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.

/pdf/robust-face-recognition-via-sparse-representation-4bfqv6y74o.pdf

Robust Face Recognition via Sparse Representation

As one of the most successful applications of image analysis and understanding, face recognition has recently received significant attention, especially during the past several years. At least two reasons account for this trend: the first is the wide range of commercial and law enforcement applications, and the second is the availability of feasible technologies after 30 years of research. Even though current machine recognition systems have reached a certain level of maturity, their success is limited by the conditions imposed by many real applications. For example, recognition of face images acquired in an outdoor environment with changes in illumination and/or pose remains a largely unsolved problem. In other words, current systems are still far away from the capability of the human perception system.This paper provides an up-to-date critical survey of still- and video-based face recognition research. There are two underlying motivations for us to write this survey paper: the first is to provide an up-to-date review of the existing literature, and the second is to offer some insights into the studies of machine recognition of faces. To provide a comprehensive survey, we not only categorize existing recognition techniques but also present detailed descriptions of representative methods within each category. In addition, relevant topics such as psychophysical studies, system evaluation, and issues of illumination and pose variation are covered.

Face recognition: A literature survey

/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possible illumination conditions, is a convex cone in the space of images. Using a small number of training images of each face taken with different lighting directions, the shape and albedo of the face can be reconstructed. In turn, this reconstruction serves as a generative model that can be used to render (or synthesize) images of the face under novel poses and illumination conditions. The pose space is then sampled and, for each pose, the corresponding illumination cone is approximated by a low-dimensional linear subspace whose basis vectors are estimated using the generative model. Our recognition algorithm assigns to a test image the identity of the closest approximated illumination cone. Test results show that the method performs almost without error, except on the most extreme lighting directions.

From few to many: illumination cone models for face recognition under variable lighting and pose

We present a new method that we call generalized discriminant analysis (GDA) to deal with nonlinear discriminant analysis using kernel function operator. The underlying theory is close to the support vector machines (SVM) insofar as the GDA method provides a mapping of the input vectors into high-dimensional feature space. In the transformed space, linear properties make it easy to extend and generalize the classical linear discriminant analysis (LDA) to nonlinear discriminant analysis. The formulation is expressed as an eigenvalue problem resolution. Using a different kernel, one can cover a wide class of nonlinearities. For both simulated data and alternate kernels, we give classification results, as well as the shape of the decision function. The results are confirmed using real data to perform seed classification.

/pdf/generalized-discriminant-analysis-using-a-kernel-approach-2p31nwoukr.pdf

Generalized Discriminant Analysis Using a Kernel Approach

This paper presents some new results on face recognition using Radial Basis Function (RBF) Neural Networks. First, face features are extracted by discriminant eigenfeatures. Then, a general approach, which determines the initial structure and parameters of RBF neural networks, is presented. A hybrid learning algorithm is used to dramatically decrease the dimension of the search space in the gradient method, which is crucial on optimization of high-dimension problem. Experimental results conducted on the ORL database image of Cambridge University show that the error rate is 1.5% which is a tremendous improvement over the best existing result of 3.83%.

Face recognition using radial basis function (RBF) neural networks

The performance of many state-of-the-art face recognition (FR) methods deteriorates rapidly when large databases are considered. We propose a novel clustering method based on a linear discriminant analysis methodology which deals with the problem of FR on a large-scale database. Contrary to traditional clustering methods such as K-means, which are based on certain "similarity criteria", the proposed method uses a novel "separability criterion" to partition a training set from the large database into a set of K smaller and simpler subsets or maximal-separability clusters (MSCs). Based on these MSCs, a novel two-stage hierarchical classification framework is proposed. Under the framework, the complex FR problem on a large database is decomposed into a set of simpler ones, where traditional methods can be successfully applied. Experiments with a database containing 1654 face images of 157 subjects indicate that the error rate performance of a traditional method under the proposed framework can be greatly improved without significantly increasing computational complexity.

/pdf/boosting-face-recognition-on-a-large-scale-database-5akciy2chp.pdf

Boosting face recognition on a large-scale database

A new face recognition system is introduced and analyzed in this paper. The system utilizes a novel statistical pattern recognition method to optimize the feature selection process. The optimized feature set feeds a classification module, which is based on the modified /spl nu/-support vector machine approach (/spl nu/-SVM). The optimized feature set reduces the burden of the subsequent /spl nu/-SVM classifier and improves its learning speed and classification accuracy. The paper includes simulation studies and comparative evaluation with several existing systems on the ORL face database. Results indicate that the proposed system has excellent performance achieving the lowest error rate reported to date for the ORL face database using only a very small set of features.

/pdf/face-recognition-using-feature-optimization-and-spl-nu-bizvgcsf1r.pdf

Face recognition using feature optimization and /spl nu/-support vector learning

The paper presents a study on color to gray image conversion from a novel point of view: face detection. To the best knowledge of the authors, research in such a specific topic has not been conducted before. Our work reveals that the standard NTSC conversion is not optimal for face detection tasks, although it may be the best for use to display pictures on monochrome televisions. It is further found experimentally with two AdaBoost-based face detection systems that the detect rates may vary up to 10% by simply changing the parameters of the RGB to Gray conversion. On the other hand, the change has little influence on the false positive rates. Compared to the standard NTSC conversion, the detect rate with the best found parameter setting is 2.85% and 3.58% higher for the two evaluated face detection systems. Promisingly, the work suggests a new solution to the color to gray conversion. It could be extremely easy to be incorporated into most existing face detection systems for accuracy improvement without introduction of any extra cost in computational complexity.

On conversion from color to gray-scale images for face detection

In this paper, we address the false rejection problem due to the small solid state sensor area available for fingerprint image capture. We propose a minutiae data synthesis approach to circumvent this problem. The main advantages of this approach over the existing image mosaicing approach include low memory storage requirements and low computational complexity. Moreover, the possible matching search overhead due to data redundancy can be reduced. Extensive experiments are conducted to determine the best transformation suitable for minutiae alignment. Among the three transformations presented, affine transformation is found to be most suited for minutiae alignment. We demonstrate the idea of synthesis with an example using physical fingerprint images. The proposed synthesis system is also shown to reduce the number of false rejects caused by the use of different fingerprint regions for matching.

Juwei Lu

Papers

Face recognition using radial basis function (RBF) neural networks

Boosting face recognition on a large-scale database

Face recognition using feature optimization and /spl nu/-support vector learning

On conversion from color to gray-scale images for face detection

Minutiae data synthesis for fingerprint identification applications