Search

Most face recognition systems require faces to be detected and localized a priori. In this paper, an approach to simultaneously detect and localize multiple faces having arbitrary views and different scales is proposed. The main contribution of this paper is the introduction of a face constellation, which enables multiview face detection and localization. In contrast to other multiview approaches that require many manually labeled images for training, the proposed face constellation requires only a single reference image of a face containing two manually indicated reference points for initialization. Subsequent training face images from arbitrary views are automatically added to the constellation (registered to the reference image) based on finding the correspondences between distinctive local features. Thus, the key advantage of the proposed scheme is the minimal manual intervention required to train the face constellation. We also propose an approach to identify distinctive correspondence points between pairs of face images in the presence of a large amount of false matches. To detect and localize multiple faces with arbitrary views, we then propose a probabilistic classifier-based formulation to evaluate whether a local feature cluster corresponds to a face. Experimental results conducted on the FERET, CMU, and FDDB datasets show that our proposed approach has better performance compared to the state-of-the-art approaches for detecting faces with arbitrary pose.

Most facial emotion recognition algorithms assume that the face is near frontal and the face pose fixed during the recognition process. However, such constrain limits the adoption for real-world applications. To solve this, pose-invariant descriptor for emotion recognition is required. This work proposes a novel pose-invariant dynamic descriptor that encodes the relative movement information of facial landmarks. The proposed feature set is able to handle speed variations and continuous head pose variations, while the subject is expressing an emotion. In addition, the proposed method is fast and thus can be realize real-time implementation for real-world application. Performance evaluation done using three publicly available databases; Cohn-Kanade $$(\hbox {CK}^{+})$$ , Amsterdam Dynamic Facial Expression Set (ADFES), and Audio Visual Emotion Challenge (AVEC 2011) showed that our proposed method outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Facial age classification is an approach to classify face images into one of several predefined age groups. One of the difficulties in applying learning techniques to the age classification problem is the large amount of labeled training data required. Acquiring such training data is very costly in terms of age progress, privacy, human time, and effort. Although unlabeled face images can be obtained easily, it would be expensive to manually label them on a large scale and getting the ground truth. The frugal selection of the unlabeled data for labeling to quickly reach high classification performance with minimal labeling efforts is a challenging problem. In this paper, we present an active learning approach based on an online incremental bilateral two-dimension linear discriminant analysis (IB2DLDA) which initially learns from a small pool of labeled data and then iteratively selects the most informative samples from the unlabeled set to increasingly improve the classifier. Specifically, we propose a novel data selection criterion called the furthest nearest-neighbor (FNN) that generalizes the margin-based uncertainty to the multiclass case and which is easy to compute, so that the proposed active learning algorithm can handle a large number of classes and large data sizes efficiently. Empirical experiments on FG-NET and Morph databases together with a large unlabeled data set for age categorization problems show that the proposed approach can achieve results comparable or even outperform a conventionally trained active classifier that requires much more labeling effort. Our IB2DLDA-FNN algorithm can achieve similar results much faster than random selection and with fewer samples for age categorization. It also can achieve comparable results with active SVM but is much faster than active SVM in terms of training because kernel methods are not needed. The results on the face recognition database and palmprint/palm vein database showed that our approach can handle problems with large number of classes. Our contributions in this paper are twofold. First, we proposed the IB2DLDA-FNN, the FNN being our novel idea, as a generic on-line or active learning paradigm. Second, we showed that it can be another viable tool for active learning of facial age range classification. [ABSTRACT FROM AUTHOR]

Abstract: Fingerprint classification is crucial to reduce the processing time in a large-scale database. Two popular features used are the singularities and orientation information and they are complementary. Therefore, an algorithm based on the interactive validation of singular points and the constrained nonlinear orientation model is proposed. The final features used for classification comprises the coefficients of the orientation model and the singularity information. This resulted in very compact feature vector which is used as input to an SVM classifier to perform the classification. The experiments conducted on the NIST database 4 show the effectiveness of the proposed method in producing good classification result. [Copyright &y& Elsevier]

Abstract: In design of a multibiometric system, a major concern is the learning cost in terms of computation complexity and memory usage due to large data size. In this paper, we propose an online learning network to circumvent the computational problem. Although conventional online learning algorithms can be adopted, their optimization of the fitting distance residuals does not meet the actual classification error requirement. A direct optimization to the classification performance is thus desired. Since the proposed classification-based formulation involves a class-specific weight which varies according to the total number of genuine-users and imposters, an online learning formulation becomes non-trivial. Extensive empirical evaluations on publicly available data sets show promising potential of the proposed method in terms of fusion verification accuracy and computational cost. [Copyright &y& Elsevier]