Integrated Expression-Invariant Face Recognition with Constrained Optical Flow

Size: px
Start display at page:

Download "Integrated Expression-Invariant Face Recognition with Constrained Optical Flow"

Transcription

1 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow Chao-Kue Hseh, Shang-Hong La 2, and Yung-Chang Chen Department of Electrcal Engneerng, Natonal Tsng Hua Unversty, Tawan 2 Department of Computer Scence, Natonal Tsng Hua Unversty, Tawan d9395@oz.nthu.edu.tw, la@cs.nthu.edu.tw, ycchen@ee.nthu.edu.tw Abstract. Face recognton s one of the most ntensvely studed topcs n computer vson and pattern recognton. A constraned optcal flow algorthm, whch combnes the advantages of the unambguous correspondence of feature pont labelng and the flexble representaton of optcal flow computaton, has been proposed n our pervous work for face recognton from expressonal face mages. In ths paper, we propose an ntegrated face recognton system that s robust aganst facal expressons by combnng nformaton from the computed ntra-person optcal flow and the syntheszed face mage n a probablstc framework. Our expermental results show that the proposed system mproves the accuracy of face recognton from expressonal face mages. Keywords: Face recognton, expresson recognton, constraned optcal flow, expresson normalzaton. Introducton Face recognton has been studed for the past few decades. Even though the 2D face recognton methods have been actvely studed n the past, there are stll nherent dsadvantages and drawbacks. It was shown that the recognton rate can drop dramatcally when the head pose and llumnaton varatons are too large, or when there s expresson on the face mage. Pose, llumnaton, and expresson varatons are three essental ssues to be dealt wth n the research of face recognton. Some authors have proposed dfferent approaches to deal wth such expresson varatons. One way [] s to compute the optcal flow between the testng and tranng face mage. Another way [2] used a mask or a morphable model for the mage regstraton n a face recognton system. In our prevous work, we combned the advantages of the above two approaches: the unambguous correspondence of feature pont labelng and the flexble representaton of optcal flow computaton. A constraned optcal flow algorthm was proposed, whch can deal wth poston movements and ntensty changes at the same tme when handlng the correspondng feature ponts. We have then appled the algorthm not only to the applcaton of face recognton from expresson normalzaton [3], but also on the nter- and ntra-person T. Wada, F. Huang, and S. Ln (Eds.): PSIVT 29, LNCS 544, pp , 29. Sprnger-Verlag Berln Hedelberg 29

2 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 73 optcal flow analyss [4], whch can be used for further face and expresson recognton. Both methods can mprove the accuracy of the face recognton from expressonal face mages, even though dfferent nformaton s utlzed n these two algorthms. In ths paper, we propose to explot two dfferent types of nformaton,.e. the computed optcal flow and the syntheszed mage, to mprove the accuracy of face recognton. Expermental valdaton s gven to show the mproved performance of the proposed face recognton system. The remanng of ths paper s organzed as follows. We brefly revew the constraned optcal flow computatonal technque and our prevous works on expresson normalzaton and expresson optcal flow analyss n secton 2 and 3, respectvely. The proposed face recognton system s presented n secton 4. Secton 5 gves some expermental results and secton 6 concludes ths paper. 2 Constraned Optcal Flow Computaton The computatonal algorthms of tradtonal optcal flow cannot guarantee that the computed optcal flow corresponds to the exact pxels n dfferent mages, snce the ntensty varatons due to expresson may mslead the computaton of optcal flow. Teng et al. [5] proposed to mnmze the followng dscrete energy functon to compute the optcal flow, whch used an adaptve smoothness adjustment scheme consdered both flow components (u and v ) and all the brghtness varaton multpler and offset factors (m and c ) Ix, u+ Iy, v+ It, + mi + c f ( u) = w D Ix, Iy, I λ α + α + β + β ( x, ux, y, uy, x, vx, y, vy, ) D ( x, mx, y, my, x, cx, y, cy, ) + μ γ + γ + δ + δ D Furthermore, t can be rewrtten n a matrx-vector form and effcently solved by the ncomplete Cholesky precondtoned conjugate gradent (ICPCG) algorthm [5]. In order to guarantee the computed optcal flow to be consstent to the moton vectors at these correspondng feature ponts, we modfy the unconstraned optmzaton problem n the orgnal formulaton of the optcal flow estmaton to a constraned optmzaton problem [3] gven as follows: T T ( u) = u Ku 2 u b+ c, (, ), (, ), (, ) mnmze f subject to u x y = u and v x y = v x y S where S s the set of feature ponts and (, ) u v s the specfed optcal flow vector at the th feature pont. We appled a modfed ICPCG procedure to solve ths constraned optmzaton problem and the detals are referred to [3]., 2 ()

3 74 C.-K. Hseh, S.-H. La, and Y.-C. Chen 3 Prevous Works In ths secton, we brefly revew expresson normalzaton [3] and nter- and ntraperson optcal flow analyss [4] n our prevous works. 3. Expresson Normalzaton The face recognton problem can be consdered as to determne the class c that mnmzes the dfference between the reference mage R c and the syntheszed neutral mage from the testng facal expresson mage T by usng R c as the reference. After the mage algnment and normalzaton of the nput testng mage T and reference mage R c, where c =,2,,C, and C s the total number of subjects n the face database, we can formulate the face recognton problem as follows: ( ( c) ) arg mn R Syn T; OF T; R c c To further mprove the computatonal effcency, we modfy the face recognton problem as follows: ( Rc ( Rc ) ) ( T ( T ) ) arg mn Syn ; OF ; Syn ; OF ; c where s a unversal neutral face mage. To be more specfc, nstead of transformng the nput mage to the neutral mage for each class, we now transform all mages to a unversal coordnate as. We defne the operaton, Syn( T; OF ( T; R c )), as the OF-Syn operator. The modfed system flow chart s shown n Fg.. Although there are C+ OF-Syn operators n total, the C OF-Syn operatons among them can be performed n advance, thus only one such operaton s needed n the testng or recognton phase. (2) (3) OF-Syn OF-Syn - 2 OF-Syn M OF-Syn Preprocessng Testng after nput - Comparator - Result Fg.. The proposed expresson-nvarant face recognton flow chart accordng to Eq. (3) 3.2 Expresson Optcal Flow Analyss The tradtonal expressve optcal flow s computed from a neutral face mage of person to an expresson mage EX,k wth expresson k of the same subject. However,

4 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 75 the computed optcal flows are generally not n the same coordnate, snce the geometry of neutral faces s dfferent for dfferent persons. Some research only consdered moton vectors at certan feature ponts to overcome ths problem, but only lmted nformaton about facal movement s used n ths case. EX 2, EX, OF ntra,2_ OF all,2_ OF all,_ OF ntra,_ 2 OF nter, OF nter,2 Fg. 2. Illustraton of decomposng nput optcal flow (OF all ) to nter-person (OF nter ) and ntraperson (OF ntra ) parts We proposed a dfferent soluton for optcal flow normalzaton, as shown n Fg. 3. Instead of computng the ntra-person optcal flow OF ntra,_k drectly from the neutral face to an expressve face mage for each person, we start from a global neutral face to obtan the nter-person optcal flow OF nter, = OF( ; ) and overall optcal OF all,_k = OF( ; EX,k ). The ntra-person optcal flow can then be generated by pxelwse dfferencng as follows: OF ntra,_k = OF all,_k - OF nter,. (4) There are two advantages of dong t ths way: () all expressve face mages of every subject have the same number of moton vectors; (2) all optcal flows are computed on the same geometry of. After obtanng the normalzed optcal flows from dfferent expressons, we consder t as a problem of subspace modelng. In other words, we can extract K optcal flow bases OB ntra,k to descrbe ntra-person optcal flows. Moreover, when there s an nput mage, we can recognze the face by determnng the person, whose nter-person optcal flow OF nter, makes the ntra-person optcal flow be best spanned by the traned optcal flow bases. Ths can be formulated as the followng optmzaton problem: arg mn ( ) nput nter, k ntra, k b, kk, =,..., K k= K OF OF b OB (5) Furthermore, the spannng coeffcents b k of each bass OB ntra,k may be used for expresson recognton. A negatve coeffcent does not make sense n physcal

5 76 C.-K. Hseh, S.-H. La, and Y.-C. Chen expresson moton, thus we proposed a modfed egenvector algorthm to enforce non-negatve projecton coeffcents. 4 Proposed Face Recognton System There are two types of nformaton generated by the constraned optcal flow algorthm: the optcal flow and the syntheszed neural face mage by mage warpng wth the computed optcal flow. As dscussed n the prevous secton, the two face recognton methods based on the expresson normalzed mages and the computed optcal flow are descrbed n secton 3. and 3.2, respectvely. In the frst method, the optcal flows for the nput expresson-varant mages are dfferent from dfferent subjects n terms of geometry and dmensonalty, thus the optcal flow nformaton was not used for comparson n the frst method. On the other hand, n the second method, we compute the optcal flow n the opposte drecton,.e. from the global neutral face to an nput expresson varant face, to preserve the same geometry for the computed optcal flow, but t cannot be used drectly to synthesze the correspondng neutral mage for comparson. Only partal nformaton was exploted n each of these two methods. In ths paper, we ntend to ntegrate these two methods nto the proposed expresson-nvarant face recognton system to fully explot the nformaton of the optcal flow and the syntheszed neutral mage for face recognton. To do ths, we formulate the problem as follows: N, E ( N I ) max P, E, =,2,..., N where I s the nput mage, N s a neutral face mage n tranng data set, and E denotes the expresson optcal flow vector between I and N. Based on the posteror probablty, equaton (6) can be rewrtten as N, E ( ) ( ) ( ) max P N P E P I N, E. Furthermore, the occurrence probablty of each canddate s assumed equally probable,.e. P(N ) s a constant for all. The formulaton can be smplfed as N, E ( ) ( E) max P E P I N,. There are two parts n equaton (8),.e. the probablty of the expresson movement P(E), and the probablty of the nput mage under the condton of the subject N wth the expresson E. As dscussed before, a sngle type of optcal flow cannot keep the unformty of dmensonalty and geometry n both crcumstances. Thus. we defne P(E) and P(I N, E) separately. To further defne P(E) wth preservaton of dentcal geometry and dmensonalty for each N, we use the same strategy n method 2,.e. the ntra-person optcal flow. Wth equaton (4), the moton nformaton E n P(E) s defned as ( xy, ) = ( xy, ) ( @ u v w, (9) (6) (7) (8)

6 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 77 where v(x, y) s the overall optcal flow from global neutral face to nput mage I, w(x, y) s the nter-person optcal flow from to the guessed neutral face N, and u(x, y) s the ntra-person optcal flow from N to I. Moreover, and the denotes the optcal flow represented wth the geometry of, even though the ntra-person optcal flow s defned as the pxel-wsed movement from N to I. The probablty of P(I N, E) s then defned as the smlarty between nput mage I and the syntheszed mage from neutral face N and the computed optcal flow movement,.e. P I Syn N, exp ( I N E) ( ; u ) N. 2 σ Snce the optcal flow used for syntheszng neutral face N to a certan expresson must be represented wth the same geometry of N, the ntra-person optcal flow u ( xy, ) n equaton (9) s not approprate n ths crcumstance. An ntra-person optcal flow under the geometry of N s needed n equaton (). The MAP optmzaton problem s now rewrtten as ( ; u@ N ) 2 I Syn N max P( E) P( I N, E) = max P( ) exp, 2,, E E σ N N Thus two components are needed to compute n the above formulaton: one s the ntra-person optcal flow at the geometry of (Intra@ ), and the other s the ntra-person optcal flow at the geometry of (Intra@N ). We can frst compute the optcal flow Intra@ drectly and warp t to obtan Intra@ (Fg., defned as procedure ), or oppostely, we can compute Intra@ frst and then warp to Intra@ (Fg., defned as procedure 2). In the frst flow, we compute Intra@ as the dagram shown n Fg. 3,.e. (2) = OF ; Input OF ;. ( ) ( ) The optcal flow Intra@ can be smply obtaned by computng OF( ; Input). After collectng one type of ntra-person optcal flow, we can further obtan the other one by nonlnear warpng wth the nter-person optcal flow as shown n Fg. 4. Take Intra@ to Intra@ for example. The movement of each pxel has been obtaned n Intra@ calculaton. The correspondng poston n of each pxel n can be determned easly through nter-person optcal flow Inter@. In most cases, the correspondng poston s not on nteger grd. We can estmate the moton of each non-nteger pxel by blnear nterpolaton. The overall system flowcharts of procedure and 2 are depcted n Fg. 5 and Fg. 6, respectvely. In procedure, snce the OF block of OF( ; ) can be pre-computed n the tranng process, only one optcal flow calculaton, the Input@ s needed n the testng process. However, the optcal flow used for synthess, whch requres more precson, s obtaned through a long computatonal procedure. Ths may damage the () ()

7 78 C.-K. Hseh, S.-H. La, and Y.-C. Chen ( ; Input ) OF ( ; ) OF Inter Intr a@ N Fg. 3. Intra-person optcal flow, Intra@ calculaton n procedure ( ; ) OF Input Intra@ ( ) OF ; Fg. 4. Dagram of ntra-person optcal flow mappng from one person to another qualty of the syntheszed result f any non-neglgble naccuracy s nvolved durng the flow. In procedure 2, on the other hand, even though the operaton OF( ; ) can be pre-computed n the tranng process as well, the OF block OF( ; Input) s requred to compute for each guess. There are totally C tmes of OF computatons n the testng procedure, whch are drectly followed by mage synthess block. The objectve functon can be computed after the two types of ntra-person optcal flow are calculated. We consdered the probablty of ntra-person optcal flow as a mxture of Gaussan probablty dstrbuton wth centers correspondng to the samples n the tranng optcal flow dataset, that s, P u f y y y y y = = 2 T T T ) = ( ) exp ( ) ( ) Σ, (3) where y s the ntra-person optcal flow n the tranng data, s the ndex and T s the number of tranng sample, and y denotes u. As for the smlarty between nput mage and the syntheszed mages, we drectly calculate the recprocal of the

8 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 79 of_ntra@ C Fg. 5. System flowchart of procedure C C Fg. 6. System flowchart of procedure 2 of_ntra@ C of_ntra@ C Fg. 7. Modfed system flowchart of procedure 2 average of pxel-wse dfference between them. Accordng to the orgnal defnton, snce the two values are under dfferent scales, one wll domnate the result of fnal probablty. Instead of comparng the fnal result after combnng the two values as

9 7 C.-K. Hseh, S.-H. La, and Y.-C. Chen shown n Fg. 6, we modfy the flow to Fg. 7. We compare and score the two values separately frst, and then combne the scores for fnal decson as S Fnal = r S P(E) + S P(I N, E), (4) where r s a weght determned emprcally. S P(E) and S P(I N, E) stand for the score of P(E) and P(I N, E) respectvely. 5 Expermental Results Our experments were performed on the Bnghamton Unversty 3D Face Expresson (BU-3DFE) Database [6]. The BU-3DFE database contans the face mages and 3D face models of subjects (56 females and 44 males) each wth a neutral face and 6 dfferent expressons (angry, dsgust, fear, happy, sad, and surprsed) at dfferent levels (from level (weakest) to 4 (strongest)). Note that only the 2D face mages were used n our experments. Among them, 34 subjects are randomly selected for ntra-person optcal flow tranng, and the others are used as the testng set. 5. Pre-processng We manually labeled 2 feature ponts, ncludng 3 ponts for each eyebrow and 4 ponts for each eye, one at the nose tp and the other 6 around the mouth regon. Wth the labeled ponts, the dstance between the outer corners of both eyes s used as the reference to normalze face mages. 5.2 Face Recognton wth Proposed System As descrbed n the prevous secton, we follow the modfed flowchart shown n Fg. 8. We apply a mask (Fg. 8(b)) defned from the global neutral face (Fg. 8(a)) to extract the regon of nterest. Moreover, the regon nsde the mouth s dscarded, as llustrated n Fg. 8(e). Both the optcal flow and the grayscales of the syntheszed mage wthn the mask wll be used n face recognton process. Some expermental mages are shown n Fg. 8. For an nput mage (Fg. 8(d)), we frst poston the correspondng mask (Fg. 8(e)) to obtan the masked mage (Fg. 8(f)). After that, for each canddate n the database (Fg. 8(g) and 8(j)), the ntra-person optcal flow,.e. ntra@, s computed and used for vrtual mage synthess (Fg. 8(h) and Fg. 8(k)). The masked mages (Fg. 8() and 8(l)) can fnally be appled for smlarty comparson. Expresson-nvarant face recognton results are lsted n Table -3. Accordng to the results, the average face recognton rates based on the syntheszed mage or the ntra-person optcal flow ndvdually are 85.86% and 82.39%, respectvely. In addton to usng the syntheszed mage and optcal flow nformaton separately, we also carry out the face recognton experment by usng the proposed ntegrated soluton,.e. based on Equ. (4). In ths experment, to ponts are gven to the top ten canddates n each comparson, and we equally weght the nformaton of syntheszed mage and ntra-person optcal flow,.e. r =. The recognton rate s mproved to 9.28% as shown n Table 3.

10 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 7 (a) (b) (c) (d) (e) (f) (g) (h) () (j) (k) (l) Fg. 8. Illustraton of expermental mages: (a) global neutral face, (b) mask mage, (c) masked mage of (a), (d) nput mage, (e) warped mask mage, (f) masked nput mage, (g) guessed subject, (h) syntheszed face from (g) to (d), () masked syntheszed mage (g) usng mask mage (e), (j) guessed subject 2, (k) syntheszed face from (g) to (d), and (l) masked syntheszed mage (k) usng mask mage (e) Table. Recognton result usng the syntheszed face mages only Expresson Level (%) Level 2(%) Level 3(%) Level 4(%) Average AN DI FE HA SA SU % The mpact of dfferent weghtng s also dscussed n our experment. We try dfferent weghtngs rangng from.5 to 2 and the face recognton accuraces are depcted n Fg. 9. We can see that the proposed system can acheve the best accuracy at 93% when r =.7, whch means the syntheszed mage s of hgher sgnfcance.

11 72 C.-K. Hseh, S.-H. La, and Y.-C. Chen Table 2. Recognton result usng ntra-person optcal flow only Expresson Level (%) Level 2(%) Level 3(%) Level 4(%) Average AN DI FE HA SA SU % Table 3. Recognton result usng the ntegrated nformaton, ncludng the syntheszed mages and ntra-person optcal flow Expresson Level (%) Level 2(%) Level 3(%) Level 4(%) Average AN DI FE HA SA SU % 94% 92% 9% 88% 86% Fg. 9. Recognton result on the test data wth dfferent weghtng parameters n eq.(4) 6 Concluson In ths paper, we proposed an ntegrated expresson-nvarant face recognton system based on the constraned optcal flow. In the prevous works on optcal flow based face recognton, ether the syntheszed face mage or the ntra-person flow s used ndvdually for face and expresson recognton. In ths work, we proposed to ntegrate the nformaton of syntheszed mages and the ntra-person optcal flow dstrbuton probablty to mprove the face recognton accuracy. As the expermental results shows, the proposed system mproves the accuracy of face and expresson recognton on expressonal face mages. However, the proposed ntegrated system s more computatonally costly compared to the prevous works, snce the optcal flow computaton, ntra-person optcal flow mappng and mage synthess are needed for all canddates n the database. Ths s the man research topc n our future study.

12 Integrated Expresson-Invarant Face Recognton wth Constraned Optcal Flow 73 References. L, X., Mor, G., Zhang, H.: Expresson-nvarant face recognton wth expresson classfcaton. In: Proc. 3rd Canadan Conf. on Computer and Robot Vson (June 26) 2. Martnez, A.M.: Recognzng expresson varant faces from a sngle sample mage per class. In: Proc. IEEE Conf. Computer Vson Pattern Recognton (June 23) 3. Hseh, C.-K., La, S.-H., Chen, Y.-C.: Expresson-nvarant face recognton wth accurate optcal flow. In: Ip, H.H.-S., Au, O.C., Leung, H., Sun, M.-T., Ma, W.-Y., Hu, S.-M. (eds.) PCM 27. LNCS, vol. 48, pp Sprnger, Hedelberg (27) 4. Hseh, C.-K., La, S.-H., Chen, Y.-C.: Expressonal face mage analyss wth constraned optcal flow. In: Proc. of ICME, Hannover, Germany, June (28) 5. Teng, C.-H., La, S.-H., Chen, Y.-S., Hsu, W.-H.: Accurate optcal flow computaton under non-unform brghtness varatons. In: Computer Vson and Image Understandng, vol. 97, pp (25) 6. Yn, L., We, X., Sun, Y., Wang, J., Rosato, M.J.: A 3D facal expresson database for facal behavor research. In: Proc. Intern. Conf. on Automatc Face and Gesture Recognton, pp (Aprl 26)

Parallelism for Nested Loops with Non-uniform and Flow Dependences

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

More information

A Binarization Algorithm specialized on Document Images and Photos

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

More information

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

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

More information

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

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

More information

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

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

More information

Recognizing Faces. Outline

Recognizing Faces. Outline Recognzng Faces Drk Colbry Outlne Introducton and Motvaton Defnng a feature vector Prncpal Component Analyss Lnear Dscrmnate Analyss !"" #$""% http://www.nfotech.oulu.f/annual/2004 + &'()*) '+)* 2 ! &

More information

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

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

More information

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS

EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS P.G. Demdov Yaroslavl State Unversty Anatoly Ntn, Vladmr Khryashchev, Olga Stepanova, Igor Kostern EYE CENTER LOCALIZATION ON A FACIAL IMAGE BASED ON MULTI-BLOCK LOCAL BINARY PATTERNS Yaroslavl, 2015 Eye

More information

Local Quaternary Patterns and Feature Local Quaternary Patterns

Local 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 information

A Fast Content-Based Multimedia Retrieval Technique Using Compressed Data

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

More information

An efficient method to build panoramic image mosaics

An efficient method to build panoramic image mosaics An effcent method to buld panoramc mage mosacs Pattern Recognton Letters vol. 4 003 Dae-Hyun Km Yong-In Yoon Jong-Soo Cho School of Electrcal Engneerng and Computer Scence Kyungpook Natonal Unv. Abstract

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

A Fast Visual Tracking Algorithm Based on Circle Pixels Matching

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

More information

A Background Subtraction for a Vision-based User Interface *

A Background Subtraction for a Vision-based User Interface * A Background Subtracton for a Vson-based User Interface * Dongpyo Hong and Woontack Woo KJIST U-VR Lab. {dhon wwoo}@kjst.ac.kr Abstract In ths paper, we propose a robust and effcent background subtracton

More information

Learning a Class-Specific Dictionary for Facial Expression Recognition

Learning a Class-Specific Dictionary for Facial Expression Recognition BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 16, No 4 Sofa 016 Prnt ISSN: 1311-970; Onlne ISSN: 1314-4081 DOI: 10.1515/cat-016-0067 Learnng a Class-Specfc Dctonary for

More information

Face Recognition University at Buffalo CSE666 Lecture Slides Resources:

Face Recognition University at Buffalo CSE666 Lecture Slides Resources: Face Recognton Unversty at Buffalo CSE666 Lecture Sldes Resources: http://www.face-rec.org/algorthms/ Overvew of face recognton algorthms Correlaton - Pxel based correspondence between two face mages Structural

More information

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

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

More information

Cluster Analysis of Electrical Behavior

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

More information

An Image Fusion Approach Based on Segmentation Region

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

More information

Lecture 5: Multilayer Perceptrons

Lecture 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 information

User Authentication Based On Behavioral Mouse Dynamics Biometrics

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

More information

Classifier Selection Based on Data Complexity Measures *

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

More information

Support Vector Machines

Support Vector Machines /9/207 MIST.6060 Busness Intellgence and Data Mnng What are Support Vector Machnes? Support Vector Machnes Support Vector Machnes (SVMs) are supervsed learnng technques that analyze data and recognze patterns.

More information

FEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur

FEATURE 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 information

Human Face Recognition Using Generalized. Kernel Fisher Discriminant

Human Face Recognition Using Generalized. Kernel Fisher Discriminant Human Face Recognton Usng Generalzed Kernel Fsher Dscrmnant ng-yu Sun,2 De-Shuang Huang Ln Guo. Insttute of Intellgent Machnes, Chnese Academy of Scences, P.O.ox 30, Hefe, Anhu, Chna. 2. Department of

More information

Edge Detection in Noisy Images Using the Support Vector Machines

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

More information

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

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

More information

On Modeling Variations For Face Authentication

On Modeling Variations For Face Authentication On Modelng Varatons For Face Authentcaton Xaomng Lu Tsuhan Chen B.V.K. Vjaya Kumar Department of Electrcal and Computer Engneerng, Carnege Mellon Unversty Abstract In ths paper, we present a scheme for

More information

S1 Note. Basis functions.

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

More information

Collaboratively Regularized Nearest Points for Set Based Recognition

Collaboratively Regularized Nearest Points for Set Based Recognition Academc Center for Computng and Meda Studes, Kyoto Unversty Collaboratvely Regularzed Nearest Ponts for Set Based Recognton Yang Wu, Mchhko Mnoh, Masayuk Mukunok Kyoto Unversty 9/1/013 BMVC 013 @ Brstol,

More information

Review of approximation techniques

Review of approximation techniques CHAPTER 2 Revew of appromaton technques 2. Introducton Optmzaton problems n engneerng desgn are characterzed by the followng assocated features: the objectve functon and constrants are mplct functons evaluated

More information

Multi-View Face Alignment Using 3D Shape Model for View Estimation

Multi-View Face Alignment Using 3D Shape Model for View Estimation Mult-Vew Face Algnment Usng 3D Shape Model for Vew Estmaton Yanchao Su 1, Hazhou A 1, Shhong Lao 1 Computer Scence and Technology Department, Tsnghua Unversty Core Technology Center, Omron Corporaton ahz@mal.tsnghua.edu.cn

More information

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

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

More information

Using Fuzzy Logic to Enhance the Large Size Remote Sensing Images

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

More information

Detection of an Object by using Principal Component Analysis

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

More information

PCA Based Gait Segmentation

PCA 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 information

Outline. Discriminative classifiers for image recognition. Where in the World? A nearest neighbor recognition example 4/14/2011. CS 376 Lecture 22 1

Outline. 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 information

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures

A Novel Adaptive Descriptor Algorithm for Ternary Pattern Textures A Novel Adaptve Descrptor Algorthm for Ternary Pattern Textures Fahuan Hu 1,2, Guopng Lu 1 *, Zengwen Dong 1 1.School of Mechancal & Electrcal Engneerng, Nanchang Unversty, Nanchang, 330031, Chna; 2. School

More information

Development of an Active Shape Model. Using the Discrete Cosine Transform

Development of an Active Shape Model. Using the Discrete Cosine Transform Development of an Actve Shape Model Usng the Dscrete Cosne Transform Kotaro Yasuda A Thess n The Department of Electrcal and Computer Engneerng Presented n Partal Fulfllment of the Requrements for the

More information

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input

Real-time Joint Tracking of a Hand Manipulating an Object from RGB-D Input Real-tme Jont Tracng of a Hand Manpulatng an Object from RGB-D Input Srnath Srdhar 1 Franzsa Mueller 1 Mchael Zollhöfer 1 Dan Casas 1 Antt Oulasvrta 2 Chrstan Theobalt 1 1 Max Planc Insttute for Informatcs

More information

An Optimal Algorithm for Prufer Codes *

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

More information

Classifying Acoustic Transient Signals Using Artificial Intelligence

Classifying 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 information

An AAM-based Face Shape Classification Method Used for Facial Expression Recognition

An AAM-based Face Shape Classification Method Used for Facial Expression Recognition Internatonal Journal of Research n Engneerng and Technology (IJRET) Vol. 2, No. 4, 23 ISSN 2277 4378 An AAM-based Face Shape Classfcaton Method Used for Facal Expresson Recognton Lunng. L, Jaehyun So,

More information

Related-Mode Attacks on CTR Encryption Mode

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

More information

Object-Based Techniques for Image Retrieval

Object-Based Techniques for Image Retrieval 54 Zhang, Gao, & Luo Chapter VII Object-Based Technques for Image Retreval Y. J. Zhang, Tsnghua Unversty, Chna Y. Y. Gao, Tsnghua Unversty, Chna Y. Luo, Tsnghua Unversty, Chna ABSTRACT To overcome the

More information

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

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

More information

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

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

More information

Robust Face Alignment for Illumination and Pose Invariant Face Recognition

Robust Face Alignment for Illumination and Pose Invariant Face Recognition Robust Face Algnment for Illumnaton and Pose Invarant Face Recognton Fath Kahraman 1, Bnnur Kurt 2, Muhttn Gökmen 2 Istanbul Techncal Unversty, 1 Informatcs Insttute, 2 Computer Engneerng Department 34469

More information

CS 534: Computer Vision Model Fitting

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

More information

Shape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram

Shape 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 information

A high precision collaborative vision measurement of gear chamfering profile

A high precision collaborative vision measurement of gear chamfering profile Internatonal Conference on Advances n Mechancal Engneerng and Industral Informatcs (AMEII 05) A hgh precson collaboratve vson measurement of gear chamferng profle Conglng Zhou, a, Zengpu Xu, b, Chunmng

More information

Mathematics 256 a course in differential equations for engineering students

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

More information

An Image Compression Algorithm based on Wavelet Transform and LZW

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

More information

Video Object Tracking Based On Extended Active Shape Models With Color Information

Video Object Tracking Based On Extended Active Shape Models With Color Information CGIV'2002: he Frst Frst European Conference Colour on Colour n Graphcs, Imagng, and Vson Vdeo Object rackng Based On Extended Actve Shape Models Wth Color Informaton A. Koschan, S.K. Kang, J.K. Pak, B.

More information

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

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

More information

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

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

More information

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

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

More information

Novel Fuzzy logic Based Edge Detection Technique

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

More information

MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION

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

More information

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification

12/2/2009. Announcements. Parametric / Non-parametric. Case-Based Reasoning. Nearest-Neighbor on Images. Nearest-Neighbor Classification Introducton to Artfcal Intellgence V22.0472-001 Fall 2009 Lecture 24: Nearest-Neghbors & Support Vector Machnes Rob Fergus Dept of Computer Scence, Courant Insttute, NYU Sldes from Danel Yeung, John DeNero

More information

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

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

More information

Face Recognition using 3D Directional Corner Points

Face Recognition using 3D Directional Corner Points 2014 22nd Internatonal Conference on Pattern Recognton Face Recognton usng 3D Drectonal Corner Ponts Xun Yu, Yongsheng Gao School of Engneerng Grffth Unversty Nathan, QLD, Australa xun.yu@grffthun.edu.au,

More information

Intra-Parametric Analysis of a Fuzzy MOLP

Intra-Parametric Analysis of a Fuzzy MOLP Intra-Parametrc Analyss of a Fuzzy MOLP a MIAO-LING WANG a Department of Industral Engneerng and Management a Mnghsn Insttute of Technology and Hsnchu Tawan, ROC b HSIAO-FAN WANG b Insttute of Industral

More information

The Research of Support Vector Machine in Agricultural Data Classification

The 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 information

A Robust Method for Estimating the Fundamental Matrix

A Robust Method for Estimating the Fundamental Matrix Proc. VIIth Dgtal Image Computng: Technques and Applcatons, Sun C., Talbot H., Ourseln S. and Adraansen T. (Eds.), 0- Dec. 003, Sydney A Robust Method for Estmatng the Fundamental Matrx C.L. Feng and Y.S.

More information

Paintings at an Exhibition EE368 Group 17 Project Report

Paintings at an Exhibition EE368 Group 17 Project Report 1 Pantngs at an Exhbton EE368 Group 17 Project Report Mthun Kamat Stanford Unversty mkamat at stanford dot edu Abstract An algorthm s developed and mplemented to recognze pantngs on dsplay at the Cantor

More information

Feature Reduction and Selection

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

More information

Modular PCA Face Recognition Based on Weighted Average

Modular PCA Face Recognition Based on Weighted Average odern Appled Scence odular PCA Face Recognton Based on Weghted Average Chengmao Han (Correspondng author) Department of athematcs, Lny Normal Unversty Lny 76005, Chna E-mal: hanchengmao@163.com Abstract

More information

Problem Set 3 Solutions

Problem Set 3 Solutions Introducton to Algorthms October 4, 2002 Massachusetts Insttute of Technology 6046J/18410J Professors Erk Demane and Shaf Goldwasser Handout 14 Problem Set 3 Solutons (Exercses were not to be turned n,

More information

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

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

More information

UB at GeoCLEF Department of Geography Abstract

UB at GeoCLEF Department of Geography   Abstract UB at GeoCLEF 2006 Mguel E. Ruz (1), Stuart Shapro (2), June Abbas (1), Slva B. Southwck (1) and Davd Mark (3) State Unversty of New York at Buffalo (1) Department of Lbrary and Informaton Studes (2) Department

More information

Discriminative Dictionary Learning with Pairwise Constraints

Discriminative 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 information

Object Contour Tracking Using Multi-feature Fusion based Particle Filter

Object Contour Tracking Using Multi-feature Fusion based Particle Filter Object Contour Tracng Usng Mult-feature Fuson based Partcle Flter Xaofeng Lu 1,3, L Song 1,2, Songyu Yu 1, Nam Lng 2 Insttute of Image Communcaton and Informaton Processng 1 Shangha Jao Tong Unversty,

More information

Face Recognition by Fusing Binary Edge Feature and Second-order Mutual Information

Face Recognition by Fusing Binary Edge Feature and Second-order Mutual Information Face Recognton by Fusng Bnary Edge Feature and Second-order Mutual Informaton Jatao Song, Bejng Chen, We Wang, Xaobo Ren School of Electronc and Informaton Engneerng, Nngbo Unversty of Technology Nngbo,

More information

Ecient Computation of the Most Probable Motion from Fuzzy. Moshe Ben-Ezra Shmuel Peleg Michael Werman. The Hebrew University of Jerusalem

Ecient Computation of the Most Probable Motion from Fuzzy. Moshe Ben-Ezra Shmuel Peleg Michael Werman. The Hebrew University of Jerusalem Ecent Computaton of the Most Probable Moton from Fuzzy Correspondences Moshe Ben-Ezra Shmuel Peleg Mchael Werman Insttute of Computer Scence The Hebrew Unversty of Jerusalem 91904 Jerusalem, Israel Emal:

More information

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation

An Iterative Solution Approach to Process Plant Layout using Mixed Integer Optimisation 17 th European Symposum on Computer Aded Process Engneerng ESCAPE17 V. Plesu and P.S. Agach (Edtors) 2007 Elsever B.V. All rghts reserved. 1 An Iteratve Soluton Approach to Process Plant Layout usng Mxed

More information

Multiple Frame Motion Inference Using Belief Propagation

Multiple Frame Motion Inference Using Belief Propagation Multple Frame Moton Inference Usng Belef Propagaton Jang Gao Janbo Sh The Robotcs Insttute Department of Computer and Informaton Scence Carnege Mellon Unversty Unversty of Pennsylvana Pttsburgh, PA 53

More information

Competitive Sparse Representation Classification for Face Recognition

Competitive Sparse Representation Classification for Face Recognition Vol. 6, No. 8, 05 Compettve Sparse Representaton Classfcaton for Face Recognton Yng Lu Chongqng Key Laboratory of Computatonal Intellgence Chongqng Unversty of Posts and elecommuncatons Chongqng, Chna

More information

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

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

More information

Enhanced Face Detection Technique Based on Color Correction Approach and SMQT Features

Enhanced Face Detection Technique Based on Color Correction Approach and SMQT Features Journal of Software Engneerng and Applcatons, 2013, 6, 519-525 http://dx.do.org/10.4236/jsea.2013.610062 Publshed Onlne October 2013 (http://www.scrp.org/journal/jsea) 519 Enhanced Face Detecton Technque

More information

A Unified Framework for Semantics and Feature Based Relevance Feedback in Image Retrieval Systems

A 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 information

Robust Mean Shift Tracking with Corrected Background-Weighted Histogram

Robust Mean Shift Tracking with Corrected Background-Weighted Histogram Robust Mean Shft Trackng wth Corrected Background-Weghted Hstogram Jfeng Nng, Le Zhang, Davd Zhang and Chengke Wu Abstract: The background-weghted hstogram (BWH) algorthm proposed n [] attempts to reduce

More information

Virtual Machine Migration based on Trust Measurement of Computer Node

Virtual 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 information

Histogram of Template for Pedestrian Detection

Histogram of Template for Pedestrian Detection PAPER IEICE TRANS. FUNDAMENTALS/COMMUN./ELECTRON./INF. & SYST., VOL. E85-A/B/C/D, No. xx JANUARY 20xx Hstogram of Template for Pedestran Detecton Shaopeng Tang, Non Member, Satosh Goto Fellow Summary In

More information

Automatic Generation of Caricatures with Multiple Expressions Using Transformative Approach

Automatic Generation of Caricatures with Multiple Expressions Using Transformative Approach Automatc Generaton of Carcatures wth Multple Expressons Usng Transformatve Approach Wen-Hung Lao and Chen-An La Department of Computer Scence, Natonal Chengch Unversty, Tape, Tawan {whlao,g9202}@cs.nccu.edu.tw

More information

Joint Example-based Depth Map Super-Resolution

Joint Example-based Depth Map Super-Resolution Jont Example-based Depth Map Super-Resoluton Yanje L 1, Tanfan Xue,3, Lfeng Sun 1, Janzhuang Lu,3,4 1 Informaton Scence and Technology Department, Tsnghua Unversty, Bejng, Chna Department of Informaton

More information

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

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

More information

Computer Animation and Visualisation. Lecture 4. Rigging / Skinning

Computer Animation and Visualisation. Lecture 4. Rigging / Skinning Computer Anmaton and Vsualsaton Lecture 4. Rggng / Sknnng Taku Komura Overvew Sknnng / Rggng Background knowledge Lnear Blendng How to decde weghts? Example-based Method Anatomcal models Sknnng Assume

More information

The Codesign Challenge

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

More information

Unsupervised Learning

Unsupervised Learning Pattern Recognton Lecture 8 Outlne Introducton Unsupervsed Learnng Parametrc VS Non-Parametrc Approach Mxture of Denstes Maxmum-Lkelhood Estmates Clusterng Prof. Danel Yeung School of Computer Scence and

More information

Positive Semi-definite Programming Localization in Wireless Sensor Networks

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

More information

MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS XUNYU PAN

MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS XUNYU PAN MOTION PANORAMA CONSTRUCTION FROM STREAMING VIDEO FOR POWER- CONSTRAINED MOBILE MULTIMEDIA ENVIRONMENTS by XUNYU PAN (Under the Drecton of Suchendra M. Bhandarkar) ABSTRACT In modern tmes, more and more

More information

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices Internatonal Mathematcal Forum, Vol 7, 2012, no 52, 2549-2554 An Applcaton of the Dulmage-Mendelsohn Decomposton to Sparse Null Space Bases of Full Row Rank Matrces Mostafa Khorramzadeh Department of Mathematcal

More information

Fingerprint matching based on weighting method and SVM

Fingerprint matching based on weighting method and SVM Fngerprnt matchng based on weghtng method and SVM Ja Ja, Lanhong Ca, Pnyan Lu, Xuhu Lu Key Laboratory of Pervasve Computng (Tsnghua Unversty), Mnstry of Educaton Bejng 100084, P.R.Chna {jaja}@mals.tsnghua.edu.cn

More information

Load-Balanced Anycast Routing

Load-Balanced Anycast Routing Load-Balanced Anycast Routng Chng-Yu Ln, Jung-Hua Lo, and Sy-Yen Kuo Department of Electrcal Engneerng atonal Tawan Unversty, Tape, Tawan sykuo@cc.ee.ntu.edu.tw Abstract For fault-tolerance and load-balance

More information

Appearance-based Statistical Methods for Face Recognition

Appearance-based Statistical Methods for Face Recognition 47th Internatonal Symposum ELMAR-2005, 08-10 June 2005, Zadar, Croata Appearance-based Statstcal Methods for Face Recognton Kresmr Delac 1, Mslav Grgc 2, Panos Latss 3 1 Croatan elecom, Savsa 32, Zagreb,

More information

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15 CS434a/541a: Pattern Recognton Prof. Olga Veksler Lecture 15 Today New Topc: Unsupervsed Learnng Supervsed vs. unsupervsed learnng Unsupervsed learnng Net Tme: parametrc unsupervsed learnng Today: nonparametrc

More information

Efficient Video Coding with R-D Constrained Quadtree Segmentation

Efficient 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 information

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET

BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET 1 BOOSTING CLASSIFICATION ACCURACY WITH SAMPLES CHOSEN FROM A VALIDATION SET TZU-CHENG CHUANG School of Electrcal and Computer Engneerng, Purdue Unversty, West Lafayette, Indana 47907 SAUL B. GELFAND School

More information

PERFORMANCE EVALUATION FOR SCENE MATCHING ALGORITHMS BY SVM

PERFORMANCE EVALUATION FOR SCENE MATCHING ALGORITHMS BY SVM PERFORMACE EVALUAIO FOR SCEE MACHIG ALGORIHMS BY SVM Zhaohu Yang a, b, *, Yngyng Chen a, Shaomng Zhang a a he Research Center of Remote Sensng and Geomatc, ongj Unversty, Shangha 200092, Chna - yzhac@63.com

More information