Multi-scale Sparse Representation for Robust Face Recognition (original) (raw)
Related papers
Robust Coarse-to-Fine Sparse Representation for Face Recognition
Lecture Notes in Computer Science, 2013
Recently Sparse Representation-based classification (SRC) has been successfully applied to pattern classification. In this paper, we present a robust Coarse-to-Fine Sparse Representation (CFSR) for face recognition. In the coarse coding phase, the test sample is represented as a linear combination of all the training samples. In the last phase, a number of "nearest neighbors" is determined to represent the test sample to perform classification. CFSR produces the sparseness through the coarse phase, and exploits the local data structure to perform classification in the fine phase. Moreover, this method can make a better classification decision by determining an individual dictionary for each test sample. Extensive experiments on benchmark face databases show that our method has competitive performance in face recognition compared with other state-of-the-art methods.
Face recognition by sparse representation
Compressed Sensing
In this chapter, we present a comprehensive framework for tackling the classical problem of face recognition, based on theory and algorithms from sparse representation. Despite intense interest in the past several decades, traditional pattern recognition theory still stops short of providing a satisfactory solution capable of recognizing human faces in the presence of real-world nuisances such as occlusion and variabilities in pose and illumination. Our new approach, called sparse representation-based classification (SRC), is motivated by a very natural notion of sparsity, namely, one should always try to explain a query image using a small number of training images from a single subject category. This sparse representation is sought via 1-minimization. We show how this core idea can be generalized and extended to account for various physical variabilities encountered in face recognition. The end result of our investigation is a full-fledged practical system aimed at security and access control applications. The system is capable of accurately recognizing subjects out of a database of several hundred subjects with state-of-the-art accuracy.
Sparse representation for face recognition: A review paper
IET Image Processing
With the increasing use of surveillance cameras, face recognition is being studied by many researchers for security purposes. Although high accuracy has been achieved for frontal faces, the existing methods have shown poor performance for occluded and corrupt images. Recently, sparse representation based classification (SRC) has shown the state-ofthe-art result in face recognition on corrupt and occluded face images. Several researchers have developed extended SRC methods in the last decade. This paper mainly focuses on SRC and its extended methods of face recognition. SRC methods have been compared on the basis of five issues of face recognition such as linear variation, non-linear variation, undersampled, pose variation, and low resolution. Detailed analysis of SRC methods for issues of face recognition have been discussed based on experimental results and execution time. Finally, the limitation of SRC methods have been listed to help the researchers to extend the work of existing methods to resolve the unsolved issues. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
Sparse Representation and Face Recognition
International Journal of Image, Graphics and Signal Processing, 2018
Now a days application of sparse representation are widely spreading in many fields such as face recognition. For this usage, defining a dictionary and choosing a proper recovery algorithm plays an important role for the method accuracy. In this paper, two type of dictionaries based on input face images, the method named SRC, and input extracted features, the method named MKD-SRC, are constructed. SRC fails for partial face recognition whereas MKD-SRC overcomes the problem. Three extension of MKD-SRC are introduced and their performance for comparison are presented. For recommending proper recovery algorithm, in this paper, we focus on three greedy algorithms, called MP, OMP, CoSaMP and another called Homotopy. Three standard data sets named AR, Extended Yale-B and Essex University are used to asses which recovery algorithm has an efficient response for proposed methods. The preferred recovery algorithm was chosen based on achieved accuracy and run time.
Sparse Representation Based Face Recognition Using Weighted Regions
Face recognition is a challenging research topic, especially when the training (gallery) and recognition (probe) images are acquired using different cameras under varying conditions. Even a small noise or occlusion in the images can compromise the accuracy of recognition. Lately, sparse encoding based classification algorithms gave promising results for such uncontrollable scenarios. In this paper, we introduce a novel methodology by modeling the sparse encoding with weighted patches to increase the robustness of face recognition even further. In the training phase, we define a mask (i.e., weight matrix) using a sparse representation selecting the facial regions, and in the recognition phase, we perform comparison on selected facial regions. The algorithm was evaluated both quantitatively and qualitatively using two comprehensive surveillance facial image databases, i.e., SCface andMFPV, with the results clearly superior to common state-of-the-art methodologies in different scenarios.
ROBUST FACE RECOGNITION FRAMEWORK WITH BLOCK WEIGHTED SPARSE REPRESENTATION BASED CLASSIFICATION
The sparse representation based classification method can be divided into two categories: holistic approaches and local feature-based approaches. In spite of the significant success in face recognition, improvements on higher robustness or lower computational complexity are still necessary for its real application. Thus, we first propose a novel Block Weighted Sparse Representation based Classification (BW-SRC) method based on the maximum likelihood model. Then, to ensure the accuracy of BW-SRC, we conduct a pre-alignment process by utilizing the locations of local feature points (in this article, we use SIFT keypoints). Combining the pre-alignment process and BW-SRC, we establish a novel framework for robust face recognition, which is more effective and more robust than the state-of-the-art methods in practical scenarios. Finally, by conducting experiments on AR and Yale databases, the performance of our proposed method and framework is demonstrated and compared with global SRC and blocked SRC. The proposed framework is proven as low-computation, alignment-free and robustness to rotation, illumination and disguise, and more appropriate for practical scenarios.
Sparse Representation Based Face Recognition with Limited Labeled Samples
2013 2nd IAPR Asian Conference on Pattern Recognition, 2013
Sparse representations have emerged as a powerful approach for encoding images in a large class of machine recognition problems including face recognition. These methods rely on the use of an over-complete basis set for representing an image. This often assumes the availability of a large number of labeled training images, especially for high dimensional data. In many practical problems, the number of labeled training samples are very limited leading to significant degradations in classification performance. To address the problem of lack of training samples, we propose a semi-supervised algorithm that labels the unlabeled samples through a multi-stage label propagation combined with sparse representation. In this representation, each image is decomposed as a linear combination of its nearest basis images, which has the advantage of both locality and sparsity. Extensive experiments on publicly available face databases show that the results are significantly better compared to state-of-theart face recognition methods in semi-supervised setting and are on par with fully supervised techniques.
Significance of dictionary for sparse coding based face recognition
International Conference on Biometrics, 2012
Sparse representation based classification (SRC) successfully addresses the problem of face recognition under various illumination and occlusion conditions, if sufficient training images are given. This paper discusses the significance of dictionary in sparse coding based face recognition. We primarily address the problem of sufficiencyoftraining data in various illumination conditions. The dictionary is generated using alower dimensional representation of image, which emphasizes the subject specific unique information of the face image. This representation is called weighted decomposition (WD) face image, because it attempts to give more weightage to unique information of face image. The effect of illumination in computation of WD face image is reduced using edginess based representation of image, which is derivedu sing one-dimensional (1-D) processing of image. 1-D processing provides multiple partial evidences, which are combined to enhance the face recognition performance. The experimental results suggest that the proposed approach addresses the issue of sufficiency of training data efficiently.
Locality-constrained group sparse representation for robust face recognition
2011 18th IEEE International Conference on Image Processing, 2011
This paper presents a novel sparse representation for robust face recognition. We advance both group sparsity and data locality and formulate a unified optimization framework, which produces a locality and group sensitive sparse representation (LGSR) for improved recognition. Empirical results confirm that our LGSR not only outperforms state-of-the-art sparse coding based image classification methods, our approach is robust to variations such as lighting, pose, and facial details (glasses or not), which are typically seen in real-world face recognition problems.
2011 IEEE International Conference on Multimedia and Expo, 2011
Recently, local binary patterns (LBP) based descriptors and sparse representation based classification (SRC) become both eminent techniques in face recognition. Preliminary techniques of combining LBP and SRC have been proposed in the literature. However, the state-of-art method suffers from the "curse of dimensionality" for real world scenarios. In this paper, a novel face recognition algorithm of combining LBP with SRC is proposed; in which the dimensionality problem is resolved by divide-and-conquer and the discriminative power is strengthen via its pyramid architecture. The proposed face recognition method is evaluated on AR Face Database and yields very impressive results.