Robust Face Recognition via Sparse Representation
TLDR
This work considers the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise, and proposes a general classification algorithm for (image-based) object recognition based on a sparse representation computed by C1-minimization.Abstract:
We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by C1-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.read more
Citations
More filters
Journal ArticleDOI
Latent Space Sparse and Low-Rank Subspace Clustering
TL;DR: Methods that learn the projection of data and find the sparse and/or low-rank coefficients in the low-dimensional latent space and apply spectral clustering to a similarity matrix built from these representations are described.
Proceedings ArticleDOI
Dynamic captioning: video accessibility enhancement for hearing impairment
TL;DR: A video accessibility enhancement scheme with a Dynamic Captioning approach, which explores a rich set of technologies including face detection and recognition, visual saliency analysis, text-speech alignment, etc, to help hearing impaired audience better recognize the speaking characters.
Journal ArticleDOI
Constructing a Nonnegative Low-Rank and Sparse Graph With Data-Adaptive Features
TL;DR: Zhang et al. as mentioned in this paper proposed a nonnegative low-rank and sparse (NNRS) graph for the given data representation, where the weights of edges in the graph are obtained by seeking a non-negative low rank and sparse reconstruction coefficients matrix that represents each data sample as a linear combination of others.
Journal ArticleDOI
Data-Driven Sparse Sensor Placement for Reconstruction
TL;DR: In this paper, the singular value decomposition and QR pivoting are used to find sparse point sensors for signal reconstruction in high-dimensional high-bandwidth systems, and a tailored library of features extracted from training data is used.
Journal ArticleDOI
The State of the Art Ten Years After a State of the Art: Future Research in Music Information Retrieval
TL;DR: A case study of all published research using the most-used benchmark dataset in MGR during the past decade shows that none of the evaluations in these many works is valid to produce conclusions with respect to recognizing genre, i.e. that a system is using criteria relevant for recognizing genre.
References
More filters
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Book
The Nature of Statistical Learning Theory
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
Book
Convex Optimization
Stephen Boyd,Lieven Vandenberghe +1 more
TL;DR: In this article, the focus is on recognizing convex optimization problems and then finding the most appropriate technique for solving them, and a comprehensive introduction to the subject is given. But the focus of this book is not on the optimization problem itself, but on the problem of finding the appropriate technique to solve it.
Journal ArticleDOI
Eigenfaces for recognition
Matthew Turk,Alex Pentland +1 more
TL;DR: A near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals, and that is easy to implement using a neural network architecture.
Journal ArticleDOI
Eigenfaces vs. Fisherfaces: recognition using class specific linear projection
TL;DR: A face recognition algorithm which is insensitive to large variation in lighting direction and facial expression is developed, based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variations in lighting and facial expressions.