Showing papers by "Stan Z. Li published in 2005"

Ordinal palmprint represention for personal identification [represention read representation]

Abstract: Palmprint-based personal identification, as a new member in the biometrics family, has become an active research topic in recent years. Although great progress has been made, how to represent palmprint for effective classification is still an open problem. In this paper, we present a novel palmprint representation - ordinal measure, which unifies several major existing palmprint algorithms into a general framework. In this framework, a novel palmprint representation method, namely orthogonal line ordinal features, is proposed. The basic idea of this method is to qualitatively compare two elongated, line-like image regions, which are orthogonal in orientation and generate one bit feature code. A palmprint pattern is represented by thousands of ordinal feature codes. In contrast to the state-of-the-art algorithm reported in the literature, our method achieves higher accuracy, with the equal error rate reduced by 42% for a difficult set, while the complexity of feature extraction is halved.

Real-time multiple objects tracking with occlusion handling in dynamic scenes

Abstract: This work presents a real-time system for multiple objects tracking in dynamic scenes. A unique characteristic of the system is its ability to cope with long-duration and complete occlusion without a prior knowledge about the shape or motion of objects. The system produces good segment and tracking results at a frame rate of 15-20 fps for image size of 320 /spl times/ 240, as demonstrated by extensive experiments performed using video sequences under different conditions indoor and outdoor with long-duration and complete occlusions in changing background.

Learning multiview face subspaces and facial pose estimation using independent component analysis

Abstract: An independent component analysis (ICA) based approach is presented for learning view-specific subspace representations of the face object from multiview face examples. ICA, its variants, namely independent subspace analysis (ISA) and topographic independent component analysis (TICA), take into account higher order statistics needed for object view characterization. In contrast, principal component analysis (PCA), which de-correlates the second order moments, can hardly reveal good features for characterizing different views, when the training data comprises a mixture of multiview examples and the learning is done in an unsupervised way with view-unlabeled data. We demonstrate that ICA, TICA, and ISA are able to learn view-specific basis components unsupervisedly from the mixture data. We investigate results learned by ISA in an unsupervised way closely and reveal some surprising findings and thereby explain underlying reasons for the emergent formation of view subspaces. Extensive experimental results are presented.

Manifold Learning and Applications in Recognition

Abstract: Great amount of data under varying intrinsic features are empirically thought of as high-dimensional nonlinear manifold in the observation space. With respect to different categories, we present two recognition approaches, i.e. the combination of manifold learning algorithm and linear discriminant analysis (MLA+LDA), and nonlinear auto-associative modeling (NAM). For similar object recognition, e.g. face recognition, MLA + LDA is used. Otherwise, NAM is employed for objects from largely different categories. Experimental results on different benchmark databases show the advantages of the proposed approaches.

Learning to fuse 3d+2d based face recognition at both feature and decision levels

Abstract: 2D intensity images and 3D shape models are both useful for face recognition, but in different ways. While algorithms have long been developed using 2D or 3D data, recently has seen work on combining both into multi-modal face biometrics to achieve higher performance. However, the fusion of the two modalities has mostly been at the decision level, based on scores obtained from independent 2D and 3D matchers. In this paper, we propose a systematic framework for fusing 2D and 3D face recognition at both feature and decision levels, by exploring synergies of the two modalities at these levels. The novelties are the following. First, we propose to use Local Binary Pattern (LBP) features to represent 3D faces and present a statistical learning procedure for feature selection and classifier learning. This leads to a matching engine for 3D face recognition. Second, we propose a statistical learning approach for fusing 2D and 3D based face recognition at both feature and decision levels. Experiments show that the fusion at both levels yields significantly better performance than fusion at the decision level.

Adaptive nonlinear auto-associative modeling through manifold learning

Abstract: We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm.

Automated feature points management for video mosaic construction

Abstract: This paper presents a two level automatic feature points management method for constructing a seamless entire panorama from video sequence. In the first level, through fusing the number of tracked feature points and the estimated ratio of lost information of the mosaicing image, a feature point quantity management module is developed to select the key frames. In the second level, a feature points quality management technique is used to choose the key points for mosaicing. This module includes a coarse-to-fine method with two steps: (1) Feature points quality based key point subset creation; and (2) Multi-resolution based key point selection. The main contribution of the algorithm is that it is able to achieve robust and fast mosaicing result while maintain the most valuable information of the scene. Experiments are performed using video sequences under different conditions. The results show that the proposed algorithm could achieve robust and efficient video mosaic image.

Geometrical probability covering algorithm

Abstract: In this paper, we propose a novel classification algorithm, called geometrical probability covering (GPC) algorithm, to improve classification ability. On the basis of geometrical properties of data, the proposed algorithm first forms extended prototypes through computing means of any two prototypes in the same class. Then Gaussian kernel is employed for covering the geometrical structure of data and used as a local probability measurement. By computing the sum of the probabilities that a new sample to be classified to the set of prototypes and extended prototypes, the classified criterion based on the global probability measurement is achieved. The proposed GPC algorithm is simple but powerful, especially, when training samples are sparse and small size. Experiments on several databases show that the proposed algorithm is promising. Also, we explore other potential applications such as outlier removal with the proposed GPC algorithm.