... 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,

Images containing faces are essential to intelligent vision-based human computer interaction, and research efforts in face processing include face recognition, face tracking, pose estimation, and expression recognition. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions which contain a face regardless of its three-dimensional position, orientation, and the lighting conditions. Such a problem is challenging because faces are nonrigid and have a high degree of variability in size, shape, color, and texture. Numerous techniques have been developed to detect faces in a single image, and the purpose of this paper is to categorize and evaluate these algorithms. We also discuss relevant issues such as data collection, evaluation metrics, and benchmarking. After analyzing these algorithms and identifying their limitations, we conclude with several promising directions for future research.

Faces represent complex, multidimensional, meaningful visual stimuli and developing a computational model for face recognition is difficult [43]. We present a hybrid neural network solution which compares favorably with other methods. The system combines local image sampling, a self-organizing map neural network, and a convolutional neural network. The self-organizing map provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides for partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the self-organizing map, and a multi-layer perceptron in place of the convolutional netwo...

A novel learning approach for human face detection using a network of linear units is presented. The SNoW learning architecture is a sparse network of linear functions over a pre-defined or incrementally learned feature space and is specifically tailored for learning in the presence of a very large number of features. A wide range of face images in different poses, with different expressions and under different lighting conditions are used as a training set to capture the variations of human faces. Experimental results on commonly used benchmark data sets of a wide range of face images show that the SNoW-based approach outperforms methods that use neural networks, Bayesian methods, support vector machines and others. Furthermore, learning and evaluation using the SNoW-based method are significantly more efficient than with other methods.

In this letter we propose a facGE feature extracA-W tecracA whic utilizes polynomial clynomial derived from 2D DiscHWE Cosine Transform (DCT)cT)2:EEB8 obtained from horizontally and vertic:2) neighbouringblochb Fac authenticing2 results on the VidTIMIT database suggest that the proposed feature set is superior (in terms of robustness to illuminationclumin anddiscAB:2)AH8# ability) to features extracs2 using four popular methods: Princs:2 Component Analysis (PCA), PCA with histogram equalizationpre-procion2AB 2D DCT and 2D Gabor wavelets; the results also suggest that histogram equalizationpre-procion2A inc-proc the error rate and o#ers no help against illuminationcuminat Moreover, the proposed feature set is over 80 times faster toc2GWW# than features based on Gabor wavelets. Further experiments on the Weizmann database also show that the proposed approac is more robust than 2D Gabor wavelets and 2D DCT coefficients.

Support Vector Machines (SVMs) have been recently proposed as a new technique for pattern recognition. In this paper, the SVMs with a binary tree recognition strategy are used to tackle the face recognition problem. We illustrate the potential of SVMs on the Cambridge ORL face database, which consists of 400 images of 40 individuals, containing quite a high degree of variability in expression, pose, and facial details. We also present the recognition experiment on a larger face database of 1079 images of 137 individuals. We compare the SVMs based recognition with the standard eigenface approach using the Nearest Center Classification (NCC) criterion. Keywords: Face recognition, support vector machines, optimal separating hyperplane, binary tree, eigenface, principal component analysis. 1 Introduction Face recognition technology can be used in wide range of applications such as identity authentication, access control, and surveillance. Interests and research activities in face recogn...

In this paper we describe an embedded Hidden Markov Model (HMM)-based approach for face detection and recognition that uses an efficient set of observation vectors obtained from the 2D-DCT coefficients. The embedded HMM can model the two dimensional data better than the onedimensional HMM and is computationally less complex than the two-dimensional HMM. This model is appropriate for face images since it exploits an important facial characteristic: frontal faces preserve the same structure of "super states" from top to bottom, and also the same left-to-right structure of "states" inside each of these "super states". 1. INTRODUCTION A face identification system can be used to detect the location of faces from different scenes and recognize them as one of the faces stored in a database. The system must operate under a variety of conditions, such as varying illuminations and backgrounds, and it must be able to handle non-frontal facial images of males and females of different ages and ra...

Hidden Markov Models (HMM) have been successfully used for speech and action recognition where the data that is to be modeled is one-dimensional. Although attempts to use these one-dimensional HMMs for face recognition have been moderately successful, images are two-dimensional (2-D). Since 2-D HMM's are too complex for real-time face recognition, in this paper we present a new approach for face recognition using an embedded HMM and compare this new approach to the eigenface method for face recognition, and to other HMM-based methods. Specifically, an embedded HMM has equal or better performance than previous methods, with reduced computational complexity. 1. INTRODUCTION Face recognition from still images and video sequences is emerging as an active research area with numerous commercial and law enforcement applications. Face recognition systems can be used to allow access to an ATM machine or a computer, to control the entry of people into restricted areas, and to recognize people ...

It has been shown previously that systems based on local features and relatively complex generative models, namely 1D Hidden Markov Models (HMMs) and pseudo-2D HMMs, are suitable for face recognition (here we mean both identification and verification). Recently a simpler generative model, namely the Gaussian Mixture Model (GMM), was also shown to perform well. In this paper we first propose to increase the performance of the GMM approach (without sacrificing its simplicity) through the use of local features with embedded positional information; we show that the performance obtained is comparable to 1D HMMs. Secondly, we evaluate different training techniques for both GMM and HMM based systems. We show that the traditionally used Maximum Likelihood (ML) training approach has problems estimating robust model parameters when there is only a few training images available; we propose to tackle this problem through the use of Maximum a Posteriori (MAP) training, where the lack of data problem can be effectively circumvented; we show that models estimated with MAP are significantly more robust and are able to generalize to adverse conditions present in the BANCA database.

A new approach combining a simple local representation method with a k-nearest neighbours-based direct voting scheme is proposed for face recognition. This approach rises computational problems that we efectively solve through an approximate fast k-nearest neighbours search technique. Experimental results with the widely used Olivetti Research Ltd (ORL) face database are reported showing the effectiveness of the proposed approach.