Mining Discriminative Components With Low-Rank and Sparsity Constraints for Face Recognition Qiang Zhang, Baoxin Li Computer Science and Engineering Arizona.

Slides:



Advertisements
Similar presentations
Active Appearance Models
Advertisements

Face Alignment by Explicit Shape Regression
Feature Selection as Relevant Information Encoding Naftali Tishby School of Computer Science and Engineering The Hebrew University, Jerusalem, Israel NIPS.
Principal Component Analysis Based on L1-Norm Maximization Nojun Kwak IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008.
Data Mining Feature Selection. Data reduction: Obtain a reduced representation of the data set that is much smaller in volume but yet produces the same.
A CTION R ECOGNITION FROM V IDEO U SING F EATURE C OVARIANCE M ATRICES Kai Guo, Prakash Ishwar, Senior Member, IEEE, and Janusz Konrad, Fellow, IEEE.
Sparse Modeling for Finding Representative Objects Ehsan Elhamifar Guillermo Sapiro Ren´e Vidal Johns Hopkins University University of Minnesota Johns.
Structured Sparse Principal Component Analysis Reading Group Presenter: Peng Zhang Cognitive Radio Institute Friday, October 01, 2010 Authors: Rodolphe.
Proposed concepts illustrated well on sets of face images extracted from video: Face texture and surface are smooth, constraining them to a manifold Recognition.
Image Congealing (batch/multiple) image (alignment/registration) Advanced Topics in Computer Vision (048921) Boris Kimelman.
Face Alignment with Part-Based Modeling
Mixture of trees model: Face Detection, Pose Estimation and Landmark Localization Presenter: Zhang Li.
COMPUTER AIDED DIAGNOSIS: FEATURE SELECTION Prof. Yasser Mostafa Kadah –
Proportion Priors for Image Sequence Segmentation Claudia Nieuwenhuis, etc. ICCV 2013 Oral.
More MR Fingerprinting
Bayesian Robust Principal Component Analysis Presenter: Raghu Ranganathan ECE / CMR Tennessee Technological University January 21, 2011 Reading Group (Xinghao.
Robust Network Compressive Sensing Lili Qiu UT Austin NSF Workshop Nov. 12, 2014.
Face Recognition Under Varying Illumination Erald VUÇINI Vienna University of Technology Muhittin GÖKMEN Istanbul Technical University Eduard GRÖLLER Vienna.
Principal Component Analysis
A Study of Approaches for Object Recognition
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
Real-time Combined 2D+3D Active Appearance Models Jing Xiao, Simon Baker,Iain Matthew, and Takeo Kanade CVPR 2004 Presented by Pat Chan 23/11/2004.
Automatic Pose Estimation of 3D Facial Models Yi Sun and Lijun Yin Department of Computer Science State University of New York at Binghamton Binghamton,
Face Recognition Based on 3D Shape Estimation
Feature Extraction for Outlier Detection in High- Dimensional Spaces Hoang Vu Nguyen Vivekanand Gopalkrishnan.
FACE RECOGNITION, EXPERIMENTS WITH RANDOM PROJECTION
Sufficient Dimensionality Reduction with Irrelevance Statistics Amir Globerson 1 Gal Chechik 2 Naftali Tishby 1 1 Center for Neural Computation and School.
Joint Image Clustering and Labeling by Matrix Factorization
Jinhui Tang †, Shuicheng Yan †, Richang Hong †, Guo-Jun Qi ‡, Tat-Seng Chua † † National University of Singapore ‡ University of Illinois at Urbana-Champaign.
AdvisorStudent Dr. Jia Li Shaojun Liu Dept. of Computer Science and Engineering, Oakland University 3D Shape Classification Using Conformal Mapping In.
Face Recognition and Feature Subspaces
Gwangju Institute of Science and Technology Intelligent Design and Graphics Laboratory Multi-scale tensor voting for feature extraction from unstructured.
DeepFont: Large-Scale Real-World Font Recognition from Images
1 Recognition by Appearance Appearance-based recognition is a competing paradigm to features and alignment. No features are extracted! Images are represented.
Combined Central and Subspace Clustering for Computer Vision Applications Le Lu 1 René Vidal 2 1 Computer Science Department, Johns Hopkins University,
An Information Fusion Approach for Multiview Feature Tracking Esra Ataer-Cansizoglu and Margrit Betke ) Image and.
Filter + Support Vector Machine for NIPS 2003 Challenge Jiwen Li University of Zurich Department of Informatics The NIPS 2003 challenge was organized to.
Pairwise Linear Regression: An Efficient and Fast Multi-view Facial Expression Recognition By: Anusha Reddy Tokala.
A Novel Local Patch Framework for Fixing Supervised Learning Models Yilei Wang 1, Bingzheng Wei 2, Jun Yan 2, Yang Hu 2, Zhi-Hong Deng 1, Zheng Chen 2.
Mingyang Zhu, Huaijiang Sun, Zhigang Deng Quaternion Space Sparse Decomposition for Motion Compression and Retrieval SCA 2012.
Multiple Instance Learning for Sparse Positive Bags Razvan C. Bunescu Machine Learning Group Department of Computer Sciences University of Texas at Austin.
CHAPTER 1: Introduction. 2 Why “Learn”? Machine learning is programming computers to optimize a performance criterion using example data or past experience.
School of Computer Science 1 Information Extraction with HMM Structures Learned by Stochastic Optimization Dayne Freitag and Andrew McCallum Presented.
earthobs.nr.no Retraining maximum likelihood classifiers using a low-rank model Arnt-Børre Salberg Norwegian Computing Center Oslo, Norway IGARSS.
Large-Scale Matrix Factorization with Missing Data under Additional Constraints Kaushik Mitra University of Maryland, College Park, MD Sameer Sheoreyy.
Zhilin Zhang, Bhaskar D. Rao University of California, San Diego March 28,
Reconstruction-free Inference on Compressive Measurements Suhas Lohit, Kuldeep Kulkarni, Pavan Turaga, Jian Wang, Aswin Sankaranarayanan Arizona State.
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin, South Korea Copyright © solarlits.com.
2D-LDA: A statistical linear discriminant analysis for image matrix
Ultra-high dimensional feature selection Yun Li
Multi-label Prediction via Sparse Infinite CCA Piyush Rai and Hal Daume III NIPS 2009 Presented by Lingbo Li ECE, Duke University July 16th, 2010 Note:
WCPM 1 Chang-Tsun Li Department of Computer Science University of Warwick UK Image Clustering Based on Camera Fingerprints.
Facets: Fast Comprehensive Mining of Coevolving High-order Time Series Hanghang TongPing JiYongjie CaiWei FanQing He Joint Work by Presenter:Wei Fan.
Martina Uray Heinz Mayer Joanneum Research Graz Institute of Digital Image Processing Horst Bischof Graz University of Technology Institute for Computer.
Deformation Modeling for Robust 3D Face Matching Xioguang Lu and Anil K. Jain Dept. of Computer Science & Engineering Michigan State University.
Processing visual information for Computer Vision
Deeply learned face representations are sparse, selective, and robust
Guillaume-Alexandre Bilodeau
DeepFont: Identify Your Font from An Image
Supervised Time Series Pattern Discovery through Local Importance
Face Recognition and Feature Subspaces
Fast Preprocessing for Robust Face Sketch Synthesis
Final Year Project Presentation --- Magic Paint Face
Unsupervised Face Alignment by Robust Nonrigid Mapping
Outline Multilinear Analysis
Domingo Mery Department of Computer Science
Introduction to Sensor Interpretation
Learning Incoherent Sparse and Low-Rank Patterns from Multiple Tasks
Domingo Mery Department of Computer Science
Presentation transcript:

Mining Discriminative Components With Low-Rank and Sparsity Constraints for Face Recognition Qiang Zhang, Baoxin Li Computer Science and Engineering Arizona State University Tempe, AZ, qzhang53,

Problem Description In many applications, we may acquire multiple copies of signals from the same source (an ensemble of signals); Signals in ensemble may be very similar (sharing a common source), but may also have very distinctive differences (e.g., very different acquisition conditions) plus other unique but small variations (e.g., sensor noise).

Examples Common sources

Examples Different acquisition conditions

Examples Sensor noises

Examples Signals in ensemble

Signals in Ensemble The decomposition of the signal has several benefits: – Obtaining better compression rate. E.g., distributed compressed sensing [Duarte], joint sparsity model [Duarte 2005]; – Extract more relevant features. E.g., A compressive sensing approach for expression- invariant face recognition [Nagesh 2009];

Example: Face Images Given face images of same subjects

Example: Face Images Can we identify a “clean” image for them?

Example: Face Images And their illumination conditions?

Example: Face Image Set Face image can be represented as a variable parameterized by subject and imaging condition, e.g., illumination, expression etc.; The images of same subject would share a common component; The innovation components should contribute to the imaging conditions. – Innovation component may not be necessary sparse, e.g., the one due to illumination variations.

Example: Decomposing Face Images AR dataset: expression variation as a sparse component. X C E

Example: Decomposing Face Images X C A

Proposed Model

Proposed Model Cont’d

Examples X = C + A + E

Solving the Decomposition

Comparison with Other Models

Decomposition Algorithms

Decomposition Algorithms Cont’d

Parameters Selection

Convergence Property With proper selection of parameters, the proposed algorithm will converge to the optimal solution. In experiment, the algorithm converges within 100 iterations.

Examples: Decomposition Process Show examples for how the algorithm converges.

Experiment We use three experiments to evaluate the proposed model and algorithm: – Decomposing the synthetic images; – Decomposing the images from extended YaleB dataset; – Applying decomposed component to classification tasks;

Decomposing the synthetic images We create training images by mixing the images with low-rank background images. In addition, we add some sparse- supported noise.

Decomposing the synthetic images The decomposition result. From top to bottom: common components, low- rank components and sparse components.

Decomposition: Robustness over Missing Training Instances We randomly remove 20% training images and test the robustness of decomposition algorithm. From top to bottom: training images and common component, low-rank component.

Decomposing Extended YaleB Dataset We use all 2432 images of extended YaleB dataset, which includes 38 subjects and 64 illumination conditions; – Common components capture information unique to certain subjects; – Low rank components capture the illumination conditions of the images; – Sparse components capture the sparse-supported noises and shadows;

Decomposing Extended YaleB Dataset Left: common components; Right: the low-rank components.

Applying Decomposed Component to Face Recognition

Face Recognition: Subspaces Reconstruct image with common component of Subject 1 and low-rank components: (a) coefficient of the reconstruction, (b) the input image, and (c) the reconstructed image. Subject 1Subject 2 Reconstruction with incorrect common components

Face Recognition: Measuring the Distance of Subspaces

Face Recognition: Experiment We test the algorithm on extended YaleB dataset and Multi-PIE dataset; – Randomly split the set into training sets and testing sets; – To test its robustness over missing training instances, we randomly remove some of the training instances and keep “# train per subject” training instances for each subject; – The performance is compared with SRC, Volterraface and SUN.

Face Recognition: Extended YaleB Dataset #train per subject Proposed 99.78±0.24%99.54±0.04%99.18±0.14%95.15±1.03% SRC 96.48±0.44%95.29±0.52%91.90±0.94%78.65±1.81% Volterrafaces 99.95±0.06%99.80±0.26%99.48±0.49%90.22±11.84% SUN 89.61±1.85%87.64±2.80%76.91±3.71%60.17±2.09% #train per subject Proposed 99.56±0.00%99.33±0.23%98.32±0.03%80.03±2.17% SRC 89.14±0.00%87.88±0.44%81.02±0.13%58.54±1.26% Volterrafaces 99.25±0.34%99.17±0.39%96.27±4.03%91.03±2.43% SUN 79.22±0.00%76.75±0.00%68.86±0.00%51.60±0.00% Extended YaleB dataset includes 64 illumination conditions and 38 subjects.

Face Recognition: Multi-PIE Dataset #train per image Proposed 100±0.00% 99.65±0.37%97.49±0.21% SRC 99.88±0.07% 99.73±0.14%97.73±0.54% Volterrafaces 100±0.00% 95.83±4.16% SUN 100%99.84±0.11%99.45±0.43%95.75±0.49% #train per image Proposed 100±0.00% %99.17±0.15%94.70±0.20% SRC 99.91±0.16%98.89±1.74%96.90±3.73%87.18±1.78% Volterrafaces 100±0.00% 99.54±0.31%94.30±4.72% SUN 100±0.00%99.84±0.05%98.53±0.29%88.75±4.72% We test the performances on face images of frontal poses (P27), which include 68 subjects and 45 illumination variations.

Face Recognition: Robustness over Poses Variations we use all the images from 5 near frontal poses (C05, C07, C09, C27, C29), which includes153 conditions for each subject. We randomly pick M=40 illumination conditions for training and the remaining for testing. #train per subject Proposed 99.98±0.03%99.92±0.06%99.24±0.06%90.95±0.70% SRC 99.98±0.03%99.45±0.03%96.79±0.28%86.98±0.16% Volterrafaces 99.60±0.22%98.37±0.47%97.63±0.28%89.72±1.45% SUN 99.93±0.05%99.38±0.14%97.89±0.30%88.29±0.02%

Variation Recognition

We test the proposed algorithm on AR dataset, which contains 100 subjects and 2 sessions, where each session 13 variations. We use the first session for training and second session for testing. We show the confusion matrix, which presents the result in percentages. variations

Conclusions We proposed a novel decomposition of a set of face images of multiple subjects, each with multiple images; It facilitates explicit modeling of typical challenges in face recognition, such as illumination conditions and large occlusion; For future work, we plan to expand the current algorithm by incorporating another step that attempts to estimate a mapping matrix for assigning a condition label to each image, during the optimization iteration.