Object Recognition Based on Photometric Alignment Using Random Sample Consensus
|
|
- Kathleen Griffith
- 5 years ago
- Views:
Transcription
1 Vol. 44 No. SIG 9(CVIM 7) July attached shadow photometrc algnment RANSAC RANdom SAmple Consensus Yale Face Database B RANSAC Object Recognton Based on Photometrc Algnment Usng Random Sample Consensus Takahro Okabe and Yoch Sato Photometrc algnment s a technque that represents both dffuse reflecton components and attached shadows under an arbtrary pont lght source wth three bass mages. In ths paper, we propose a method based on photometrc algnment for object recognton under varyng llumnaton. In order to synthesze a test mage relably n the face of outlers such as specular reflecton components and shadows, our method utlzes RANSAC (RANdom SAmple Consensus) whch has been used successfully for estmatng the bass mages. To demonstrate the effectveness of the proposed method, we conducted experments by usng the Yale Face Database B and confrmed that RANSAC s effectve not only for estmaton of the bass mages but also for object recognton under varyng llumnaton. 1. attached shadow cast shadow 4 22),23) Lambert generatve methods Insttute of Industral Scence, The Unversty of Tokyo Lambert 3 attached shadow 0 attached shadow attached shadow 3 22),23) 2 3 attached shadow cast shadow 124
2 Vol. 44 No. SIG 9(CVIM 7) RANSAC photometrc stereo 26) SVDMD Sngular Value Decomposton wth Mssng Data 24) 8) SVDMD 7) 14) RANSAC 6) 11) 16) 11),16) RANSAC attached shadow Yale Face Database B 7) RANSAC RANSAC feature-based methods appearance-based methods 2 5) 3),15),18),21),25) Lambert Lambert 3 22),23) 3 attached shadow cast shadow 7),8) attached shadow Lambert convex cone llumnaton cone 3 4) attached shadow 7),8) attached shadow attached shadow 1 2) 3) 7) 8) 10) 12) lnear subspace method
3 126 July ) 7),8) 4 9 1),20) 9 10),12) 10),12) 1 segmented lnear subspace method 2) 3 attached shadow attached shadow attached shadow 3. attached shadow 3.1 Lambert x (D) x (D) = ρ n T s b T s, ( =1, 2,,n) (1) ρ n s x (D) b T n n 3 B x (D) = Bs (2) (2) n L = {x x = Bs, s R 3 } (3) llumnaton subspace 4) 3 3 e (j) (j =1, 2, 3) x (D) = c 1 e (1) + c 2 e (2) + c 3 e (3). (4) c j (j =1, 2, 3) 3 attached shadow 3.2 attached shadow attached shadow
4 Vol. 44 No. SIG 9(CVIM 7) RANSAC 127 Attached shadow (1) b T s < 0 attached shadow attached shadow x (D+AS) 0 x (D+AS) = max (Bs, 0). (5) max(z, 0) z 0 3 attached shadow ( 3 ) x (D+AS) = max c j e (j), 0. (6) j=1 attached shadow attached shadow 22),23) attached shadow cast shadow ),8),11),14),16),26) 4.1 attached shadow cast shadow 4 (4) 3 (6) attached shadow attached shadow Lambert 3 RANSAC attached shadow 4.2 RANSAC (1) 3 ĉ j (j =1, 2, 3) (2) (1) attached shadow ( 3 ) ˆx = max ĉ j e (j), 0, ( =1, 2,,n). e (j) j=1 (7) j
5 128 July 2003 { 1 ( x (test) ˆx <t : nler) ξ = 0 ( x (test) ˆx t : outler) (8) x (test) t Lambert 19) (3) nler n support = ξ (9) =1 (4) (1) (3) (1) (3) support (5) nler t attached shadow { 1 (ξ =1,t< ˆx < 1 t) w = (10) 0 (others) ( n C = w =1 x (test) 3 j=1 ĉ j e (j) ) 2 (11) ĉ j (j =1, 2, 3) (6) (2) (7) (5) (6) (5) (6) ξ, ( =1, 2,,n) (8) support support support 8bt RANSAC RANSAC 11) 2 3 attached shadow cast shadow attached shadow cast shadow 3 nler nler attached shadow nler (4) attached shadow support support (5) 5. Yale Face Database B 7) 13) ,850 2 θ 5 650
6 Vol. 44 No. SIG 9(CVIM 7) RANSAC 129 (a) (b) (c) Fg Cropped mages of ten ndvduals. (d) (e) Subset1 12 Subset2 25 Subset3 50 Subset4 77 Subset5 77 Fg. 4 4 A test mage and syntheszed mages. 2 Fg. 2 Example mages n each subset: varablty due to llumnaton. 3 Fg. 3 Bass mages attached shadow cast shadow SVDMD 8) 3 (8) t σ t IS 3 PA1 3 RANSAC PA2 4 RANSAC 4 PA2 (a) (b) (d) t (c) (e) cast shadow 3 1 t 4σ IS attached shadow PA1 PA σ 5.5σ 4 1% 5 2%
7 130 July (%) Table 1 Recognton error rates (%). Method Subset2 Subset3 Subset4 Subset5 IS PA PA IC: attached 7) PL 12) PL 10) Segm. LS 2) attached shadow RANSAC cast shadow 5 2 cast shadow ) ),12) 2) 3 6. attached shadow 3 RANSAC attached shadow RANSAC cast shadow cast shadow 7),8) cast shadow 17) cast shadow Yale Face Database B 7) C ) Basr, R. and Jacobs, D.: Lambertan reflectance and lnear subspaces, Proc. IEEE ICCV 2001, pp (2001). 2) Batur, A.U. and Hayes III, M.H.: Lnear subspaces for llumnaton robust face recognton, Proc. IEEE CVPR 2001, 2, pp (2001). 3) Belhumeur, P.N., Hespanha, J.P. and Kregman, D.J.: Egenfaces vs. fsherfaces: recognton usng class specfc lnear projecton, IEEE Trans. PAMI, Vol.19, No.7, pp (1997). 4) Belhumeur, P.N. and Kregman, D.J.: What s the set of mages of an object under all possble lghtng condtons?, Int l. J. Computer Vson, Vol.28, No.3, pp (1998). 5) Brunell, R. and Poggo, T.: Face recognton: features versus templates, IEEE Trans. PAMI, Vol.15, No.10, pp (1993). 6) Fschler, M.A. and Bolles, R.C.: Random sample consensus: a paradgm for model fttng wth applcatons to mage analyss and automated cartography, Comm. ACM, Vol.24, No.6, pp (1981). 7) Georghades, A.S., Belhumeur, P.N. and Kregman, D.J.: From few to many: llumnaton cone models for face recognton under varable lghtng and pose, IEEE Trans. PAMI, Vol.23, No.6, pp (2001). 8) Georghades, A.S., Kregman, D.J. and Belhumeur, P.N.: Illumnaton cones for recognton under varable lghtng: faces, Proc. IEEE CVPR 98, pp (1998). 9) Hallnan, P.W.: A low-dmensonal representaton of human faces for arbtrary lghtng condtons, Proc. IEEE CVPR 94, pp
8 Vol. 44 No. SIG 9(CVIM 7) RANSAC 131 (1994). 10) Ho, J., Lee, K.-C. and Kregman, D.J.: On reducng the complexty of llumnaton cones for face recognton, Proc. CVPR Workshop on Identfyng Objects Accross Varatons n Lghtng (2001). 11) MIRU II pp (2002). 12) Lee, K.-C., Ho, J. and Kregman, D.J.: Nne ponts of lght: acqurng subspaces for face recognton under varable lghtng, Proc. IEEE CVPR 2001, 1, pp (2001). 13) Moses, Y., Adn, Y. and Ullman, S.: Face recognton: the problem of compensatng for changes n llumnaton drecton, Proc. ECCV 94, pp (1994). 14) Mukagawa, Y., Myak, H., Mhash, S. and Shakunaga, T.: Photometrc mage-based renderng for mage generaton n arbtrary llumnaton, Proc. ICCV 2001, pp (2001). 15) Murase, H. and Nayar, S.K.: Vsual learnng and recognton of 3-D objects from appearance, Int l. J. Computer Vson, Vol.14, No.1, pp.5 24 (1995). 16) Nakashma, A., Mak, A. and Fuku, K.: Constructng llumnaton mage bass from object moton, Proc. ECCV 2002 (LNCS 2352), pp (2002). 17) CVIM , pp (2002). 18) MIRU II pp (2002). 19) Oren, M. and Nayar, S.K.: Generalzaton of the Lambertan model and mplcatons for machne vson, Int l. J. Computer Vson, Vol.14, No.3, pp (1995). 20) Ramamoorth, R. and Hanrahan, P.: On the relatonshp between radance and rradance: determnng the llumnaton from mages of a convex Lambertan object, J. Opt. Soc. Am. A, Vol.18, No.10, pp (2001). 21) Shakunaga, T. and Shgenar, K.: Decomposed egenface for face recognton under varous lghtng condtons, Proc. IEEE CVPR 2001, 1, pp (2001). 22) Shashua, A.: Geometry and photometry n 3D vsual recognton, Ph.D. Thess, MIT (1992). 23) Shashua, A.: On photometrc ssues n 3D vsual recognton from a sngle 2D mage, Int l. J. Computer Vson, Vol.21, No.1/2, pp (1997). 24) Shum, H.-Y., Ikeuch, K. and Reddy, R.: Prncpal component analyss wth mssng data and ts applcaton to polyhedral object modelng, IEEE Trans. PAMI, Vol.17, No.9, pp (1995). 25) Turk, M.A. and Pentland, A.P.: Face recognton usng egenfaces, Proc. IEEE CVPR 91, pp (1991). 26) Woodham, R.: Photometrc method for determnng surface orentaton from multple mages, Optcal Engneerng, Vol.19, No.1, pp (1980). ( ) ( ) IEEE Ph.D. n Robotcs 11 Int l Conf. Shape Modelng and Applcatons 97 MIRU IEEE VR2001 Honorable Menton for the Outstandng Paper Award ACM IEEE
LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION
LEARNING A WARPED SUBSPACE MODEL OF FACES WITH IMAGES OF UNKNOWN POSE AND ILLUMINATION Jhun Hamm, and Danel D. Lee GRASP Laboratory, Unversty of Pennsylvana, 3330 Walnut Street, Phladelpha, PA, USA jhham@seas.upenn.edu,
More informationFace 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 informationFitting & 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 informationFace 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 informationReal-time. Shading of Folded Surfaces
Rhensche Fredrch-Wlhelms-Unverstät Bonn Insttute of Computer Scence II Computer Graphcs Real-tme Shadng of Folded Surfaces B. Ganster, R. Klen, M. Sattler, R. Sarlette Motvaton http://www www.vrtualtryon.de
More informationCS 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 informationPhotometric stereo. Recovering the surface f(x,y) Three Source Photometric stereo: Step1. Reflectance Map of Lambertian Surface
Photometric stereo Illumination Cones and Uncalibrated Photometric Stereo Single viewpoint, multiple images under different lighting. 1. Arbitrary known BRDF, known lighting 2. Lambertian BRDF, known lighting
More informationOn 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 informationThe Quotient Image: Class Based Re-rendering and Recognition With Varying Illuminations
The Quotent Image: Class Based Re-renderng and Recognton Wth Varyng Illumnatons Tammy Rkln-Ravv and Amnon Shashua Insttute of Computer Scence, The Hebrew Unversty, Jerusalem 91904, Israel e-mal: ftammy,
More informationMotivation. TensorTextures: Multilinear Image-Based Rendering. Image-Based Rendering. Our Contribution. BTF Texture Mapping [Dana et al.
Motvaton ensoretures: Multlnear Image-Based Renderng Computer Graphcs Goal: Generaton of photorealstc vrtual envronments Classcal Computer Graphcs: Model based Renderng From obect models to mages Model
More informationDiscussion. History and Outline. Smoothness of Indirect Lighting. Irradiance Caching. Irradiance Calculation. Advanced Computer Graphics (Fall 2009)
Advanced Computer Graphcs (Fall 2009 CS 29, Renderng Lecture 6: Recent Advances n Monte Carlo Offlne Renderng Rav Ramamoorth http://nst.eecs.berkeley.edu/~cs29-13/fa09 Dscusson Problems dfferent over years.
More informationDiscussion. History and Outline. Smoothness of Indirect Lighting. Irradiance Calculation. Irradiance Caching. Advanced Computer Graphics (Fall 2009)
Advanced Computer Graphcs (Fall 2009 CS 283, Lecture 13: Recent Advances n Monte Carlo Offlne Renderng Rav Ramamoorth http://nst.eecs.berkeley.edu/~cs283/fa10 Dscusson Problems dfferent over years. Intally,
More informationMULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION
MULTISPECTRAL IMAGES CLASSIFICATION BASED ON KLT AND ATR AUTOMATIC TARGET RECOGNITION Paulo Quntlano 1 & Antono Santa-Rosa 1 Federal Polce Department, Brasla, Brazl. E-mals: quntlano.pqs@dpf.gov.br and
More informationIllumination Normalization for Robust Face Recognition Against Varying Lighting Conditions
llumnaton Normalzaton for Robust Face Recognton Aganst Varyng Lghtng Condtons Shguang Shan, Wen Gao, Bo Cao, Debn Zhao C-SVSON JDL, nsttute of Computng echnology, CAS, P.O.Box 274, Beng, Chna, 18 Computer
More informationAn 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 informationImage 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 informationCollaboratively 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 informationScan Conversion & Shading
Scan Converson & Shadng Thomas Funkhouser Prnceton Unversty C0S 426, Fall 1999 3D Renderng Ppelne (for drect llumnaton) 3D Prmtves 3D Modelng Coordnates Modelng Transformaton 3D World Coordnates Lghtng
More informationScan Conversion & Shading
1 3D Renderng Ppelne (for drect llumnaton) 2 Scan Converson & Shadng Adam Fnkelsten Prnceton Unversty C0S 426, Fall 2001 3DPrmtves 3D Modelng Coordnates Modelng Transformaton 3D World Coordnates Lghtng
More informationCorner-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 informationLecture 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 informationRange Data Registration Using Photometric Features
Range Data Regstraton Usng Photometrc Features Joon Kyu Seo, Gregory C. Sharp, and Sang Wook Lee Dept. of Meda Technology, Sogang Unversty, Seoul, Korea Dept. of Radaton Oncology, Massachusetts General
More informationThe Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 23, NO. 2, FEBRUARY 2001 129 The Quotent Image: Class-Based Re-Renderng and Recognton wth Varyng Illumnatons Amnon Shashua, Member,
More informationRobust 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 informationComputer Graphics. Jeng-Sheng Yeh 葉正聖 Ming Chuan University (modified from Bing-Yu Chen s slides)
Computer Graphcs Jeng-Sheng Yeh 葉正聖 Mng Chuan Unversty (modfed from Bng-Yu Chen s sldes) llumnaton and Shadng llumnaton Models Shadng Models for Polygons Surface Detal Shadows Transparency Global llumnaton
More informationWhat are the camera parameters? Where are the light sources? What is the mapping from radiance to pixel color? Want to solve for 3D geometry
Today: Calbraton What are the camera parameters? Where are the lght sources? What s the mappng from radance to pel color? Why Calbrate? Want to solve for D geometry Alternatve approach Solve for D shape
More informationLEAST SQUARES. RANSAC. HOUGH TRANSFORM.
LEAS SQUARES. RANSAC. HOUGH RANSFORM. he sldes are from several sources through James Has (Brown); Srnvasa Narasmhan (CMU); Slvo Savarese (U. of Mchgan); Bll Freeman and Antono orralba (MI), ncludng ther
More informationFace Recognition Based on SVM and 2DPCA
Vol. 4, o. 3, September, 2011 Face Recognton Based on SVM and 2DPCA Tha Hoang Le, Len Bu Faculty of Informaton Technology, HCMC Unversty of Scence Faculty of Informaton Scences and Engneerng, Unversty
More informationColor in OpenGL Polygonal Shading Light Source in OpenGL Material Properties Normal Vectors Phong model
Color n OpenGL Polygonal Shadng Lght Source n OpenGL Materal Propertes Normal Vectors Phong model 2 We know how to rasterze - Gven a 3D trangle and a 3D vewpont, we know whch pxels represent the trangle
More informationLearning a Locality Preserving Subspace for Visual Recognition
Learnng a Localty Preservng Subspace for Vsual Recognton Xaofe He *, Shucheng Yan #, Yuxao Hu, and Hong-Jang Zhang Mcrosoft Research Asa, Bejng 100080, Chna * Department of Computer Scence, Unversty of
More informationPalmprint 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 informationFace Recognition Under Varying Illumination Based on MAP Estimation Incorporating Correlation Between Surface Points
Face Recognition Under Varying Illumination Based on MAP Estimation Incorporating Correlation Between Surface Points Mihoko Shimano 1, Kenji Nagao 1, Takahiro Okabe 2,ImariSato 3, and Yoichi Sato 2 1 Panasonic
More informationPOSSIBILITY FUZZY C-MEANS CLUSTERING FOR EXPRESSION INVARIANT FACE RECOGNITION
POSSIBILITY FUZZY C-MEANS CLUSTERING FOR EXPRESSION INVARIANT FACE RECOGNITION Aruna Bhat Department of Electrcal Engneerng, IIT Delh, HauzKhas, New Delh ABSTRACT Face beng the most natural method of dentfcaton
More informationRealistic Rendering. Traditional Computer Graphics. Traditional Computer Graphics. Production Pipeline. Appearance in the Real World
Advanced Computer Graphcs (Fall 2009 CS 294, Renderng Lecture 11 Representatons of Vsual Appearance Rav Ramamoorth Realstc Renderng Geometry Renderng Algorthm http://nst.eecs.berkeley.edu/~cs294-13/fa09
More informationFeature 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 informationLighting. Dr. Scott Schaefer
Lghtng Dr. Scott Schaefer 1 Lghtng/Illumnaton Color s a functon of how lght reflects from surfaces to the eye Global llumnaton accounts for lght from all sources as t s transmtted throughout the envronment
More informationCompetitive 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 informationGlobal Illumination: Radiosity
Last Tme? Global Illumnaton: Radosty Planar Shadows Shadow Maps An early applcaton of radatve heat transfer n stables. Projectve Texture Shadows (Texture Mappng) Shadow Volumes (Stencl Buffer) Schedule
More informationLearning the Multilinear Structure of Visual Data
Learnng the Multlnear Structure of Vsual Data Mengjao Wang Yanns Panagaks Patrck Snape Stefanos Zaferou Imperal College London {m.wang15,.panagaks,p.snape,s.zaferou}@mperal.ac.uk Abstract Statstcal decomposton
More informationMonte Carlo 1: Integration
Monte Carlo : Integraton Prevous lecture: Analytcal llumnaton formula Ths lecture: Monte Carlo Integraton Revew random varables and probablty Samplng from dstrbutons Samplng from shapes Numercal calculaton
More informationTone-Aware Sparse Representation for Face Recognition
Tone-Aware Sparse Representaton for Face Recognton Lngfeng Wang, Huayu Wu and Chunhong Pan Abstract It s stll a very challengng task to recognze a face n a real world scenaro, snce the face may be corrupted
More informationRecognizing 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 informationComputer 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 informationGeneral Regression and Representation Model for Face Recognition
013 IEEE Conference on Computer Vson and Pattern Recognton Workshops General Regresson and Representaton Model for Face Recognton Janjun Qan, Jan Yang School of Computer Scence and Engneerng Nanjng Unversty
More informationEYE 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 informationMulti-stable Perception. Necker Cube
Mult-stable Percepton Necker Cube Spnnng dancer lluson, Nobuuk Kaahara Fttng and Algnment Computer Vson Szelsk 6.1 James Has Acknowledgment: Man sldes from Derek Hoem, Lana Lazebnk, and Grauman&Lebe 2008
More informationTwo-Dimensional Supervised Discriminant Projection Method For Feature Extraction
Appl. Math. Inf. c. 6 No. pp. 8-85 (0) Appled Mathematcs & Informaton cences An Internatonal Journal @ 0 NP Natural cences Publshng Cor. wo-dmensonal upervsed Dscrmnant Proecton Method For Feature Extracton
More informationCluster Analysis of Electrical Behavior
Journal of Computer and Communcatons, 205, 3, 88-93 Publshed Onlne May 205 n ScRes. http://www.scrp.org/ournal/cc http://dx.do.org/0.4236/cc.205.350 Cluster Analyss of Electrcal Behavor Ln Lu Ln Lu, School
More informationRELATIVE ORIENTATION ESTIMATION OF VIDEO STREAMS FROM A SINGLE PAN-TILT-ZOOM CAMERA. Commission I, WG I/5
RELATIVE ORIENTATION ESTIMATION OF VIDEO STREAMS FROM A SINGLE PAN-TILT-ZOOM CAMERA Taeyoon Lee a, *, Taeung Km a, Gunho Sohn b, James Elder a a Department of Geonformatc Engneerng, Inha Unersty, 253 Yonghyun-dong,
More informationMonte Carlo 1: Integration
Monte Carlo : Integraton Prevous lecture: Analytcal llumnaton formula Ths lecture: Monte Carlo Integraton Revew random varables and probablty Samplng from dstrbutons Samplng from shapes Numercal calculaton
More informationAnalysis of photometric factors based on photometric linearization
3326 J. Opt. Soc. Am. A/ Vol. 24, No. 10/ October 2007 Mukaigawa et al. Analysis of photometric factors based on photometric linearization Yasuhiro Mukaigawa, 1, * Yasunori Ishii, 2 and Takeshi Shakunaga
More informationA Bilinear Model for Sparse Coding
A Blnear Model for Sparse Codng Davd B. Grmes and Rajesh P. N. Rao Department of Computer Scence and Engneerng Unversty of Washngton Seattle, WA 98195-2350, U.S.A. grmes,rao @cs.washngton.edu Abstract
More informationFeature Extraction Based on Maximum Nearest Subspace Margin Criterion
Neural Process Lett DOI 10.7/s11063-012-9252-y Feature Extracton Based on Maxmum Nearest Subspace Margn Crteron Y Chen Zhenzhen L Zhong Jn Sprnger Scence+Busness Meda New York 2012 Abstract Based on the
More informationSkeleton Cube for Lighting Environment Estimation
(MIRU2004) 2004 7 606 8501 E-mail: {takesi-t,maki,tm}@vision.kuee.kyoto-u.ac.jp 1) 2) Skeleton Cube for Lighting Environment Estimation Takeshi TAKAI, Atsuto MAKI, and Takashi MATSUYAMA Graduate School
More informationRobust Inlier Feature Tracking Method for Multiple Pedestrian Tracking
2011 Internatonal Conference on Informaton and Intellgent Computng IPCSIT vol.18 (2011) (2011) IACSIT Press, Sngapore Robust Inler Feature Trackng Method for Multple Pedestran Trackng Young-Chul Lm a*
More informationBOOSTING 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 informationCombination 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 informationFitting and Alignment
Fttng and Algnment Computer Vson Ja-Bn Huang, Vrgna Tech Many sldes from S. Lazebnk and D. Hoem Admnstratve Stuffs HW 1 Competton: Edge Detecton Submsson lnk HW 2 wll be posted tonght Due Oct 09 (Mon)
More informationImprovement of Spatial Resolution Using BlockMatching Based Motion Estimation and Frame. Integration
Improvement of Spatal Resoluton Usng BlockMatchng Based Moton Estmaton and Frame Integraton Danya Suga and Takayuk Hamamoto Graduate School of Engneerng, Tokyo Unversty of Scence, 6-3-1, Nuku, Katsuska-ku,
More informationNew dynamic zoom calibration technique for a stereo-vision based multi-view 3D modeling system
New dynamc oom calbraton technque for a stereo-vson based mult-vew 3D modelng system Tao Xan, Soon-Yong Park, Mural Subbarao Dept. of Electrcal & Computer Engneerng * State Unv. of New York at Stony Brook,
More informationThe Problem. The Problem. What is Face Recognition? The Problem. Quiz. The Context of Face Recognition
An Overvew of Face Recognton Usng Egenfaces Acknowledgements: Orgnal Sldes from Prof. atthew Turk -- also notes from the web -Egenvalues and Egenvectors -PCA -Egenfaces Outlne Why automated face recognton?
More informationRobust Face Recognition Using Eigen Faces and Karhunen-Loeve Algorithm
Robust Face Recognton Usng Egen Faces and Karhunen-Loeve Algorthm Parvnder S. Sandhu, Iqbaldeep Kaur, Amt Verma, Prateek Gupta Abstract The current research paper s an mplementaton of Egen Faces and Karhunen-Loeve
More informationA 3D Reconstruction System of Indoor Scenes with Rotating Platform
A 3D Reconstructon System of Indoor Scenes wth Rotatng Platform Feng Zhang, Lmn Sh, Zhenhu Xu, Zhany Hu Insttute of Automaton, Chnese Academy of Scences {fzhang, lmsh, zhxu, huzy}@nlpr.a.ac.cnl Abstract
More informationKernel principal component analysis network for image classification 1
Kernel prncpal component analyss network for mage classfcaton Wu Dan 4 Wu Jasong 34 Zeng Ru 4 Jang Longyu 4 Lotf Senhadj 34 Shu Huazhong 4 ( Key Laboratory of Computer Network and Informaton Integraton
More information3D Shape of Specular Surface Measurement Using Five Degrees of Freedom Camera System
Khar usuf, Prasetyo Ed, Amr Radz Abdul Ghan 3D Shape of Specular Measurement Usng Fve Degrees of Freedom Camera System KHAIRI USUF, PRASETO EDI and AMIR RADI ABDUL GHANI Department of Engneerng Desgn and
More informationLOCAL 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 informationDependence of the Color Rendering Index on the Luminance of Light Sources and Munsell Samples
Australan Journal of Basc and Appled Scences, 4(10): 4609-4613, 2010 ISSN 1991-8178 Dependence of the Color Renderng Index on the Lumnance of Lght Sources and Munsell Samples 1 A. EL-Bally (Physcs Department),
More informationShape Representation Robust to the Sketching Order Using Distance Map and Direction Histogram
Shape Representaton Robust to the Sketchng Order Usng Dstance Map and Drecton Hstogram Department of Computer Scence Yonse Unversty Kwon Yun CONTENTS Revew Topc Proposed Method System Overvew Sketch Normalzaton
More informationAccounting for the Use of Different Length Scale Factors in x, y and z Directions
1 Accountng for the Use of Dfferent Length Scale Factors n x, y and z Drectons Taha Soch (taha.soch@kcl.ac.uk) Imagng Scences & Bomedcal Engneerng, Kng s College London, The Rayne Insttute, St Thomas Hosptal,
More informationLocal Minima Free Parameterized Appearance Models
Local Mnma Free Parameterzed Appearance Models Mnh Hoa Nguyen Fernando De la Torre Robotcs Insttute, Carnege Mellon Unversty Pttsburgh, PA 1513, USA. mnhhoa@cmu.edu ftorre@cs.cmu.edu Abstract Parameterzed
More informationUsing the Visual Words based on Affine-SIFT Descriptors for Face Recognition
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
More informationInfrared face recognition using texture descriptors
Infrared face recognton usng texture descrptors Moulay A. Akhlouf*, Abdelhakm Bendada Computer Vson and Systems Laboratory, Laval Unversty, Quebec, QC, Canada G1V0A6 ABSTRACT Face recognton s an area of
More informationDIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION. Department of Artificial Intelligence Kyushu Institute of Technology
DIFFUSE-SPECULAR SEPARATION OF MULTI-VIEW IMAGES UNDER VARYING ILLUMINATION Kouki Takechi Takahiro Okabe Department of Artificial Intelligence Kyushu Institute of Technology ABSTRACT Separating diffuse
More informationA 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 information3D Face Reconstruction With Local Feature Refinement
ternatonal Journal of Multmeda and Ubqutous Engneerng Vol.9, No.8 (014), pp.59-7 http://dx.do.org/10.1457/jmue.014.9.8.06 3D Face Reconstructon Wth Local Feature Refnement Rudy Adpranata 1, Kartka Gunad
More information3D Face Reconstruction With Local Feature Refinement. Abstract
, pp.6-74 http://dx.do.org/0.457/jmue.04.9.8.06 3D Face Reconstructon Wth Local Feature Refnement Rudy Adpranata, Kartka Gunad and Wendy Gunawan 3, formatcs Department, Petra Chrstan Unversty, Surabaya,
More informationIllumination-Robust Face Recognition based on Gabor Feature Face Intrinsic Identity PCA Model
Illumination-Robust Face Recognition based on Gabor Feature Face Intrinsic Identity PCA Model TAE IN SEOL*, SUN-TAE CHUNG*, SUNHO KI**, SEONGWON CHO**, YUN-KWANG HONG*** *School of Electronic Engineering
More informationFEATURE EXTRACTION. Dr. K.Vijayarekha. Associate Dean School of Electrical and Electronics Engineering SASTRA University, Thanjavur
FEATURE EXTRACTION Dr. K.Vjayarekha Assocate Dean School of Electrcal and Electroncs Engneerng SASTRA Unversty, Thanjavur613 41 Jont Intatve of IITs and IISc Funded by MHRD Page 1 of 8 Table of Contents
More informationA Novel Image Matching Method Based on SIFT
Sensors & Transducers, Vol. 7, Issue 5, May 04, pp. 76-8 Sensors & Transducers 04 by IFSA Publshng, S. L. http://www.sensorsportal.com A Novel Image Matchng Method Based on SIFT Yuan-Sheng LIN, * Gang
More informationPCA Based Gait Segmentation
Honggu L, Cupng Sh & Xngguo L PCA Based Gat Segmentaton PCA Based Gat Segmentaton Honggu L, Cupng Sh, and Xngguo L 2 Electronc Department, Physcs College, Yangzhou Unversty, 225002 Yangzhou, Chna 2 Department
More informationLecture 9 Fitting and Matching
In ths lecture, we re gong to talk about a number of problems related to fttng and matchng. We wll formulate these problems formally and our dscusson wll nvolve Least Squares methods, RANSAC and Hough
More informationRecovering spectral data from digital prints with an RGB camera using multi-exposure method
Recoverng spectral data from dgtal prnts wth an RGB camera usng mult-exposure method Mkko Nuutnen, Prkko Ottnen; Department of Meda Technology, Aalto Unversty School of Scence and Technology; Espoo, Fnland
More informationAngle-Independent 3D Reconstruction. Ji Zhang Mireille Boutin Daniel Aliaga
Angle-Independent 3D Reconstructon J Zhang Mrelle Boutn Danel Alaga Goal: Structure from Moton To reconstruct the 3D geometry of a scene from a set of pctures (e.g. a move of the scene pont reconstructon
More informationSkew 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 informationA 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 informationLearning Image Alignment without Local Minima for Face Detection and Tracking
Learnng Image Algnment wthout Local Mnma for Face Detecton and Trackng Mnh Hoa Nguyen Fernando De la Torre Robotcs Insttute, Carnege Mellon Unversty Pttsburgh, PA 15213, USA. mnhhoa@cmu.edu ftorre@cs.cmu.edu
More informationNine Points of Light: Acquiring Subspaces for Face Recognition under Variable Lighting
To Appear in CVPR 2001 Nine Points of Light: Acquiring Subspaces for Face Recognition under Variable Lighting Kuang-Chih Lee Jeffrey Ho David Kriegman Beckman Institute and Computer Science Department
More informationFitting a Morphable Model to 3D Scans of Faces
Fttng a Morphable Model to 3D Scans of Faces Volker Blanz Unverstät Segen, Segen, Germany blanz@nformatk.un-segen.de Krstna Scherbaum MPI Informatk, Saarbrücken, Germany scherbaum@mp-nf.mpg.de Hans-Peter
More informationGenerating a Mapping Function from one Expression to another using a Statistical Model of Facial Shape
Generatng a Mappng Functon from one Expresson to another usng a Statstcal Model of Facal Shape John Ghent Computer Scence Department Natonal Unversty of Ireland, Maynooth Maynooth, Co. Kldare, Ireland
More informationFast, Arbitrary BRDF Shading for Low-Frequency Lighting Using Spherical Harmonics
Thrteenth Eurographcs Workshop on Renderng (2002) P. Debevec and S. Gbson (Edtors) Fast, Arbtrary BRDF Shadng for Low-Frequency Lghtng Usng Sphercal Harmoncs Jan Kautz 1, Peter-Pke Sloan 2 and John Snyder
More informationRobust Low-Rank Regularized Regression for Face Recognition with Occlusion
Robust Low-Rank Regularzed Regresson for ace Recognton wth Occluson Janjun Qan, Jan Yang, anlong Zhang and Zhouchen Ln School of Computer Scence and ngneerng, Nanjng Unversty of Scence and echnology Key
More informationAppearance-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 informationActive shape model-based user identification for an intelligent wheelchair. P. Jia* and H. Hu. 1 Introduction
Int. J. Advanced Mechatronc Systems, Vol. X, No. Y, 200X 1 Actve shape model-based user dentfcaton for an ntellgent wheelchar P. Ja* and H. Hu School of Computer Scence and Electronc Engneerng, Unversty
More informationClustering Appearances of Objects Under Varying Illumination Conditions
Clustering Appearances of Objects Under Varying Illumination Conditions Jeffrey Ho Ming-Hsuan Yang Jongwoo Lim Kuang-Chih Lee David Kriegman jho@cs.ucsd.edu myang@honda-ri.com jlim1@uiuc.edu klee10@uiuc.edu
More informationImproved 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 informationSTUDY ON CLOSE RANGE DIGITISATION TECHNIQUES INTEGRATED WITH REFLECTANCE ESTIMATION
STUDY ON CLOSE RANGE DIGITISATION TECHNIQUES INTEGRATED WITH REFLECTANCE ESTIMATION Jakub Krzesłowsk Insttute of Mcromechancs and Photoncs, Warsaw Unversty of Technology, Bobol 8 02-525 Warsaw, Poland
More informationClassifier Selection Based on Data Complexity Measures *
Classfer Selecton Based on Data Complexty Measures * Edth Hernández-Reyes, J.A. Carrasco-Ochoa, and J.Fco. Martínez-Trndad Natonal Insttute for Astrophyscs, Optcs and Electroncs, Lus Enrque Erro No.1 Sta.
More information3D Face Structure Extraction from Images at Arbitrary Poses and under. Arbitrary Illumination Conditions
3D Face Structure Extracton from Images at Arbtrary Poses and under Arbtrary Illumnaton Condtons A Thess Submtted to the Faculty Of Drexel Unversty By Cupng Zhang In partal fulfllment of the Requrements
More informationVideo 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 informationA Range Image Refinement Technique for Multi-view 3D Model Reconstruction
A Range Image Refnement Technque for Mult-vew 3D Model Reconstructon Soon-Yong Park and Mural Subbarao Electrcal and Computer Engneerng State Unversty of New York at Stony Brook, USA E-mal: parksy@ece.sunysb.edu
More information