Scale Invariant Feature Transform (SIFT) proposed by Lowe has been widely and successfully applied to object detection and recognition. However, the representation ability of SIFT features in face recognition has rarely been investigated systematically. In this paper, we proposed to use the person-specific SIFT features and a simple nonstatistical matching strategy combined with local and global similarity on key-points clusters to solve face recognition problems. Large scale experiments on FERET and CAS-PEAL face databases using only one training sample per person have been carried out to compare it with other non person-specific features such as Gabor wavelet feature and Local Binary Pattern feature. The experimental results demonstrate the robustness of SIFT features to expression, accessory and pose variations.

Correlation is one of the most widely used similarity measures in machine learning like Euclidean and Mahalanobis distances. However, compared with proposed numerous discriminant learning algorithms in distance metric space, only a very little work has been conducted on this topic using correlation similarity measure. In this paper, we propose a novel discriminant learning algorithm in correlation measure space, Correlation Discriminant Analysis (CDA). In this framework, based on the definitions of within-class correlation and between-class correlation, the optimum transformation can be sought for to maximize the difference between them, which is in accordance with good classification performance empirically. Under different cases of the transformation, different implementations of the algorithm are given. Extensive empirical evaluations of CDA demonstrate its advantage over alternative methods.

No abstract

Abstract. Considering the fast respond and high generalization accuracy of the min-max modular support vector machine (M 3 -SVM), we apply M 3 -SVM to solving the gender recognition problem and propose a novel task decomposition method in this paper. Firstly, we extract features from the face images by using a facial point detection and Gabor wavelet transform method. Then we divide the training data set into several subsets with the 'part-versus-part' task decomposition method. The most important advantage of the proposed task decomposition method over existing random method is that the explicit prior knowledge about ages contained in the face images is used in task decomposition. We perform simulations on a real-world gender data set and compare the performance of the traditional SVMs and that of M 3 -SVM with the proposed task decomposition method. The experimental results indicate that M 3 -SVM with our new method have better performance than traditional SVMs and M 3 -SVM with random task decomposition method.

For applications based on facial image processing, pose variation is a difficult problem. In this paper, we propose a gender and age estimation system that is robust against pose variations. The acceptable facial pose range is a yaw (left-right) from -30 degrees to +30 degrees and a pitch (up-down) from -20 degrees to +20 degrees. According to our experiments on several large databases collected under real environments, the gender estimation accuracy is 84.8% and the age estimation accuracy is 80.9% (subjects are divided into 5 classes). The average processing time is about 70 ms/frame for gender estimation and 95 ms/frame for age estimation (Pentium4 3.2 GHz). The system can be used to automatically analyze shopping customers and pedestrians using surveillance cameras.