Using the Visual Words based on Affine-SIFT Descriptors for Face Recognition

Size: px
Start display at page:

Download "Using the Visual Words based on Affine-SIFT Descriptors for Face Recognition"

Transcription

1 Usng the Vsual Words based on Affne-SIFT Descrptors for Face Recognton Yu-Shan Wu, Heng-Sung Lu, Gwo-Hwa Ju, Tng-We Lee, Yen-Ln Chu Busness Customer Solutons Lab., Chunghwa Telecommuncaton Laboratores 2, Lane 55, Mn-Tsu Road Sec.5 Yang-Me, Taoyuan, Tawan 3260, R.O.C. {yushanwu, lhs306, jgh, fnas, Abstract Vdeo-based face recognton has drawn a lot of attenton n recent years. On the other hand, Bag-of-vsual Words (BoWs) representaton has been successfully appled n mage retreval and object recognton recently. In ths paper, a vdeo-based face recognton approach whch uses vsual words s proposed. In classc vsual words, Scale Invarant Feature Transform (SIFT) descrptors of an mage are frstly extracted on nterest ponts detected by dfference of Gaussan (DoG), then k-means-based vsual vocabulary generaton s appled to replace these descrptors wth the ndexes of the closet vsual words. However, n facal mages, SIFT descrptors are not good enough due to facal pose dstorton, facal expresson and lghtng condton varaton. In ths paper, we use Affne-SIFT (ASIFT) descrptors as facal mage representaton. Expermental results on UCSD/Honda Vdeo Database and VdTIMIT Vdeo Database suggest that vsual words based on Affne-SIFT descrptors can acheve lower error rates n face recognton task. Keywords-component; face recognton, SIFT, Affne-SIFT, vsual words. I. INTRODUCTION Vdeo-based face recognton has been a popular research topc because of ts scentfc challenges and wde use of vdeo montorng. However, there are many well-known approaches proposed to overcome the face recognton problems. Among them, Prncple Component Analyss (PCA) [] searches a subspace n the feature space that has the largest varance and then projects the feature vectors onto t. Lnear Dscrmnant Analyss (LDA) [2] attemps to obtan another subspace whch can maxmze the rato of betweenclass varance to the wthn-class varance. Localty Preservng Projecton (LPP) [3] also trys to fnd an optmal lnear transform that preserves local neghbor nformaton of data set n a certan sense. Recentl methods based on multple mages/vdeo sequences for face recognton are also proposed. Mutual Subspace Method (MSM) [4] consders the mnmum angle between nput and reference subspaces as measure of smlart and each subspace s formed by PCA operaton on mage sequence from each person. Constraned Mutual Subspace Method (CMSM) [5][6][7] s an mproved verson of MSM. The constructon of nput and reference subspaces are the same as n MSM, except the bases of these subspaces are further projected onto a constraned subspace and the projected bases are used to calculate the smlarty between two persons. All the above methods are concentratng on the projecton or transformaton of feature vector. The feature vector of a face mage used by these methods s usually smple gray value n row-major order. However, the feature selecton and extracton are also extremely mportant n face recognton. Recentl Bag-of-vsual Words (BoWs) [8][9] mage representaton has been utlzed n many computer vson problems and has demonstrated mpressve performance. In ths method, Scale-Invarant Feature Transform (SIFT) [0] features of an mage are frstly extracted on nterest ponts whch are usually detected by dfference of Gaussan (DoG) method. Then a clusterng method s used to convert these SIFT features to codeword hstogram. Fnally the degree of smlarty between two mages can thus be measured by the dstance between ther hstograms. Dfferent face mages of the same person obtaned by camera n varyng poston and angle undergo apparent deformatons. These deformatons can be allevated by affne transform of mage plane. The parameters of the affne transform can be descrbed scale, rotaton, translaton, camera lattude and longtude angles. Although SIFT method s nvarant to three out of the above fve parameters, t s not good enough. ASIFT method [] s proposed to cover all fve parameters and has been proved to be fully affne nvarant. Furthermore, the computaton complexty of the ASIFT method can be reduced to about twce of SIFT method by a two-resoluton scheme. In ths paper, we appled ASIFT Vsual Words as face mage representaton. Expermental results on UCSD/Honda [2] Vdeo Database and VdTIMIT [3] Vdeo Database show that ASIFT Vsual Words method s superor to other classcal methods. Ths paper s organzed as follows. In Secton II, we ntroduce three representatons for face mage, SIFT Method, ASIFT method and the proposed method. In Secton III, expermental results based on famous UCSD/Honda Vdeo Database and VdTIMIT Vdeo Database are depcted. Fnall the dscusson and concluson are presented n secton IV. II. FACE RECOGNITION APPROACHES In ths secton, we ntroduce two mage representatons mentoned prevously n Secton I and the proposed method.

2 In secton 2. and 2.2, SIFT method and ASIFT method for face mage representaton are ntroduced respectvely. In secton 2.3, the proposed face recognton method s derved. Fnall the performance evaluaton of face recognton n vdeo sequences s ntroduced n secton Scale Invarant Feature Transform(SIFT) SIFT method compares two mages by a rotaton, a translaton and a scale change to decde whether one mage can be deduced from the other mage. To acheve scale nvarance, SIFT smulates the zoom n scale space. Ths can be accomplshed by searchng for stable ponts across all possble scales and these stable ponts can be thought to be nvarant to scale change. The scale space of an mage s formed by the convoluton of ths mage wth a varablescale Gaussan G ( σ ) at several scales, where σ s the scale parameter. The convoluton result L ( σ ) can be defned as: L( σ ) = G( σ ) I( y) () Where * means the convoluton operaton at coordnates, and ( x, y) G( σ ) e 2 2πσ 2 2 ( x + y ) / 2 2 σ = (2) In order to detect stable keyponts n scale space effcentl the method proposed by Lowe [0] s used, whch uses the dfference-of-gaussan functon convolved wth the mage. The dfference of two nearby scales separated by a constant scale factor c can be computed as: D( σ ) = ( G( cσ ) G( σ ))* I( y) = L( cσ ) L( σ ) In any case for scale space feature descrpton, the smoothed mages L at every scale need to be computed. Therefore, n ths method D can be computed by smple mage subtracton. In order to detect the extrema relabl there has an mportant ssue on how to determne the frequency of samplng n scale and spatal domans. Here we take the settngs made by Lowe [0], 3 scales per octave and the standard devaton σ of Gaussan G s set to be 0.5. By takng apart all samplng ssues and by applyng several thresholds to elmnate unrelable features, the SIFT method computes scale-space extrema ( x, y, σ ) of the spatal Laplacan L ( σ ) and samples for each of these extrema a square mage patch centered at x, y ), whch ( has domnant gradents over ts neghbors. Because the resultng mage patches at scale σ are searched basng on gradent drecton, t s nvarant to llumnaton changes. Furthermore, only local hstograms of the drecton of the gradent are kept, the SIFT descrptor s nvarant to translaton and rotaton. 2.2 Affne-SIFT(ASIFT) The dea of combnng smulatng all zooms out of the query mage and normalzng rotaton and translaton s the (3) man ngredent of SIFT method. Based on ths dea, ASIFT method smulates the two camera axs parameters, the longtude angle and the lattude angle (whch s equvalent to tlt), and then apples SIFT method to smulate scale (zoom out) and to normalze translaton and rotaton. Smlar to SIFT method, the samplng frequency needs to be consdered because smulatng the whole affne space s not prohbtve and mpractcal. Furthermore, a tworesoluton scheme for comparng the smlarty between two mages needs to be used to reduce the ASIFT complexty ASIFT algorthm Step: Smulates all possble affne dstortons of the query mage, where the dstortons are caused by the change of camera optcal axs orentaton from a frontal vew. The degree of dstorton s depended on two parameters, the longtude angle φ and the lattude angle θ. For longtude angle φ, the query mage undergoes rotatons. For lattude angle θ, the query mage undergoes subsamples wth parameter t = cosθ, whch means the convoluton by a Gaussan wth standard devaton k t 2. The constant value k = 0.8 s settled by Lowe [0]. Step2: Snce the effcency of computaton needed to be taken nto account, the samplng steps are performed on a fnte number of lattude angles and longtude angles. Step3: All smulated mages from the query mage are compared by a smlarty matchng method (SIFT) Acceleraton wth a two-resoluton scheme for ASIFT The two-resoluton scheme s used to accelerate the process of computng the smlarty between two mages. The man dea of ths scheme s frstly selectng the affne transforms that yelds well matches at low-resoluton. Then t smulates mages from the query and the searched mages both at these selected affne transforms and at orgnalresoluton. Fnall computes the smlarty between these smulated mages. The steps of two-resoluton scheme are summarzed as follows: Step: Computes the low-resoluton mages of the query mage u and the searched mage v by usng a Gaussan Flter and a downsamplng operator. The resultng low-resoluton mages can be defned as: u' = PF GFu and v' = PF GFv (4) where u ' and v ' are the low-resoluton mages of u and v, respectvely. G F and P F are the Gaussan Flter and downsamplng operator, respectvely. And the subndex F represents the sze factor of operator. Step2: Apples ASIFT method to u ' and v '.

3 Fg. Matchng ablty comparson between SIFT and ASIFT method. Step3: Selects M affne transforms that yeldng well matches between u and v. Step4: Apples ASIFT method on u and v at the M affne transforms selected by step3. And chooses the best match among these M transforms as the smlarty between u and v. Fg. shows some face examples to compare the matchng ablty between SIFT and ASIFT method, n whch left two columns show the matchng results for SIFT method and rght two columns show the matchng results for ASIFT method respectvely. From Fg. we can see that when the varaton of facal pose and angle of the same person s hgher, SIFT method could not fnd any match. And among all examples, the matchng ablty of ASIFT method s obvously superor to SIFT method. 2.3 The proposed method The face mage representaton we adopted n ths paper s ASIFT Vsual Words. In ths representaton, vsual vocabulary must frstly be generated. Vsual vocabulary s generated by usng herarchcal K-means method to cluster a large number of ASIFT descrptors. The reason we adopted herarchcal K-means method here s by consderng both the clusterng tme and the clusterng effcency. When the clusterng process s convergent, the centers of all clusters are formng the vsual vocabulary. Now the ASIFT descrptors of every face mage can be converted to a hstogram form by usng vsual vocabulary. Suppose there are z centers (say code words) { C, C2,..., C z } n vsual vocabulary and there are r ASIFT descrptors { A, A2,..., A r } n a face mage. For each descrptor j r, we A j, calculate the Eucldan Dstances between A j and all the centers C, z. Chooses the center whch has mnmum dstance and records the ndex of ths center n R( A j ), j r. The vsual words representaton of ths mage s defned as: r H ( ) = E ( j), z, r j = where E ( j) s as follows:, f R( Aj ) ==. E ( j) { 0, otherwse. ( (5) = (6) And H ) s a hstogram of length z and t s also the vsual words representaton of ths face. The dstance between two vsual words representatons from two faces can be evaluated by Bhattacharyya dstance [4]. 2.4 Performance Evaluaton of Face Recognton In Vdeo Sequences There are many schemes n face classfcaton of vdeo sequences, such as probablstc majorty votng and Bayes maxmum a posteror scheme proposed n [5]. In both schemes, the smlarty between a test mage and a vdeo sequences s computed by consderng the smlartes between ths test mage and all mages n ths vdeo sequences. Ths s not approprate snce two face mages of a person from two dfferent facal poses may ntroduce lower smlarty. And ths wll lower the overall smlarty between a test mage and a vdeo sequences from the same person. In ths paper, we defne the smlarty between a test mage w and a vdeo sequences S as: Sm( w, S) = max Sm( w, s ), s S. (7) Where s s a face mage n the Vdeo Sequence S. In ths defnton, among all the smlartes between a test mage and all face mages n a vdeo sequences, only the maxmal smlarty s used. III. EXPERIMENTAL RESULTS In ths secton, we use the popular UCSD/Honda vdeo database and VdTIMIT vdeo database to evaluate the performance of face recognton. In UCSD/Honda vdeo database, there are 59 vdeo sequences of 20 dfferent people. There are about frames n each vdeo, ncludng large pose and expresson varatons wth sgnfcantly complex out-of-plane (3-D) head rotatons. These 59 vdeo sequences are further dvded nto a tranng subset of 20 vdeos and a testng subset of 39 vdeos. Among all members n ths database, only one person dd not take any testng vdeo.

4 TABLE I EXPERIMENTAL RESULTS ON UCSD/HONDA DATABASE Method Recognton Rate LBP 76.87% LGBP 74.85% Fg. 2 Sample face mages extracted from UCSD/Honda Vdeo Database. MBLBP 75.54% SIFT Vsual Words 72.95% ASIFT Vsual Words 87.36% TABLE II EXPERIMENTAL RESULTS ON VIDTIMIT DATABASE Method Recognton Rate Fg. 3 Sample face mages extracted from VdTIMIT Vdeo Database. VdTIMIT vdeo database contans 43 dfferent people and each person has 3 vdeo sequences. There are about frames n each vdeo sequences. The frst 3 sequences of each person were taken under 4 regular head movements (left, rght, up and down) and the last 0 sequences were taken under speakng short sentences. In our experment, we use the frst sequence as tranng vdeo and use the second and the thrd sequences as testng vdeos. For all vdeo sequences, Vola-Jones face detector [6] was frstly appled to detect face n each frame. Then we would manually delete frames whch the detected poston of face s ncorrect. Fg. 2 and Fg. 3 show some correctly detected face samples on these two corpora. All detected faces are preprocessed by llumnaton compensaton [7]. In our experment, the frst 25 frames and the frst 00 frames respectvely from every subject s tranng and testng face sequences are used for performance evaluaton. And the numbers of vsual phrases we used n UCSD/Honda database and VdTIMIT database are 9000 and 6384, respectvely. The proposed ASIFT Vsual Words method s compared aganst other four classcal approaches, they are LBP[8], MBLBP[9], Local Gabor Bnary Pattern[20], SIFT Vsual Words. The recognton rates on UCSD/Honda vdeo database and on VdTIMIT vdeo database are summarzed n Tables I and II, respectvely. From the Table I we can see that the proposed method s superor to other classcal approaches. From Table II, the recognton rate of our proposed method s also superor to other classcal approaches, but the mprovement of performance s not obvous. The reason s probably that the head movements are regular n ths database and the facal poses are smlar n tranng and testng vdeos. Furthermore, there s no facal expresson change n the frst 3 vdeo sequences used n our experment. LBP 90.25% LGBP 77.0% MBLBP 85.7% SIFT Vsual Words 88.8% ASIFT Vsual Words 92.0% IV. CONCLUSIONS In ths paper, we proposed a face recognton method whch uses ASIFT vsual words as mage representaton. We also proposed a face recognton scheme n vdeo sequences to further mprove face recognton performance. REFERENCES [] Turk. M., Pentland. A., Egenfaces for recognton, Journal of Cogntve Neuro-scence 3, pp. 7-86, 99. [2] Etemad. K., Chellappa. R., Dscrmnant analyss for recognton of human face mages, Journal of the Optcal Socety of Amerca 4, pp , 997. [3] X.F. He and P. Nyog, Localty preservng projectons, Proc. Of NIPS 03, [4] O. Yamaquch, K. Fuku and K.maeda, Face recognton usng temporal mage sequence, Pro, Int l Conf. on Automatc Face and Gesture Recognton, pp , 998. [5] K. Fuku, and O. Yamaquch, Face recognton usng multvewpont patterns for robot vson, Symp. Of Robotcs Research, [6] Masash Nshyama, Osamu Yamaguch, and Kazuhro Fuku, Face recognton wth the multple constraned mutual subspace method, Audo- and Vdeo-Based Bometrc Person Authentcaton, 5th Internatonal Conference, [7] Kazuhro Fukul, Bjorn Stenger, and Osamu Yamaguch, A framework for 3D object recognton usng the kernel constraned

5 mutual subspace method, Asan Conference on Computer Vson(ACCV), [8] S. Lazebnk, C. Schmd, and J. Ponce, Beyond bags of features: Spatal pyramd matchng for recognzng natural scene categores, n Proc. CVPR, pp , [9] F. Perronnn and C. Dance, Fsher kernels on vsual vocabulary for mage categorzaton, n Proc. CVPR, pp. -8, [0] D. Lowe, Dstnctve mage features from scale-nvarant key ponts, Int. J. Comput. Vs., 60, pp. 9-0, [] J. M. Morel and G. Yu, ASIFT: A new framework for fully affne nvarant mage comparson, SIAM Journal on Image Scence, vol. 2 ssue 2, [2] K. C. Lee, J. Ho, M.H. Yang and D. Kregman, Vsual trackng and recognton usng probablstc appearance manfolds, Computer Vson and Image Understandng, vol. 99(3), pp , [3] C. Sanderson and B. C. Lovell, Mult-regon probablstc hstograms for robust and scalable dentty nference, Lecture Notes n Computer Scence(LNCS), vol. 5558, pp , [4] Kalath, T., The dvergence and Bhattacharyya dstance measures n sgnal selecton, IEEE Transactons on Communcaton Technology 5(): DOI: 0. 09/TCOM , 967. [5] See, J. and Fauz, M.F.A., Neghborhood dscrmnatve manfold projecton for face recognton n vdeo, Internatonal Conference on Pattern Analyss and Intellgent Robotcs(ICPAIR), vol., pp. 3-8, 20. [6] P. Vola and M. Jones, Robust real-tme face detecton, Int. Journal of Computer Vson, vol. 57(2), pp , [7] Ngoc-Son Vu and Capler, A., Illumnaton-robust face recognton usng retna modelng, IEEE Internatonal Conference on Image Processng(ICIP), pp , [8] Ahonen, T., Petkanen, M., Face recognton wth local bnary patterns. In: Proceedngs of the European Conference on Computer Vson, Prague, Czech, pp , [9] Shengca Lao, Xangxn Zhu, Zhen Le, Lun Zhang, and Stan Z. L, Learnng mult-scale block local bnary patterns for face recognton, Lecture Notes n Computer Scence(LNCS), vol. 4642, pp , [20] Xnghua Sun, Hongxa Xu, Chunxa Zhao and Jngyu Yang, Facal expresson recognton based on hstogram sequence of local gabor bnary patterns, IEEE Conference on Cybernetcs and Intellgent Systems, pp , 2008.

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

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

Scale Selective Extended Local Binary Pattern For Texture Classification

Scale Selective Extended Local Binary Pattern For Texture Classification Scale Selectve Extended Local Bnary Pattern For Texture Classfcaton Yutng Hu, Zhlng Long, and Ghassan AlRegb Multmeda & Sensors Lab (MSL) Georga Insttute of Technology 03/09/017 Outlne Texture Representaton

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

Image Alignment CSC 767

Image Alignment CSC 767 Image Algnment CSC 767 Image algnment Image from http://graphcs.cs.cmu.edu/courses/15-463/2010_fall/ Image algnment: Applcatons Panorama sttchng Image algnment: Applcatons Recognton of object nstances

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

Improved SIFT-Features Matching for Object Recognition

Improved SIFT-Features Matching for Object Recognition Improved SIFT-Features Matchng for Obect Recognton Fara Alhwarn, Chao Wang, Danela Rstć-Durrant, Axel Gräser Insttute of Automaton, Unversty of Bremen, FB / NW Otto-Hahn-Allee D-8359 Bremen Emals: {alhwarn,wang,rstc,ag}@at.un-bremen.de

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

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

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

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

Combination of Local Multiple Patterns and Exponential Discriminant Analysis for Facial Recognition

Combination of Local Multiple Patterns and Exponential Discriminant Analysis for Facial Recognition Sensors & ransducers 203 by IFSA http://.sensorsportal.com Combnaton of Local Multple Patterns and Exponental Dscrmnant Analyss for Facal Recognton, 2 Lfang Zhou, 2 Bn Fang, 3 Wesheng L, 3 Ldou Wang College

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

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

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

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

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

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

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

Palmprint Feature Extraction Using 2-D Gabor Filters

Palmprint Feature Extraction Using 2-D Gabor Filters Palmprnt Feature Extracton Usng 2-D Gabor Flters Wa Kn Kong Davd Zhang and Wenxn L Bometrcs Research Centre Department of Computng The Hong Kong Polytechnc Unversty Kowloon Hong Kong Correspondng author:

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

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

Combination of Color and Local Patterns as a Feature Vector for CBIR

Combination of Color and Local Patterns as a Feature Vector for CBIR Internatonal Journal of Computer Applcatons (975 8887) Volume 99 No.1, August 214 Combnaton of Color and Local Patterns as a Feature Vector for CBIR L.Koteswara Rao Asst.Professor, Dept of ECE Faculty

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

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

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

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

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

Image Matching Algorithm based on Feature-point and DAISY Descriptor

Image Matching Algorithm based on Feature-point and DAISY Descriptor JOURNAL OF MULTIMEDIA, VOL. 9, NO. 6, JUNE 2014 829 Image Matchng Algorthm based on Feature-pont and DAISY Descrptor L L School of Busness, Schuan Agrcultural Unversty, Schuan Dujanyan 611830, Chna Abstract

More information

A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION

A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION ISSN: 0976-910(ONLINE) ICTACT JOURNAL ON IMAGE AND VIDEO PROCESSING, MAY 013, VOLUME: 03, ISSUE: 04 A COMBINED APPROACH USING TEXTURAL AND GEOMETRICAL FEATURES FOR FACE RECOGNITION A. Suruland 1, R. Reena

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

Gender Classification using Interlaced Derivative Patterns

Gender Classification using Interlaced Derivative Patterns Gender Classfcaton usng Interlaced Dervatve Patterns Author Shobernejad, Ameneh, Gao, Yongsheng Publshed 2 Conference Ttle Proceedngs of the 2th Internatonal Conference on Pattern Recognton (ICPR 2) DOI

More information

Face Recognition Based on SVM and 2DPCA

Face Recognition Based on SVM and 2DPCA Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty

More 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

Object Recognition Based on Photometric Alignment Using Random Sample Consensus

Object Recognition Based on Photometric Alignment Using Random Sample Consensus Vol. 44 No. SIG 9(CVIM 7) July 2003 3 attached shadow photometrc algnment RANSAC RANdom SAmple Consensus Yale Face Database B RANSAC Object Recognton Based on Photometrc Algnment Usng Random Sample Consensus

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

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

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

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity

Efficient Segmentation and Classification of Remote Sensing Image Using Local Self Similarity ISSN(Onlne): 2320-9801 ISSN (Prnt): 2320-9798 Internatonal Journal of Innovatve Research n Computer and Communcaton Engneerng (An ISO 3297: 2007 Certfed Organzaton) Vol.2, Specal Issue 1, March 2014 Proceedngs

More information

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm

Invariant Shape Object Recognition Using B-Spline, Cardinal Spline, and Genetic Algorithm Proceedngs of the 5th WSEAS Int. Conf. on Sgnal Processng, Robotcs and Automaton, Madrd, Span, February 5-7, 6 (pp4-45) Invarant Shape Obect Recognton Usng B-Splne, Cardnal Splne, and Genetc Algorthm PISIT

More information

WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING.

WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING. WIRELESS CAPSULE ENDOSCOPY IMAGE CLASSIFICATION BASED ON VECTOR SPARSE CODING Tao Ma 1, Yuexan Zou 1 *, Zhqang Xang 1, Le L 1 and Y L 1 ADSPLAB/ELIP, School of ECE, Pekng Unversty, Shenzhen 518055, Chna

More information

Classification of Face Images Based on Gender using Dimensionality Reduction Techniques and SVM

Classification of Face Images Based on Gender using Dimensionality Reduction Techniques and SVM Classfcaton of Face Images Based on Gender usng Dmensonalty Reducton Technques and SVM Fahm Mannan 260 266 294 School of Computer Scence McGll Unversty Abstract Ths report presents gender classfcaton based

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

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

Hierarchical Image Retrieval by Multi-Feature Fusion

Hierarchical Image Retrieval by Multi-Feature Fusion Preprnts (www.preprnts.org) NOT PEER-REVIEWED Posted: 26 Aprl 207 do:0.20944/preprnts20704.074.v Artcle Herarchcal Image Retreval by Mult- Fuson Xaojun Lu, Jaojuan Wang,Yngq Hou, Me Yang, Q Wang* and Xangde

More information

LOCAL FEATURE EXTRACTION AND MATCHING METHOD FOR REAL-TIME FACE RECOGNITION SYSTEM. Ho-Chul Shin, Hae Chul Choi and Seong-Dae Kim

LOCAL FEATURE EXTRACTION AND MATCHING METHOD FOR REAL-TIME FACE RECOGNITION SYSTEM. Ho-Chul Shin, Hae Chul Choi and Seong-Dae Kim LOCAL FEATURE EXTRACTIO AD MATCHIG METHOD FOR REAL-TIME FACE RECOGITIO SYSTEM Ho-Chul Shn, Hae Chul Cho and Seong-Dae Km Vsual Communcatons Lab., Department of EECS Korea Advanced Insttute of Scence and

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

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14

Computer Aided Drafting, Design and Manufacturing Volume 25, Number 2, June 2015, Page 14 Computer Aded Draftng, Desgn and Manufacturng Volume 5, Number, June 015, Page 14 CADDM Face Recognton Algorthm Fusng Monogenc Bnary Codng and Collaboratve Representaton FU Yu-xan, PENG Lang-yu College

More information

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION

A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION 1 THE PUBLISHING HOUSE PROCEEDINGS OF THE ROMANIAN ACADEMY, Seres A, OF THE ROMANIAN ACADEMY Volume 4, Number 2/2003, pp.000-000 A PATTERN RECOGNITION APPROACH TO IMAGE SEGMENTATION Tudor BARBU Insttute

More 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

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

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

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

Content-Based Bird Retrieval using Shape context, Color moments and Bag of Features

Content-Based Bird Retrieval using Shape context, Color moments and Bag of Features www.ijcsi.org 101 Content-Based Brd Retreval usng Shape context, Color moments and Features Bahr abdelkhalak 1 and hamd zouak 2 1 Faculty of Scences, Unversty Chouab Doukkal, Equpe: Modélsaton mathématque

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

IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH

IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH IMAGE MATCHING WITH SIFT FEATURES A PROBABILISTIC APPROACH Jyot Joglekar a, *, Shrsh S. Gedam b a CSRE, IIT Bombay, Doctoral Student, Mumba, Inda jyotj@tb.ac.n b Centre of Studes n Resources Engneerng,

More information

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval

Fuzzy C-Means Initialized by Fixed Threshold Clustering for Improving Image Retrieval Fuzzy -Means Intalzed by Fxed Threshold lusterng for Improvng Image Retreval NAWARA HANSIRI, SIRIPORN SUPRATID,HOM KIMPAN 3 Faculty of Informaton Technology Rangst Unversty Muang-Ake, Paholyotn Road, Patumtan,

More information

Mercer Kernels for Object Recognition with Local Features

Mercer Kernels for Object Recognition with Local Features TR004-50, October 004, Department of Computer Scence, Dartmouth College Mercer Kernels for Object Recognton wth Local Features Swe Lyu Department of Computer Scence Dartmouth College Hanover NH 03755 A

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

A Deflected Grid-based Algorithm for Clustering Analysis

A Deflected Grid-based Algorithm for Clustering Analysis A Deflected Grd-based Algorthm for Clusterng Analyss NANCY P. LIN, CHUNG-I CHANG, HAO-EN CHUEH, HUNG-JEN CHEN, WEI-HUA HAO Department of Computer Scence and Informaton Engneerng Tamkang Unversty 5 Yng-chuan

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

Face Recognition Method Based on Within-class Clustering SVM

Face Recognition Method Based on Within-class Clustering SVM Face Recognton Method Based on Wthn-class Clusterng SVM Yan Wu, Xao Yao and Yng Xa Department of Computer Scence and Engneerng Tong Unversty Shangha, Chna Abstract - A face recognton method based on Wthn-class

More information

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

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

More information

Large-scale Web Video Event Classification by use of Fisher Vectors

Large-scale Web Video Event Classification by use of Fisher Vectors Large-scale Web Vdeo Event Classfcaton by use of Fsher Vectors Chen Sun and Ram Nevata Unversty of Southern Calforna, Insttute for Robotcs and Intellgent Systems Los Angeles, CA 90089, USA {chensun nevata}@usc.org

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

LECTURE : MANIFOLD LEARNING

LECTURE : MANIFOLD LEARNING LECTURE : MANIFOLD LEARNING Rta Osadchy Some sldes are due to L.Saul, V. C. Raykar, N. Verma Topcs PCA MDS IsoMap LLE EgenMaps Done! Dmensonalty Reducton Data representaton Inputs are real-valued vectors

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

Discriminative classifiers for object classification. Last time

Discriminative classifiers for object classification. Last time Dscrmnatve classfers for object classfcaton Thursday, Nov 12 Krsten Grauman UT Austn Last tme Supervsed classfcaton Loss and rsk, kbayes rule Skn color detecton example Sldng ndo detecton Classfers, boostng

More information

Robust Kernel Representation with Statistical Local Features. for Face Recognition

Robust Kernel Representation with Statistical Local Features. for Face Recognition Robust Kernel Representaton wth Statstcal Local Features for Face Recognton Meng Yang, Student Member, IEEE, Le Zhang 1, Member, IEEE Smon C. K. Shu, Member, IEEE, and Davd Zhang, Fellow, IEEE Dept. of

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

A Probabilistic Approach to Detect Urban Regions from Remotely Sensed Images Based on Combination of Local Features

A Probabilistic Approach to Detect Urban Regions from Remotely Sensed Images Based on Combination of Local Features A Probablstc Approach to Detect Urban Regons from Remotely Sensed Images Based on Combnaton of Local Features Berl Sırmaçek German Aerospace Center (DLR) Remote Sensng Technology Insttute Weßlng, 82234,

More information

Feature-based image registration using the shape context

Feature-based image registration using the shape context Feature-based mage regstraton usng the shape context LEI HUANG *, ZHEN LI Center for Earth Observaton and Dgtal Earth, Chnese Academy of Scences, Bejng, 100012, Chna Graduate Unversty of Chnese Academy

More information

Feature-Area Optimization: A Novel SAR Image Registration Method

Feature-Area Optimization: A Novel SAR Image Registration Method Feature-Area Optmzaton: A Novel SAR Image Regstraton Method Fuqang Lu, Fukun B, Lang Chen, Hao Sh and We Lu Abstract Ths letter proposes a synthetc aperture radar (SAR) mage regstraton method named Feature-Area

More information

Fast Feature Value Searching for Face Detection

Fast Feature Value Searching for Face Detection Vol., No. 2 Computer and Informaton Scence Fast Feature Value Searchng for Face Detecton Yunyang Yan Department of Computer Engneerng Huayn Insttute of Technology Hua an 22300, Chna E-mal: areyyyke@63.com

More information

An Efficient Illumination Normalization Method with Fuzzy LDA Feature Extractor for Face Recognition

An Efficient Illumination Normalization Method with Fuzzy LDA Feature Extractor for Face Recognition www.mer.com Vol.2, Issue.1, pp-060-065 ISS: 2249-6645 An Effcent Illumnaton ormalzaton Meod w Fuzzy LDA Feature Extractor for Face Recognton Behzad Bozorgtabar 1, Hamed Azam 2 (Department of Electrcal

More information

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide

Lobachevsky State University of Nizhni Novgorod. Polyhedron. Quick Start Guide Lobachevsky State Unversty of Nzhn Novgorod Polyhedron Quck Start Gude Nzhn Novgorod 2016 Contents Specfcaton of Polyhedron software... 3 Theoretcal background... 4 1. Interface of Polyhedron... 6 1.1.

More information

Integrated Expression-Invariant Face Recognition with Constrained Optical Flow

Integrated Expression-Invariant Face Recognition with Constrained Optical Flow 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

More information

A fast algorithm for color image segmentation

A fast algorithm for color image segmentation Unersty of Wollongong Research Onlne Faculty of Informatcs - Papers (Arche) Faculty of Engneerng and Informaton Scences 006 A fast algorthm for color mage segmentaton L. Dong Unersty of Wollongong, lju@uow.edu.au

More information

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

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

More information

Extraction of Texture Information from Fuzzy Run Length Matrix

Extraction of Texture Information from Fuzzy Run Length Matrix Internatonal Journal of Computer Applcatons (0975 8887) Volume 55 o.1, October 01 Extracton of Texture Informaton from Fuzzy Run Length Matrx Y. Venkateswarlu Head Dept. of CSE&IT Chatanya Insttuteof Engg.

More information

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces

Range images. Range image registration. Examples of sampling patterns. Range images and range surfaces Range mages For many structured lght scanners, the range data forms a hghly regular pattern known as a range mage. he samplng pattern s determned by the specfc scanner. Range mage regstraton 1 Examples

More information

Face Detection with Deep Learning

Face Detection with Deep Learning Face Detecton wth Deep Learnng Yu Shen Yus122@ucsd.edu A13227146 Kuan-We Chen kuc010@ucsd.edu A99045121 Yzhou Hao y3hao@ucsd.edu A98017773 Mn Hsuan Wu mhwu@ucsd.edu A92424998 Abstract The project here

More information

Mining Image Features in an Automatic Two- Dimensional Shape Recognition System

Mining Image Features in an Automatic Two- Dimensional Shape Recognition System Internatonal Journal of Appled Mathematcs and Computer Scences Volume 2 Number 1 Mnng Image Features n an Automatc Two- Dmensonal Shape Recognton System R. A. Salam, M.A. Rodrgues Abstract The number of

More information

Facial Expression Recognition Based on Local Binary Patterns and Local Fisher Discriminant Analysis

Facial Expression Recognition Based on Local Binary Patterns and Local Fisher Discriminant Analysis WSEAS RANSACIONS on SIGNAL PROCESSING Shqng Zhang, Xaomng Zhao, Bcheng Le Facal Expresson Recognton Based on Local Bnary Patterns and Local Fsher Dscrmnant Analyss SHIQING ZHANG, XIAOMING ZHAO, BICHENG

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

Augmented Distinctive Features for Efficient Image Matching

Augmented Distinctive Features for Efficient Image Matching Augmented Dstnctve Features for Effcent Image Matchng Quan Wang, We Guan and Suya You CGIT/IMSC USC Los Angeles, CA 90089 quanwang@usc.edu, wguan@usc.edu and suyay@graphcs.usc.edu Abstract Fndng correspondng

More information

Semarang, Indonesia. Sepuluh Nopember Institute of Technology, Surabaya, Indonesia

Semarang, Indonesia. Sepuluh Nopember Institute of Technology, Surabaya, Indonesia 3D Surfaces Reconstructon of Seafloor Images Usng Multvew Camera Based on Image Regstraton Pulung Nurtanto Andono 1,a, I Ketut Eddy Purnama 2,b, Mochamad Harad 2,c, Tach Watanabe 3,d, and Kuno Kondo 3,e

More information

Fusion of Deep Features and Weighted VLAD Vectors based on Multiple Features for Image Retrieval

Fusion of Deep Features and Weighted VLAD Vectors based on Multiple Features for Image Retrieval MATEC Web of Conferences, 0500 (07) DTS-07 DO: 005/matecconf/070500 Fuson of Deep Features and Weghted VLAD Vectors based on Multple Features for mage Retreval Yanhong Wang,, Ygang Cen,, Lequan Lang,*,

More information

Lecture 4: Principal components

Lecture 4: Principal components /3/6 Lecture 4: Prncpal components 3..6 Multvarate lnear regresson MLR s optmal for the estmaton data...but poor for handlng collnear data Covarance matrx s not nvertble (large condton number) Robustness

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 Novel Fingerprint Matching Method Combining Geometric and Texture Features

A Novel Fingerprint Matching Method Combining Geometric and Texture Features A Novel ngerprnt Matchng Method Combnng Geometrc and Texture eatures Me Xe, Chengpu Yu and Jn Q Unversty of Electronc Scence and Technology of Chna. Chengdu,P.R.Chna xeme@ee.uestc.edu.cn Post Code:6154

More information

Machine Learning: Algorithms and Applications

Machine Learning: Algorithms and Applications 14/05/1 Machne Learnng: Algorthms and Applcatons Florano Zn Free Unversty of Bozen-Bolzano Faculty of Computer Scence Academc Year 011-01 Lecture 10: 14 May 01 Unsupervsed Learnng cont Sldes courtesy of

More information

Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition

Manifold Regularized Slow Feature Analysis for Dynamic Texture Recognition 1 Manfold Regularzed Slow Feature Analyss for Dynamc Texture Recognton Je Mao, Xangmn Xu, Member, IEEE, Xaofen Xng, and Dacheng Tao, Fellow, IEEE arxv:1706.03015v1 [cs.cv] 9 Jun 2017 Abstract Dynamc textures

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

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

Palmprint Recognition Using Directional Representation and Compresses Sensing

Palmprint Recognition Using Directional Representation and Compresses Sensing Research Journal of Appled Scences, Engneerng and echnology 4(22): 4724-4728, 2012 ISSN: 2040-7467 Maxwell Scentfc Organzaton, 2012 Submtted: March 31, 2012 Accepted: Aprl 30, 2012 Publshed: November 15,

More information

3D vector computer graphics

3D vector computer graphics 3D vector computer graphcs Paolo Varagnolo: freelance engneer Padova Aprl 2016 Prvate Practce ----------------------------------- 1. Introducton Vector 3D model representaton n computer graphcs requres

More information

Structure from Motion

Structure from Motion Structure from Moton Structure from Moton For now, statc scene and movng camera Equvalentl, rgdl movng scene and statc camera Lmtng case of stereo wth man cameras Lmtng case of multvew camera calbraton

More information

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros.

Fitting & Matching. Lecture 4 Prof. Bregler. Slides from: S. Lazebnik, S. Seitz, M. Pollefeys, A. Effros. Fttng & Matchng Lecture 4 Prof. Bregler Sldes from: S. Lazebnk, S. Setz, M. Pollefeys, A. Effros. How do we buld panorama? We need to match (algn) mages Matchng wth Features Detect feature ponts n both

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