Estimation of Face Depth Maps from Color Textures using Canonical Correlation Analysis
|
|
- Aron Norman
- 5 years ago
- Views:
Transcription
1 Computer Vision Winter Workshop 006, Ondřej Chum, Vojtěch Franc (eds.) Telč, Czech Republic, February 6 8 Czech Pattern Recognition Society Estimation of Face Depth Maps from Color Textures using Canonical Correlation Analysis Michael Reiter, René Donner, Georg Langs, and Horst Bischof Pattern Recognition and Image Processing Group, Vienna University of Technology, Favoritenstr. 9, A-040 Vienna, Austria rei@prip.tuwien.ac.at, donner@prip.tuwien.ac.at, langs@prip.tuwien.ac.at Institute for Computer Graphics and Vision, Graz University of Technology Inffeldg. 6.OG, A-800 Graz, Austria, bischof@icg.tu-graz.ac.at Abstract We propose a method for estimating face depth maps from color face images. The method is based on Canonical Correlation Analysis (CCA) which exploits the correlation between face color texture and surface depth. The results of experiments conducted on a database of 8 3D scans with corresponding color images show that only a small number of canonical factors are needed to describe the functional relation of depth and texture with reasonable accuracy. Training RGB images Depth maps CCA Canonical factor pairs Introduction The recovery of depth and shape information from D-face images allows to deal with effects of changing illumination conditions and viewing angle [6]. It can be used, for example, to remove or reduce the effects of illumination and thereby increase the recognition accuracy in complex lighting situations. As another example, consider a face image acquired by a surveillance camera showing the face in a arbitrary viewing angle. Matching with a frontal view image stored in a database could be performed by transforming the stored image, i.e. rendering a synthetic face image with corresponding viewing angle and lighting conditions using a 3D-depth map of the face. Different approaches exist for recovering shape from D face images. Yuille et al. [6] use Singular Value Decomposition (SVD) to reconstruct shape and albedo from multiple images under varying illumination conditions. By isolating each of the factors that govern the face appearance, their model allows to predict the shape of faces and generate face images under new illumination conditions with the use of less training data than standard appearance models. Shape from shading [7, 7] algorithms have been applied to face images, where different constraints such as symmetry or (piece-wise) constant albedo are used to render the problem well-posed. In statistical approaches [3,,, 4] the relationship of shape and intensity is learned by training from a set of examples, i.e. intensity images with corresponding shapes. In [3] a 3D-morphable model is learned from 3D scans, which Test Input image Predicted depth map Figure : Overview of the algorithm: During training canonical factor pairs are generated from a set of training examples. They are used for the prediction of a 3D map from RGB data during application. can be matched with new input images by an iterative optimization procedure. The parameters of the matched model can be used to determine the shape of the input face. In this paper, we propose a statistical method for predicting 3D depth maps of faces from frontal view color face images based on canonical correlation analysis (CCA)[0]. The basic idea of our approach is, that the relationship of depth and face texture, as a combined effect of illumination direction, albedo and shape can be modelled effectively with a small number of factors pairs, i.e., correlated linear features in the space of depth images and color images. The method is not limited to face images but can generally applied to other classes of objects (surfaces) having similar structure, variability and shadows. On overview of the proposed method is depicted in Fig. The CCA approach allows to take into account the vector spaces of color images and corresponding shapes simultaneously. It determines linear combinations of variables () in each of the two signals, which are
2 Estimation of Face Depth Maps from Color Textures using Canonical Correlation Analysis pairwise maximally correlated. The directions of maximum correlation (canonical factors) capture relevant signal components, constituting the functional relation of the two signals. There exist a number of related regression techniques, such as Multivariate Linear Regression(MLR) [8], Partial Least Squares [9][8], Reduced Rank Wiener Filtering (see for example [6]). CCA, in particular, has some very attractive properties (for example, it is invariant w.r.t. affine transformations - and thus scaling - of the input variables) and can not only be used for regression purposes, but whenever one needs to establish a relation between two sets of measurements (e.g., finding corresponding points in stereo images [4]). In signal processing, CCA is used for optimal reduced-rank filtering [], where the goal is data reduction, robustness against noise and high computational efficiency. It has also been successfully applied to pattern classification [3], appearance based 3D pose estimation [] and stereo vision [4]. The rest of this paper is organized as follows: Section introduces Canonical Correlation Analysis. In Section 3 the experimental setup is explained and the results are presented, while Section 4 provides a conclusion and an outlook. Canonical Correlation Analysis for prediction of depth maps from intensity images Canonical Correlation Analysis is a very powerful tool that is especially well suited for relating two sets of measurements (signals). Like principal components analysis (PCA), CCA also reduces the dimensionality of the original signals, since only a few factor-pairs are normally needed to represent the relevant information; unlike PCA, however, CCA takes into account the relationship between two signal spaces (in the correlation sense), which makes them better suited for regression tasks than PCA. We regard the image vector of the RGB color image and the depth maps as two correlated random vectors x IR p and y IR q, where q and p corresponds to the dimensionality of the vector space of the RGB images and depth maps. In [3] two separate eigenspaces are generated by PCA and a linear regression on the eigenspace coefficients is used to model the relation of x and y.. CCA We use CCA to find pairs of directions w x and w y that maximize the correlation between the projections x = w T x x and y = w T y y. In the context of CCA, the projections x and y are also referred to as. Formally, the directions can be found as maxima of the function E[xy] ρ = E[x ]E[y ] = E[w T x xy T w y ], E[w T x xx T w x ]E[w T y yy T w y ] ρ = w T x C xy w y w T x C xx w x w T y C yy w y. x y canonical factors W x x y w x LEAST SQUARES REGRESSION CCA maximises the correlation between the W y canonical factors w y Figure : Scheme of canonical correlation analysis regression. The (empirical) canonical factors W x and W y maximize the correlation of projections W T x X and W T x Y of sets of training data X and Y. whereby C xx IR p p and C yy IR q q are the withinset covariance matrices of x and y, respectively, while C xy IR p q denotes their between-set covariance matrix. A number of at most k = min(p, q) factor pairs w i x, w i y, i =,..., k can be obtained by successively solving w i = (w it x, w it y ) T = arg max (w i x,wi y ) {ρ} subject to ρ(w j x, w i y) = ρ(w i x, w j y) = 0 for j =,..., i The factor pairs w i can be obtained as solutions (i.e., eigenvectors) of a generalized eigenproblem (for details see e.g., []). The extremum values ρ(w i ), which are referred to as canonical correlations, are obtained as the corresponding eigenvalues. By employing CCA, we perform regression on only a small number (compared to the original dimensionality of the data) of linear features, i.e. derived linear combinations of original response variables y. Thus, CCA can be used to compute the (reduced) rank-n regression parameter matrix by using only n < k factor pairs. Thereby, in contrast to standard multivariate regression CCA takes advantage of the correlations of response variables to improve predictive accuracy [5]. In our approach, we use the regression scheme depicted in Fig., where we perfom regression of the response variables y onto the leading x proj = W T x x, where W x = (w x,..., w n x) with n < k. Analogously to standard multivariate regression, CCA can also directly be formulated as a linear least squares problem. It can be easily shown that minimizing RSS(w x, w y ) = E[(w T x x w T y y) ] = E[w T x xx T w x ] E[w T x xy T w y ] + E[w T y yy T w y ] = w T x C xx w x w T x C xy w y + w T y C yy w y
3 Michael Reiter, René Donner, Georg Langs, and Horst Bischof subject to the constraints w T x C xx w x =, w T y C yy w y =. yields the first canonical factor pair. An iterative (online) CCA algorithm based on the above formulation is described in [4]. This formulation also allows to successively obtain multiple factor pairs.. Predicting depth maps Given a training set of N pairs of RGB images X = (x,..., x N ) and corresponding depth maps Y = (y,..., y N ) where x j resp. y j are vector representations, we obtain empirical canonical factor pairs w i. A subset of factor pairs w i with i =,..., n < k is then used for the prediction of depth maps from new RGB images. The subset corresponds to the canonical factors with the highest canonical correlations in the training set. We denote the matrices with the leading empirical canonical factors by W x = (wx,..., wx) n and W y = (wy,..., wy n ), respectively. Given a specific input RGB image x the prediction y predicted can be obtained as y predicted (x) = R T ccax. () The matrix R cca is pre-computed during training by R cca = P Y T, () where P are the projections of training images onto the leading canonical factors, i.e., and P denotes the pseudo-inverse of P. 3 Experimental results P = W T x X (3) Setup For the experiments the USF Human-ID 3D Face Database [5] was used. The 3D form of the faces is acquired with a CyberWare Laser scanner. It gives a cylindrical depth map of the face with degree horizontal resolution. The faces were remapped into a cartesian coordinate system with the z-direction parallel to the radiant going trough the center between the eyes and resolution corresponding the the vertical resolution of the scans. Regions not belonging to the face were discarded. The evaluation was performed on a set of 8 face images. During training, we use 5-fold cross-validation on the training set of 50 images to determine the optimal number of factor pairs and the optimal value for the regularization parameter needed for CCA (for details of how to perform regularization see []). The performance is evaluated on the test set of the remaining 68 images. The prediction is assessed qualitatively and quantitatively. Note that the multiplication of x with R cca can be performed in two successive steps. In standard MLR, P = X. Absolute voxel error Figure 3: Box plots of the absolute median pixel value error for CCA regression using different numbers of factor pairs. The horizontal lines correspond to the lower and upper quartile of the MLR results. The optimum of CCA regression with a 9.% smaller median error is obtained using 5 factor pairs. Results Since the number of training data N is much lower than the dimensionality of the signal spaces, the maximum possible number of factor pairs k is determined by the number of training data pairs (50). The quantitative results given in Figures 3 and 4 show, that while the optimal number of factor pairs (determining the rank of the regression matrix) is actually much smaller than 50, the depth error improves to 85% of the error of standard regression with 5 factor pairs. Only a fraction of the available factor pairs is sufficient for predicting the texture with higher accuracy than full-rank MLR achieves. The resulting mean depth error is 6.93 voxels. Note that most of the error is caused by the distortions at the boundary of the faces. In Figure 5 the spectrum of the canonical factors is plotted. Figure 6 shows the factor pairs, and 3 corresponding to the 3 largest canonical correlations. Qualitative results are shown in Figure 7. The first and second columns show the original (ground truth) and predicted 3D depth maps (as textureless surfaces) of two example faces, respectively. In the third column the original (ground truth) 3D surface with face texture is depicted. In the forth column the 3D surface with texture predicted by CCA is shown, and in the third column the difference of the depth values is visualized in the same scale. 4 Conclusion We have presented a method for predicting face depth maps from color images using Canonical Correlation Analysis. Only a small number of factor pairs are needed to predict the depth map from color images with reasonable accuracy. The increase of accuracy when using only a small number of factor pairs indicates that the noise in the training data degrades MLR results. Despite the simple nature of the algorithm (reconstruction is performed by a matrix multiplication) that does not utilize an explicit illumination model, rea- 3
4 Estimation of Face Depth Maps from Color Textures using Canonical Correlation Analysis (a) (b) (c) (d) (e) (f) Figure 6: First 3 canonical factors of represented as RGB color images (a-c) and depth images (d-f) respectively. Original surface Reconstructed surface Original face patch Reconstructed face patch Difference surface Figure 7: Original images and CCA-predicted depth maps for 3 faces along the approximation error. The original texture is projected onto both depth maps. Note that the approximation (depth) error has the same scaling as original and reconstruction, thus displaying the high accuracy of the reconstruction. sonable depth predictions are achieved. However, in our experiments we had controlled non-varying illumination conditions. A more profound analysis w.r.t. illumination sensitivity and comparison to other shape-from-shading methods is needed. Acknowledgement This research has been supported by the Austrian Science Fund (FWF) under the grant P7083-N04 (AAMIR). Part of this work has been carried out within the K-plus Competence center ADVANCED COMPUTER VISION funded under the K plus program. 4 References [] JJ Atick, PA Griffin, and AN Redlich. Statistical approach to shape from shading: reconstruction of three- dimensional face surfaces from single two-dimensional images. Neural Computation, 996. [] Ronen Basri and David Jacobs. Photometric stereo with general, unknown lighting. In CVPR, 00. [3] V. Blanz, S. Romdhani, and T. Vetter. Face identification across different poses and illuminations with a 3d morphable model. Auto. Face and Gesture Recognition, 00. [4] Magnus Borga. Learning Multidimensional Signal Processing. Linko ping Studies in Science and Technology, Dissertations, No. 53. Department of Electrical Engineering, Linko ping University, Linko ping, Sweden, 998.
5 Michael Reiter, René Donner, Georg Langs, and Horst Bischof Relative error Figure 4: Box plots of the pixel value error for CCA regression relative to standard MLR using different numbers of factor pairs. The horizontal line correspond to the lower and upper quartile of the MLR results, which coincide with the median in this relative diagramm. Quartiles for the CCA results correspond to the variation w.r.t. the MLR result on the same individual images. [] Yingbo Hua, Maziar Nikpour, and Petre Stoica. Optimal reduced-rank estimation and filtering. IEEETSP, 49(3): , 00. [] Thomas Melzer, Michael Reiter, and Horst Bischof. Appearance models based on kernel canonical correlation analysis. Pattern Recognition, 39(9):96 973, 003. [3] A. Pezeshki, L. L. Scharf, M. R. Azimi-Sadjadi, and Y. Hua. Underwater target classification using canonical correlations. In Proc. of MTS/IEEE Oceans 03, 003. [4] John A Robinson and Justen R Hyde. Estimation of face depths by conditional densities. In BMVC, 005. [5] Sudeep Sarkar. 3D Face Database, Univ. of Florida. [6] A.L. Yuille, D. Snow, and R. Epstein. Determining generative models of objects under varying illumination: Shape and albedo from multiple images using SVD and integrability. International Journal of Computer Vision, 999. [7] W Zhao and R Chellappa. Illumination-insensitive face recognition using symmetric shape-from-shading. In IEEE CVPR, Correlation Figure 5: Spectrum of canonical correlations. [5] L. Breiman and J.H. Friedman. Predicting multivariate responses in multiple linear regression. Journal of the Royal Statistical Society, 59():3 54, 997. [6] Konstantinos I. Diamantaras and S.Y. Kung. Principal Component Neural Networks. John Wiley & Sons, 996. [7] Roman Dovgard and Ronen Basri. Statistical symmetric shape from shading for 3d structure recovery of faces. In ECCV, 004. [8] T. Hastie, R. Tibshirani, and J. Friedman. The elements of statistical learning. New York: Springer-Verlag, 00. [9] A. Höskuldsson. PLS regression methods. Journal of Chemometrics, : 8, 988. [0] H. Hotelling. Relations between two sets of variates. Biometrika, 8:3 377,
Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces
Statistical Symmetric Shape from Shading for 3D Structure Recovery of Faces Roman Dovgard and Ronen Basri Dept. of Applied Mathematics and Computer Science, Weizmann Institute of Science, Rehovot 76100,
More informationRecovering 3D Facial Shape via Coupled 2D/3D Space Learning
Recovering 3D Facial hape via Coupled 2D/3D pace Learning Annan Li 1,2, higuang han 1, ilin Chen 1, iujuan Chai 3, and Wen Gao 4,1 1 Key Lab of Intelligent Information Processing of CA, Institute of Computing
More informationFace Shape Recovery from a Single Image Using CCA Mapping between Tensor Spaces
Face Shape Recovery from a Single Image Using CCA Mapping between Tensor Spaces Zhen Lei Qinqun Bai Ran He Stan Z. Li Center for Biometrics and Security Research & National Laboratory of Pattern Recognition,
More informationOn-line, Incremental Learning of a Robust Active Shape Model
On-line, Incremental Learning of a Robust Active Shape Model Michael Fussenegger 1, Peter M. Roth 2, Horst Bischof 2, Axel Pinz 1 1 Institute of Electrical Measurement and Measurement Signal Processing
More informationModel-based 3D Shape Recovery from Single Images of Unknown Pose and Illumination using a Small Number of Feature Points
Model-based 3D Shape Recovery from Single Images of Unknown Pose and Illumination using a Small Number of Feature Points Ham M. Rara and Aly A. Farag CVIP Laboratory, University of Louisville {hmrara01,
More informationApplications Video Surveillance (On-line or off-line)
Face Face Recognition: Dimensionality Reduction Biometrics CSE 190-a Lecture 12 CSE190a Fall 06 CSE190a Fall 06 Face Recognition Face is the most common biometric used by humans Applications range from
More informationRobust Estimation of Albedo for Illumination-invariant Matching and Shape Recovery
Robust Estimation of Albedo for Illumination-invariant Matching and Shape Recovery Soma Biswas, Gaurav Aggarwal and Rama Chellappa Center for Automation Research, UMIACS Dept. of ECE, Dept. of Computer
More informationTraining-Free, Generic Object Detection Using Locally Adaptive Regression Kernels
Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIENCE, VOL.32, NO.9, SEPTEMBER 2010 Hae Jong Seo, Student Member,
More informationLinear Discriminant Analysis in Ottoman Alphabet Character Recognition
Linear Discriminant Analysis in Ottoman Alphabet Character Recognition ZEYNEB KURT, H. IREM TURKMEN, M. ELIF KARSLIGIL Department of Computer Engineering, Yildiz Technical University, 34349 Besiktas /
More informationColour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation
ÖGAI Journal 24/1 11 Colour Segmentation-based Computation of Dense Optical Flow with Application to Video Object Segmentation Michael Bleyer, Margrit Gelautz, Christoph Rhemann Vienna University of Technology
More informationMultiresponse Sparse Regression with Application to Multidimensional Scaling
Multiresponse Sparse Regression with Application to Multidimensional Scaling Timo Similä and Jarkko Tikka Helsinki University of Technology, Laboratory of Computer and Information Science P.O. Box 54,
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 information3D Face Modelling Under Unconstrained Pose & Illumination
David Bryan Ottawa-Carleton Institute for Biomedical Engineering Department of Systems and Computer Engineering Carleton University January 12, 2009 Agenda Problem Overview 3D Morphable Model Fitting Model
More informationThe Novel Approach for 3D Face Recognition Using Simple Preprocessing Method
The Novel Approach for 3D Face Recognition Using Simple Preprocessing Method Parvin Aminnejad 1, Ahmad Ayatollahi 2, Siamak Aminnejad 3, Reihaneh Asghari Abstract In this work, we presented a novel approach
More informationFace Recognition Under Variable Lighting using Harmonic Image Exemplars
Face Recognition Under Variable Lighting using Harmonic Image Exemplars Lei Zhang Dimitris Samaras Department of Computer Science SUNY at Stony Brook, NY, 11790 lzhang, samaras @cs.sunysb.edu bstract We
More informationAnnouncements. Recognition I. Gradient Space (p,q) What is the reflectance map?
Announcements I HW 3 due 12 noon, tomorrow. HW 4 to be posted soon recognition Lecture plan recognition for next two lectures, then video and motion. Introduction to Computer Vision CSE 152 Lecture 17
More informationFace View Synthesis Across Large Angles
Face View Synthesis Across Large Angles Jiang Ni and Henry Schneiderman Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 1513, USA Abstract. Pose variations, especially large out-of-plane
More informationStereo and Epipolar geometry
Previously Image Primitives (feature points, lines, contours) Today: Stereo and Epipolar geometry How to match primitives between two (multiple) views) Goals: 3D reconstruction, recognition Jana Kosecka
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 informationThree-Dimensional Face Recognition: A Fishersurface Approach
Three-Dimensional Face Recognition: A Fishersurface Approach Thomas Heseltine, Nick Pears, Jim Austin Department of Computer Science, The University of York, United Kingdom Abstract. Previous work has
More informationAn ICA based Approach for Complex Color Scene Text Binarization
An ICA based Approach for Complex Color Scene Text Binarization Siddharth Kherada IIIT-Hyderabad, India siddharth.kherada@research.iiit.ac.in Anoop M. Namboodiri IIIT-Hyderabad, India anoop@iiit.ac.in
More informationThree-dimensional nondestructive evaluation of cylindrical objects (pipe) using an infrared camera coupled to a 3D scanner
Three-dimensional nondestructive evaluation of cylindrical objects (pipe) using an infrared camera coupled to a 3D scanner F. B. Djupkep Dizeu, S. Hesabi, D. Laurendeau, A. Bendada Computer Vision and
More informationcalibrated coordinates Linear transformation pixel coordinates
1 calibrated coordinates Linear transformation pixel coordinates 2 Calibration with a rig Uncalibrated epipolar geometry Ambiguities in image formation Stratified reconstruction Autocalibration with partial
More informationRapid 3D Face Modeling using a Frontal Face and a Profile Face for Accurate 2D Pose Synthesis
Rapid 3D Face Modeling using a Frontal Face and a Profile Face for Accurate 2D Pose Synthesis Jingu Heo and Marios Savvides CyLab Biometrics Center Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu,
More informationObject and Action Detection from a Single Example
Object and Action Detection from a Single Example Peyman Milanfar* EE Department University of California, Santa Cruz *Joint work with Hae Jong Seo AFOSR Program Review, June 4-5, 29 Take a look at this:
More informationModel-based segmentation and recognition from range data
Model-based segmentation and recognition from range data Jan Boehm Institute for Photogrammetry Universität Stuttgart Germany Keywords: range image, segmentation, object recognition, CAD ABSTRACT This
More informationFace Matching between Near Infrared and Visible Light Images
Face Matching between Near Infrared and Visible Light Images Dong Yi, Rong Liu, RuFeng Chu, Zhen Lei, and Stan Z. Li Center for Biometrics Security Research & National Laboratory of Pattern Recognition
More information2D-3D Face Matching using CCA
2D-3D Face Matching using CCA Weilong Yang, Dong Yi, Zhen Lei, Jitao Sang, Stan Z. Li Center for Biometrics Security Research & National Laboratory of Pattern Recognition Institute of Automation, Chinese
More informationOn Robust Regression in Photogrammetric Point Clouds
On Robust Regression in Photogrammetric Point Clouds Konrad Schindler and Horst Bischof Institute of Computer Graphics and Vision Graz University of Technology, Austria {schindl,bischof}@icg.tu-graz.ac.at
More informationRemoving Shadows from Images
Removing Shadows from Images Zeinab Sadeghipour Kermani School of Computing Science Simon Fraser University Burnaby, BC, V5A 1S6 Mark S. Drew School of Computing Science Simon Fraser University Burnaby,
More informationNonrigid Surface Modelling. and Fast Recovery. Department of Computer Science and Engineering. Committee: Prof. Leo J. Jia and Prof. K. H.
Nonrigid Surface Modelling and Fast Recovery Zhu Jianke Supervisor: Prof. Michael R. Lyu Committee: Prof. Leo J. Jia and Prof. K. H. Wong Department of Computer Science and Engineering May 11, 2007 1 2
More informationComponent-based Face Recognition with 3D Morphable Models
Component-based Face Recognition with 3D Morphable Models B. Weyrauch J. Huang benjamin.weyrauch@vitronic.com jenniferhuang@alum.mit.edu Center for Biological and Center for Biological and Computational
More informationHaresh D. Chande #, Zankhana H. Shah *
Illumination Invariant Face Recognition System Haresh D. Chande #, Zankhana H. Shah * # Computer Engineering Department, Birla Vishvakarma Mahavidyalaya, Gujarat Technological University, India * Information
More informationApplication of Principal Components Analysis and Gaussian Mixture Models to Printer Identification
Application of Principal Components Analysis and Gaussian Mixture Models to Printer Identification Gazi. Ali, Pei-Ju Chiang Aravind K. Mikkilineni, George T. Chiu Edward J. Delp, and Jan P. Allebach School
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 informationthen assume that we are given the image of one of these textures captured by a camera at a different (longer) distance and with unknown direction of i
Image Texture Prediction using Colour Photometric Stereo Xavier Lladó 1, Joan Mart 1, and Maria Petrou 2 1 Institute of Informatics and Applications, University of Girona, 1771, Girona, Spain fllado,joanmg@eia.udg.es
More informationIntegrating Shape from Shading and Shape from Stereo for Variable Reflectance Surface Reconstruction from SEM Images
Integrating Shape from Shading and Shape from Stereo for Variable Reflectance Surface Reconstruction from SEM Images Reinhard Danzl 1 and Stefan Scherer 2 1 Institute for Computer Graphics and Vision,
More informationPhotometric Stereo with Auto-Radiometric Calibration
Photometric Stereo with Auto-Radiometric Calibration Wiennat Mongkulmann Takahiro Okabe Yoichi Sato Institute of Industrial Science, The University of Tokyo {wiennat,takahiro,ysato} @iis.u-tokyo.ac.jp
More information3D Morphable Model Parameter Estimation
3D Morphable Model Parameter Estimation Nathan Faggian 1, Andrew P. Paplinski 1, and Jamie Sherrah 2 1 Monash University, Australia, Faculty of Information Technology, Clayton 2 Clarity Visual Intelligence,
More informationRegistration of Expressions Data using a 3D Morphable Model
Registration of Expressions Data using a 3D Morphable Model Curzio Basso, Pascal Paysan, Thomas Vetter Computer Science Department, University of Basel {curzio.basso,pascal.paysan,thomas.vetter}@unibas.ch
More informationData Mining Chapter 3: Visualizing and Exploring Data Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University
Data Mining Chapter 3: Visualizing and Exploring Data Fall 2011 Ming Li Department of Computer Science and Technology Nanjing University Exploratory data analysis tasks Examine the data, in search of structures
More information3D-MAM: 3D Morphable Appearance Model for Efficient Fine Head Pose Estimation from Still Images
3D-MAM: 3D Morphable Appearance Model for Efficient Fine Head Pose Estimation from Still Images Markus Storer, Martin Urschler and Horst Bischof Institute for Computer Graphics and Vision, Graz University
More informationCar tracking in tunnels
Czech Pattern Recognition Workshop 2000, Tomáš Svoboda (Ed.) Peršlák, Czech Republic, February 2 4, 2000 Czech Pattern Recognition Society Car tracking in tunnels Roman Pflugfelder and Horst Bischof Pattern
More informationAn R Package flare for High Dimensional Linear Regression and Precision Matrix Estimation
An R Package flare for High Dimensional Linear Regression and Precision Matrix Estimation Xingguo Li Tuo Zhao Xiaoming Yuan Han Liu Abstract This paper describes an R package named flare, which implements
More informationFactorization with Missing and Noisy Data
Factorization with Missing and Noisy Data Carme Julià, Angel Sappa, Felipe Lumbreras, Joan Serrat, and Antonio López Computer Vision Center and Computer Science Department, Universitat Autònoma de Barcelona,
More informationStatistical image models
Chapter 4 Statistical image models 4. Introduction 4.. Visual worlds Figure 4. shows images that belong to different visual worlds. The first world (fig. 4..a) is the world of white noise. It is the world
More informationFace Re-Lighting from a Single Image under Harsh Lighting Conditions
Face Re-Lighting from a Single Image under Harsh Lighting Conditions Yang Wang 1, Zicheng Liu 2, Gang Hua 3, Zhen Wen 4, Zhengyou Zhang 2, Dimitris Samaras 5 1 The Robotics Institute, Carnegie Mellon University,
More informationFeature Selection Using Principal Feature Analysis
Feature Selection Using Principal Feature Analysis Ira Cohen Qi Tian Xiang Sean Zhou Thomas S. Huang Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign Urbana,
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 informationWELCOME TO THE NAE US FRONTIERS OF ENGINEERING SYMPOSIUM 2005
WELCOME TO THE NAE US FRONTIERS OF ENGINEERING SYMPOSIUM 2005 Ongoing Challenges in Face Recognition Peter Belhumeur Columbia University New York City How are people identified? People are identified by
More information22 October, 2012 MVA ENS Cachan. Lecture 5: Introduction to generative models Iasonas Kokkinos
Machine Learning for Computer Vision 1 22 October, 2012 MVA ENS Cachan Lecture 5: Introduction to generative models Iasonas Kokkinos Iasonas.kokkinos@ecp.fr Center for Visual Computing Ecole Centrale Paris
More informationThe Use of Biplot Analysis and Euclidean Distance with Procrustes Measure for Outliers Detection
Volume-8, Issue-1 February 2018 International Journal of Engineering and Management Research Page Number: 194-200 The Use of Biplot Analysis and Euclidean Distance with Procrustes Measure for Outliers
More informationGlobal localization from a single feature correspondence
Global localization from a single feature correspondence Friedrich Fraundorfer and Horst Bischof Institute for Computer Graphics and Vision Graz University of Technology {fraunfri,bischof}@icg.tu-graz.ac.at
More informationRecognition: Face Recognition. Linda Shapiro EE/CSE 576
Recognition: Face Recognition Linda Shapiro EE/CSE 576 1 Face recognition: once you ve detected and cropped a face, try to recognize it Detection Recognition Sally 2 Face recognition: overview Typical
More informationSingle view-based 3D face reconstruction robust to self-occlusion
Lee et al. EURASIP Journal on Advances in Signal Processing 2012, 2012:176 RESEARCH Open Access Single view-based 3D face reconstruction robust to self-occlusion Youn Joo Lee 1, Sung Joo Lee 2, Kang Ryoung
More informationSparsity Preserving Canonical Correlation Analysis
Sparsity Preserving Canonical Correlation Analysis Chen Zu and Daoqiang Zhang Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China {zuchen,dqzhang}@nuaa.edu.cn
More informationMULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER
MULTIVARIATE TEXTURE DISCRIMINATION USING A PRINCIPAL GEODESIC CLASSIFIER A.Shabbir 1, 2 and G.Verdoolaege 1, 3 1 Department of Applied Physics, Ghent University, B-9000 Ghent, Belgium 2 Max Planck Institute
More informationRegion matching for omnidirectional images using virtual camera planes
Computer Vision Winter Workshop 2006, Ondřej Chum, Vojtěch Franc (eds.) Telč, Czech Republic, February 6 8 Czech Pattern Recognition Society Region matching for omnidirectional images using virtual camera
More informationStructured Light II. Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov
Structured Light II Johannes Köhler Johannes.koehler@dfki.de Thanks to Ronen Gvili, Szymon Rusinkiewicz and Maks Ovsjanikov Introduction Previous lecture: Structured Light I Active Scanning Camera/emitter
More informationCLASSIFICATION AND CHANGE DETECTION
IMAGE ANALYSIS, CLASSIFICATION AND CHANGE DETECTION IN REMOTE SENSING With Algorithms for ENVI/IDL and Python THIRD EDITION Morton J. Canty CRC Press Taylor & Francis Group Boca Raton London NewYork CRC
More informationLocal invariant features
Local invariant features Tuesday, Oct 28 Kristen Grauman UT-Austin Today Some more Pset 2 results Pset 2 returned, pick up solutions Pset 3 is posted, due 11/11 Local invariant features Detection of interest
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationDynamic Human Shape Description and Characterization
Dynamic Human Shape Description and Characterization Z. Cheng*, S. Mosher, Jeanne Smith H. Cheng, and K. Robinette Infoscitex Corporation, Dayton, Ohio, USA 711 th Human Performance Wing, Air Force Research
More informationDetermination of 3-D Image Viewpoint Using Modified Nearest Feature Line Method in Its Eigenspace Domain
Determination of 3-D Image Viewpoint Using Modified Nearest Feature Line Method in Its Eigenspace Domain LINA +, BENYAMIN KUSUMOPUTRO ++ + Faculty of Information Technology Tarumanagara University Jl.
More informationPredicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus
Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture David Eigen, Rob Fergus Presented by: Rex Ying and Charles Qi Input: A Single RGB Image Estimate
More informationCONTENTS. High-Accuracy Stereo Depth Maps Using Structured Light. Yeojin Yoon
[Paper Seminar 7] CVPR2003, Vol.1, pp.195-202 High-Accuracy Stereo Depth Maps Using Structured Light Daniel Scharstein Middlebury College Richard Szeliski Microsoft Research 2012. 05. 30. Yeojin Yoon Introduction
More informationA General Expression of the Fundamental Matrix for Both Perspective and Affine Cameras
A General Expression of the Fundamental Matrix for Both Perspective and Affine Cameras Zhengyou Zhang* ATR Human Information Processing Res. Lab. 2-2 Hikari-dai, Seika-cho, Soraku-gun Kyoto 619-02 Japan
More information[Nirgude* et al., 4(1): January, 2017] ISSN Impact Factor 2.675
GLOBAL JOURNAL OF ADVANCED ENGINEERING TECHNOLOGIES AND SCIENCES FACE RECOGNITION SYSTEM USING PRINCIPAL COMPONENT ANALYSIS & LINEAR DISCRIMINANT ANALYSIS METHOD SIMULTANEOUSLY WITH 3D MORPHABLE MODEL
More informationLinear Discriminant Analysis for 3D Face Recognition System
Linear Discriminant Analysis for 3D Face Recognition System 3.1 Introduction Face recognition and verification have been at the top of the research agenda of the computer vision community in recent times.
More informationObject. Radiance. Viewpoint v
Fisher Light-Fields for Face Recognition Across Pose and Illumination Ralph Gross, Iain Matthews, and Simon Baker The Robotics Institute, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213
More informationIn Between 3D Active Appearance Models and 3D Morphable Models
In Between 3D Active Appearance Models and 3D Morphable Models Jingu Heo and Marios Savvides Biometrics Lab, CyLab Carnegie Mellon University Pittsburgh, PA 15213 jheo@cmu.edu, msavvid@ri.cmu.edu Abstract
More informationFast 3D Mean Shift Filter for CT Images
Fast 3D Mean Shift Filter for CT Images Gustavo Fernández Domínguez, Horst Bischof, and Reinhard Beichel Institute for Computer Graphics and Vision, Graz University of Technology Inffeldgasse 16/2, A-8010,
More informationStructure from Motion. Lecture-15
Structure from Motion Lecture-15 Shape From X Recovery of 3D (shape) from one or two (2D images). Shape From X Stereo Motion Shading Photometric Stereo Texture Contours Silhouettes Defocus Applications
More informationHuman Face Shape Analysis under Spherical Harmonics Illumination Considering Self Occlusion
Human Face Shape Analysis under Spherical Harmonics Illumination Considering Self Occlusion Jasenko Zivanov Andreas Forster Sandro Schönborn Thomas Vetter jasenko.zivanov@unibas.ch forster.andreas@gmail.com
More informationA linear estimation method for 3D pose and facial animation tracking.
A linear estimation method for 3D pose and facial animation tracking. José Alonso Ybáñez Zepeda E.N.S.T. 754 Paris, France ybanez@ieee.org Franck Davoine CNRS, U.T.C. 625 Compiègne cedex, France. Franck.Davoine@hds.utc.fr
More informationRecognition of Non-symmetric Faces Using Principal Component Analysis
Recognition of Non-symmetric Faces Using Principal Component Analysis N. Krishnan Centre for Information Technology & Engineering Manonmaniam Sundaranar University, Tirunelveli-627012, India Krishnan17563@yahoo.com
More informationSIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014
SIFT: SCALE INVARIANT FEATURE TRANSFORM SURF: SPEEDED UP ROBUST FEATURES BASHAR ALSADIK EOS DEPT. TOPMAP M13 3D GEOINFORMATION FROM IMAGES 2014 SIFT SIFT: Scale Invariant Feature Transform; transform image
More informationCOMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS
COMBINED METHOD TO VISUALISE AND REDUCE DIMENSIONALITY OF THE FINANCIAL DATA SETS Toomas Kirt Supervisor: Leo Võhandu Tallinn Technical University Toomas.Kirt@mail.ee Abstract: Key words: For the visualisation
More informationTranslation Symmetry Detection: A Repetitive Pattern Analysis Approach
2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops Translation Symmetry Detection: A Repetitive Pattern Analysis Approach Yunliang Cai and George Baciu GAMA Lab, Department of Computing
More informationMobile Human Detection Systems based on Sliding Windows Approach-A Review
Mobile Human Detection Systems based on Sliding Windows Approach-A Review Seminar: Mobile Human detection systems Njieutcheu Tassi cedrique Rovile Department of Computer Engineering University of Heidelberg
More informationSimultaneous surface texture classification and illumination tilt angle prediction
Simultaneous surface texture classification and illumination tilt angle prediction X. Lladó, A. Oliver, M. Petrou, J. Freixenet, and J. Martí Computer Vision and Robotics Group - IIiA. University of Girona
More informationCHAPTER 3 PRINCIPAL COMPONENT ANALYSIS AND FISHER LINEAR DISCRIMINANT ANALYSIS
38 CHAPTER 3 PRINCIPAL COMPONENT ANALYSIS AND FISHER LINEAR DISCRIMINANT ANALYSIS 3.1 PRINCIPAL COMPONENT ANALYSIS (PCA) 3.1.1 Introduction In the previous chapter, a brief literature review on conventional
More informationLambertian model of reflectance I: shape from shading and photometric stereo. Ronen Basri Weizmann Institute of Science
Lambertian model of reflectance I: shape from shading and photometric stereo Ronen Basri Weizmann Institute of Science Variations due to lighting (and pose) Relief Dumitru Verdianu Flying Pregnant Woman
More informationSemi-Supervised PCA-based Face Recognition Using Self-Training
Semi-Supervised PCA-based Face Recognition Using Self-Training Fabio Roli and Gian Luca Marcialis Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d Armi, 09123 Cagliari, Italy
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 informationTowards the completion of assignment 1
Towards the completion of assignment 1 What to do for calibration What to do for point matching What to do for tracking What to do for GUI COMPSCI 773 Feature Point Detection Why study feature point detection?
More informationCreating Invariance To Nuisance Parameters in Face Recognition
Creating Invariance To Nuisance Parameters in Face Recognition Simon J.D. Prince and James H. Elder York University Centre for Vision Research Toronto, Ontario {prince, elder}@elderlab.yorku.ca Abstract
More informationUnsupervised learning in Vision
Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual
More informationThe flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R
Journal of Machine Learning Research 6 (205) 553-557 Submitted /2; Revised 3/4; Published 3/5 The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R Xingguo Li Department
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 informationSelf-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material
Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hz Supplemental Material Ayush Tewari 1,2 Michael Zollhöfer 1,2,3 Pablo Garrido 1,2 Florian Bernard 1,2 Hyeongwoo
More informationInternational Journal of Digital Application & Contemporary research Website: (Volume 1, Issue 8, March 2013)
Face Recognition using ICA for Biometric Security System Meenakshi A.D. Abstract An amount of current face recognition procedures use face representations originate by unsupervised statistical approaches.
More informationThe Quotient Image: Class Based Recognition and Synthesis Under Varying Illumination Conditions
The Quotient Image: Class Based Recognition and Synthesis Under Varying Illumination Conditions Tammy Riklin-Raviv and Amnon Shashua Institute of Computer Science, The Hebrew University, Jerusalem 91904,
More informationStereo Matching.
Stereo Matching Stereo Vision [1] Reduction of Searching by Epipolar Constraint [1] Photometric Constraint [1] Same world point has same intensity in both images. True for Lambertian surfaces A Lambertian
More informationEstimating basis functions for spectral sensitivity of digital cameras
(MIRU2009) 2009 7 Estimating basis functions for spectral sensitivity of digital cameras Abstract Hongxun ZHAO, Rei KAWAKAMI, Robby T.TAN, and Katsushi IKEUCHI Institute of Industrial Science, The University
More informationFace Recognition At-a-Distance Based on Sparse-Stereo Reconstruction
Face Recognition At-a-Distance Based on Sparse-Stereo Reconstruction Ham Rara, Shireen Elhabian, Asem Ali University of Louisville Louisville, KY {hmrara01,syelha01,amali003}@louisville.edu Mike Miller,
More informationModelling imprints of pharmaceutical tablets for imprint quality visual inspection
Modelling imprints of pharmaceutical tablets for imprint quality visual inspection Miha Možina 1, Dejan Tomaževič 1,2, Franjo Pernuš 1,2 and Boštjan Likar 1,2 1 Sensum, Computer Vision Systems Tehnološki
More informationIllumination invariant face recognition and impostor rejection using different MINACE filter algorithms
Illumination invariant face recognition and impostor rejection using different MINACE filter algorithms Rohit Patnaik and David Casasent Dept. of Electrical and Computer Engineering, Carnegie Mellon University,
More informationRecovering illumination and texture using ratio images
Recovering illumination and texture using ratio images Alejandro Troccoli atroccol@cscolumbiaedu Peter K Allen allen@cscolumbiaedu Department of Computer Science Columbia University, New York, NY Abstract
More informationGeneralized Principal Component Analysis CVPR 2007
Generalized Principal Component Analysis Tutorial @ CVPR 2007 Yi Ma ECE Department University of Illinois Urbana Champaign René Vidal Center for Imaging Science Institute for Computational Medicine Johns
More information