATION KANBAN DEVS MODELLING, SIMULATION AND VERIFICATION Alex Cave and Saed Nahavand School of Engneeng and Technology, Deakn Unvesty, Geelong, Vctoa 3216, Austala nahavand@deakn.edu.au ABSTRACT Kanban Contol

More information

Cost of Stable Dimensioning in Optical Packet Ring with Uniform and Symmetric Traffic

Cost of Stable Dimensioning in Optical Packet Ring with Uniform and Symmetric Traffic Telfo Jounal, Vol. 5, No., 03. 43 ost of Stable Dmensonng n Optcal Packet Rng th Unfom and Symmetc Taffc Bogdan Ušćumlć, Veseln Gedć, Anne Gavey, Phlppe Gavey, Mchel Movan, and Peta Matavulj Abstact Optcal

More information

Module 6 STILL IMAGE COMPRESSION STANDARDS

Module 6 STILL IMAGE COMPRESSION STANDARDS Module 6 STILL IMAE COMPRESSION STANDARDS Lesson 17 JPE-2000 Achitectue and Featues Instuctional Objectives At the end of this lesson, the students should be able to: 1. State the shotcomings of JPE standad.

More information

Flood Runoff Simulation Using Grid-based Radar Rainfall and Vflo TM Model

Flood Runoff Simulation Using Grid-based Radar Rainfall and Vflo TM Model Flood Runoff Smulaton Usng Gd-based Rada Ranfall and Vflo TM Model HUI SEONG NOH 1, BYUNG SIK KIM 2, NA RAE KANG 3, HUNG SOO KIM 4 1 Dept. of Cvl Engneeng, Inha Unvesty, Incheon, Koea, heesung80@hanmal.net

More information

ARTICULATED MOTION ANALYSIS FROM MOTION CAPTURE DATA

ARTICULATED MOTION ANALYSIS FROM MOTION CAPTURE DATA ARICULAED MOION ANALYSIS FROM MOION CAPURE DAA J. Fayad, A. Del Bue and P. M. Q. Agua 3. ABSRAC We pesent computatonal methods to extact and model dffeent onts of a genec subect, n an automatc way. he

More information

Visual Image Retrieval by Elastic Matching of User Sketches

Visual Image Retrieval by Elastic Matching of User Sketches IEEE TASACTIS PATTE AAYSIS AD MACHIE ITEIGECE, V. 9,., FEBUAY 997 Vsual Image eteval by Elastc Matng of Use Sketes Albeto Del Bmbo, Membe, IEEE, and Peto Pala, Membe, IEEE Abstact Effectve mage eteval

More information

A LIGHT SCATTERING METHOD TO MEASURE REAL-TIME PARTICULATE EMISSIONS

A LIGHT SCATTERING METHOD TO MEASURE REAL-TIME PARTICULATE EMISSIONS A Lght Scatteng Method to Measue Real-tme Patculate Emssons Rose Gong & Keyn Wllams 6 th Austalasan Tanspot Reseach Foum Wellngton New Zealand -3 Octobe 003 A LIGHT SCATTERING METHOD TO MEASURE REAL-TIME

More information

Fair NURBS Curve Generation using a Hand-drawn Sketch for Computer Aided Aesthetic Design

Fair NURBS Curve Generation using a Hand-drawn Sketch for Computer Aided Aesthetic Design Poceedngs of the 7th WSEAS Int. Conf. on Sgnal Pocessng, Computatonal Geomet & Atfcal Vson, Athens, Geece, August 24-26, 27 29 Fa NURBS Cuve Geneaton usng a Hand-dawn Sketch fo Compute Aded Aesthetc Desgn

More information

USING VIRTUAL REALITY TO DEVELOP SIX LEGGED WALKING ROBOT CONTROL SYSTEM

USING VIRTUAL REALITY TO DEVELOP SIX LEGGED WALKING ROBOT CONTROL SYSTEM Robotcs, vtual ealty, vsualzaton, smulaton, walkng obot Tomáš MICHULEK * USING VIRTUAL REALITY TO DEVELOP SIX LEGGED WALKING ROBOT CONTROL SYSTEM Abstact Ths contbuton pesents the fst esults of ou wok

More information

A METHODOLOGY FOR RATING AND RANKING HAZARDS IN MARITIME FORMAL SAFETY ASSESSMENT USING FUZZY

A METHODOLOGY FOR RATING AND RANKING HAZARDS IN MARITIME FORMAL SAFETY ASSESSMENT USING FUZZY Doumas N. Geogos, Nktakos V. Nñtas, ambou A. aa A ETODOOGY FOR RATING AND RANKING AZARDS IN ARITIE FORA SAFETY ASSESSENT USING FUZZY OGIC A ETODOOGY FOR RATING AND RANKING AZARDS IN ARITIE FORA SAFETY

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

Fuzzy clustering ensemble based on mutual information

Fuzzy clustering ensemble based on mutual information Poceedngs of the 6th WSEAS Intenatonal Confeence on Smulaton, Modellng and Optmzaton, Lsbon, Potugal, Septembe 22-24, 26 476 Fuzz clusteng ensemble based on mutual nfomaton YAN GAO SHIWEN GU LIMING XIA

More information

Research and Application of Fingerprint Recognition Based on MATLAB

Research 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 information

Simultaneous Position, Velocity, Attitude, Angular Rates, and Surface Parameter Estimation Using Astrometric and Photometric Observations

Simultaneous Position, Velocity, Attitude, Angular Rates, and Surface Parameter Estimation Using Astrometric and Photometric Observations Smultaneous Poston, Velocty, Atttude, Angula Rates, and Suface Paamete Estmaton Usng Astometc and Photometc Obsevatons Chales J. Wettee and C. Channng Chow Pacfc Defense Solutons, LLC Khe, Hawa, USA jac.wettee@pacfcds.com

More information

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension

Segmentation of Casting Defects in X-Ray Images Based on Fractal Dimension 17th Wold Confeence on Nondestuctive Testing, 25-28 Oct 2008, Shanghai, China Segmentation of Casting Defects in X-Ray Images Based on Factal Dimension Jue WANG 1, Xiaoqin HOU 2, Yufang CAI 3 ICT Reseach

More information

A modal estimation based multitype sensor placement method

A modal estimation based multitype sensor placement method A modal estimation based multitype senso placement method *Xue-Yang Pei 1), Ting-Hua Yi 2) and Hong-Nan Li 3) 1),)2),3) School of Civil Engineeing, Dalian Univesity of Technology, Dalian 116023, China;

More information

We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors

We are IntechOpen, the world s leading publisher of Open Access books Built by scientists, for scientists. International authors and editors We ae IntechOpen, the wold s leadng publshe of Open Access books Bult by scentsts, fo scentsts 3,500 108,000 1.7 M Open access books avalable Intenatonal authos and edtos Downloads Ou authos ae among the

More information

Goniocolorimetry: from measurement to representation in the CIELAB color space

Goniocolorimetry: from measurement to representation in the CIELAB color space Gonocolomety: fom measuement to epesentaton n the CIELAB colo space Lonel Smonot PHYMAT: Physque des Matéaux, UMR CNRS 6630, Boulevad Mae et Pee Cue, BP 179, 8696 Futuoscope Chasseneul Cedex, Fance Coespondng

More information

Topic -3 Image Enhancement

Topic -3 Image Enhancement Topic -3 Image Enhancement (Pat 1) DIP: Details Digital Image Pocessing Digital Image Chaacteistics Spatial Spectal Gay-level Histogam DFT DCT Pe-Pocessing Enhancement Restoation Point Pocessing Masking

More information

Positioning of a robot based on binocular vision for hand / foot fusion Long Han

Positioning of a robot based on binocular vision for hand / foot fusion Long Han 2nd Intenational Confeence on Advances in Mechanical Engineeing and Industial Infomatics (AMEII 26) Positioning of a obot based on binocula vision fo hand / foot fusion Long Han Compute Science and Technology,

More information

School of Computer Science. control algorithms for use in datagram networks. rates to alleviate the congestion. In the case

School of Computer Science. control algorithms for use in datagram networks. rates to alleviate the congestion. In the case WF 2 Q: Wost-case Fa Weghted Fa Queueng Jon C.R. Bennett FORE Systems Hu Zhang School of Compute Scence Canege Mellon Unvesty Abstact The Genealzed Pocesso Shang (GPS) dscplne s poven to have two desable

More information

Interactive Rendering of Deforming NURBS Surfaces

Interactive Rendering of Deforming NURBS Surfaces EUROGRAHICS 97 / D. Fellne and L. Szmay-Kalos Volume 6, (997), Numbe 3 (Guest Edtos) Inteactve Rendeng of Defomng NURBS Sufaces Fedeck W. B. L Rynson W. H. Lau Mak Geen Compute Gaphcs and Meda Laboatoy

More information

GENERAL MODEL FOR AIRBORNE AND SPACEBORNE LINEAR ARRAY SENSORS

GENERAL MODEL FOR AIRBORNE AND SPACEBORNE LINEAR ARRAY SENSORS GENERAL MODEL FOR AIRBORNE AND SPAEBORNE LINEAR ARRAY SENSORS Danela Pol Insttute of Geodesy and Photogammety, Swss Fedeal Insttute of Technology, Zuch, Swtzeland danela@geod.baug.ethz.ch KEY WORDS: Oentaton,

More information

Distribution Ray Tracing

Distribution Ray Tracing Dstbuton Ray Tacng In Whtte Ray Tacng we compute lghtng vey cuely Phong + specula global lghtng In Dstbute Ray Tacng we want to compute the lghtng as accuately as possble Use the fomalsm of Raomety Compute

More information

FILTERING OF LASER SCANNING DATA IN FOREST AREAS USING FINITE ELEMENTS

FILTERING OF LASER SCANNING DATA IN FOREST AREAS USING FINITE ELEMENTS FILTERING OF LASER SCANNING DATA IN FOREST AREAS USING FINITE ELEMENTS Pete Kzystek Dept. of Geonfomatcs, Unvesty of Appled Scences, Munch, Gemany kzystek@geo.fhm.edu Commsson III, WG III/3 KEY WORDS:

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

An Optimization Procedure In A Production Line Of Sokat Soap Industry, Ikotun, Lagos State. Adamawa State, Nigeria.

An Optimization Procedure In A Production Line Of Sokat Soap Industry, Ikotun, Lagos State. Adamawa State, Nigeria. An Optmzaton Pocedue In A Poducton Lne Of Sokat Soap Industy, Ikotun, Lagos State. 1 O.S. Balogun, 2 A.A. Olatun and 3 A.A. Momoh 1 Depatment of Statstcs and Opeatons Reseach, Modbbo Adama Unvesty of Technology,

More information

SOFT COMPUTING OPTIMIZATION TECHNIQUES FOR SOLAR PHOTOVOLTAIC ARRAYS

SOFT COMPUTING OPTIMIZATION TECHNIQUES FOR SOLAR PHOTOVOLTAIC ARRAYS ARPN Jounal of Engneeng and Appled Scences 2006-20 Asan Reseach Publshng Netwok (ARPN). All ghts eseved. SOFT COMPUTING OPTIMIZATION TECHNIQUES FOR SOLAR PHOTOVOLTAIC ARRAYS Ramapabha R. and Mathu B. L.

More information

NURBS Curve Shape Modification and Fairness Evaluation for Computer Aided Aesthetic Design

NURBS Curve Shape Modification and Fairness Evaluation for Computer Aided Aesthetic Design oceedngs of the 7th WSEAS Int. Conf. on Sgnal ocessng, Computatonal Geomet & Atfcal Vson, Athens, Geece, August 4-6, 7 38 NURBS Cuve Shape Modfcaton and Faness Evaluaton fo Compute Aded Aesthetc Desgn

More information

(a, b) x y r. For this problem, is a point in the - coordinate plane and is a positive number.

(a, b) x y r. For this problem, is a point in the - coordinate plane and is a positive number. Illustative G-C Simila cicles Alignments to Content Standads: G-C.A. Task (a, b) x y Fo this poblem, is a point in the - coodinate plane and is a positive numbe. a. Using a tanslation and a dilation, show

More information

IP Network Design by Modified Branch Exchange Method

IP Network Design by Modified Branch Exchange Method Received: June 7, 207 98 IP Netwok Design by Modified Banch Method Kaiat Jaoenat Natchamol Sichumoenattana 2* Faculty of Engineeing at Kamphaeng Saen, Kasetsat Univesity, Thailand 2 Faculty of Management

More information

THE HIERARCHICAL MODEL OF INTERACTION BETWEEN INTELLIGENT AGENTS IN THE MANET CONTROL SYSTEMS

THE HIERARCHICAL MODEL OF INTERACTION BETWEEN INTELLIGENT AGENTS IN THE MANET CONTROL SYSTEMS UDC 6.396.4 THE HIERARCHICAL MODEL OF INTERACTION BETWEEN INTELLIGENT AGENTS IN THE MANET CONTROL SYSTEMS Oleg Ya. Sova Valey A. Romanyuk Mltay Insttute of Telecommuncatons and Infomatzaton Kyv Ukane Dmyto

More information

Illumination methods for optical wear detection

Illumination methods for optical wear detection Illumination methods fo optical wea detection 1 J. Zhang, 2 P.P.L.Regtien 1 VIMEC Applied Vision Technology, Coy 43, 5653 LC Eindhoven, The Nethelands Email: jianbo.zhang@gmail.com 2 Faculty Electical

More information

Statistical Bayesian Learning for Automatic Arabic Text Categorization

Statistical Bayesian Learning for Automatic Arabic Text Categorization Jounal of Compute Scence 7 (): 39-45, 20 ISSN 549-3636 20 Scence Publcatons Statstcal Baesan Leanng fo Automatc Aabc Text Categozaton Bassam Al-Salem and Mohd. Juzaddn Ab Azz Depatment of Compute Scence,

More information

An Extension to the Local Binary Patterns for Image Retrieval

An Extension to the Local Binary Patterns for Image Retrieval , pp.81-85 http://x.oi.og/10.14257/astl.2014.45.16 An Extension to the Local Binay Pattens fo Image Retieval Zhize Wu, Yu Xia, Shouhong Wan School of Compute Science an Technology, Univesity of Science

More information