Example-based learning for computer vision can be difficult when a large number of examples to represent each pattern or object class is not available. In such situations, learning from a small number of samples is of practical value. To study this issue, the task of face expression recognition with a small number of training images of each expression is considered. A new technique based on linear programming for both feature selection and classifier training is introduced. A pairwise framework for feature selection, instead of using all classes simultaneously, is presented. Experimental results compare the method with three others: a simplified Bayes classifier, support vector machine, and AdaBoost. Finally, each algorithm is analyzed and a new categorization of these algorithms is given, especially for learning from examples in the small sample case.

Abstract—The task of face recognition has been actively researched in recent years. This paper provides an up-to-date review of major human face recognition research. We first present an overview of face recognition and its applications. Then, a literature review of the most recent face recognition techniques is presented. Description and limitations of face databases which are used to test the performance of these face recognition algorithms are given. A brief summary of the face recognition vendor test (FRVT) 2002, a large scale evaluation of automatic face recognition technology, and its conclusions are also given. Finally, we give a summary of the research results. Keywords—Combined classifiers, face recognition, graph matching, neural networks. F I.

Face verification has many potential applications including filtering and ranking image/video search results on celebrities. Since these images/videos are taken under uncontrolled environments, the problem is very challenging due to dramatic lighting and pose variations, low resolutions, compression artifacts, etc. In addition, the available number of training images for each celebrity may be limited, hence learning individual classifiers for each person may cause overfitting. In this paper, we propose two ideas to meet the above challenges. First, we propose to use individual bins, instead of whole histograms, of Local Binary Patterns (LBP) as features for learning, which yields significant performance improvements and computation reduction in our experiments. Second, we present a novel Multi-Task Learning (MTL) framework, called Boosted MTL, for face verification with limited training data. It jointly learns classifiers for multiple people by sharing a few boosting classifiers in order to avoid overfitting. The effectiveness of Boosted MTL and LBP bin features is verified with a large number of celebrity images/videos from the web. 1.

Human age prediction is useful for many applications. The age information could be used as a kind of semantic knowledge for multimedia content analysis and understanding. In this paper we propose a Probabilistic Fusion Approach (PFA) that produces a high performance estimator for human age prediction. The PFA framework fuses a regressor and a classifier. We derive the predictor based on Bayes ’ rule without the mutual independence assumption that is very common for traditional classifier combination methods. Using a sequential fusion strategy, the predictor reduces age estimation errors significantly. Experiments on the large UIUC-IFP-Y aging database and the FG-NET aging database show the merit of the proposed approach to human age prediction. 1.

Performance of many state-of-the-art face recognition (FR) methods deteriorates rapidly, when large in size databases are considered. In this paper, 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 here 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 maximalseparability 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 is able to be greatly improved without significantly increasing computational complexity. 1.

There are two main approaches for face recognition with variations in lighting conditions. One is to represent images with features that are insensitive to illumination in the first place. The other main approach is to construct a linear subspace for every class under the different lighting conditions. Both of these techniques are successfully applied to some extent in face recognition, but it is hard to extend them for recognition with variant facial expressions. It is observed that features insensitive to illumination are highly sensitive to expression variations, which result in face recognition with changes in both lighting conditions and expressions a difficult task. We propose a new method called Affine Principle Components Analysis in an attempt to solve both of these problems. This method extract features to construct a subspace for face representation and warps this space to achieve better class separation. The proposed technique is evaluated using face databases with both variable lighting and facial expressions. We achieve more than 90% accuracy for face recognition by using only one sample image per class.