Xiangsheng Huang

Boosting local binary pattern (LBP)-Based face recognition

This paper presents a novel approach for face recognition by boosting statistical local features based classifiers The face image is scanned with a scalable sub-window from which the Local Binary Pattern (LBP) histograms [14] are obtained to describe the local features of a face image The multi-class problem of face recognition is transformed into a two-class one by classifying every two face images as intra-personal or extra-personal ones [9] The Chi square distance between corresponding Local Binary Pattern histograms of two face images is used as discriminative feature for intra/extra-personal classification We use AdaBoost algorithm to learn a similarity of every face image pairs The proposed method was tested on the FERET FA/FB image sets and yielded an exciting recognition rate of 97.9%.

Shape localization based on statistical method using extended local binary pattern

Accurate localization of representative points of a face is crucial to many face analysis and synthesis problems. Active shape model (ASM) is a powerful statistical tool for face alignment. However, it suffers from variations of pose, illumination and expressions. In this paper, we analyze the mechanism of active shape model and realize that the ability of normal profiles to describe the local appearance pattern is very limited. For efficient appearance pattern representation, the local binary pattern is used and extended to describe the local patterns of facial key points. For the purpose of retaining the spatial information, sub-images of key points are divided into several regions, which are combined to define the extended local binary pattern (ELBP) histogram. Then we propose an improved ASM method framework, ELBP-ASM, in which local appearance patterns of key points are modelled using extended local binary pattern. Experimental results demonstrate that ELBP-ASM achieves more accurate results compared with original method used in ASM.

Jensen-Shannon boosting learning for object recognition

In this paper, we propose a novel learning method, called Jensen-Shannon Boosting (JSBoost) and demonstrate its application to object recognition. JSBoost incorporates Jensen-Shannon (JS) divergence [Y. Bubner et al. (2001)] into AdaBoost learning. JS divergence is advantageous in that it provides more appropriate measure of dissimilarity between two classes and it is numerically more stable than other measures such as Kullback-Leibler (KL) divergence (see [Y. Bubner et al. (2001)]). The best features are iteratively learned by maximizing the projected JS divergence, based on which best weak classifiers are derived. The weak classifiers are combined into a strong one by minimizing the recognition error. JSBoost learning is demonstrated with face object recognition using a local binary pattern (LBP) [M. Pietikainen et al. (2004)] based representation. JSBoost selects the best LBP features from thousands of candidate features and constructs a strong classifier based on the selected features. JSBoost empirically produces better face recognition results than other AdaBoost variants such as RealBoost [R.E. Schapire et al. (1998)], GentleBoost [J. Friedman et al. (2000)] and KL-Boost [C. Liu et al. (2003)], as demonstrated by experiments.

Boosting Local Feature Based Classifiers for Face Recognition

In this paper, we present a method for face recognition using boosted Gabor feature based classifiers. Weak classifiers are constructed based on both magnitude and phase features derived from Gabor filters [Quadrature-phase simple-cell pairs are ap-propriately described in complex analytic from]. The multi-class problem is transformed into a two-class one of intra- and extra-class classification using intra-personal and extra-personal difference images, as in [Beyond euclidean eigenspaces:bayesian matching for visian recognition]. A cascade of strong classifiers are learned using bootstrapped negative examples, similar to the way in face detection framework [Robust real time object detection]. The combination of classifiers based on two different types of features produces better results than using either type. Experiments on FERET database show good results comparable to the best one reported in literature [The FERET evaluation methodology for face-recognition algorithms].

Regularized Discriminative Spectral Regression Method for Heterogeneous Face Matching

Face recognition is confronted with situations in which face images are captured in various modalities, such as the visual modality, the near infrared modality, and the sketch modality. This is known as heterogeneous face recognition. To solve this problem, we propose a new method called discriminative spectral regression (DSR). The DSR maps heterogeneous face images into a common discriminative subspace in which robust classification can be achieved. In the proposed method, the subspace learning problem is transformed into a least squares problem. Different mappings should map heterogeneous images from the same class close to each other, while images from different classes should be separated as far as possible. To realize this, we introduce two novel regularization terms, which reflect the category relationships among data, into the least squares approach. Experiments conducted on two heterogeneous face databases validate the superiority of the proposed method over the previous methods.

Face recognition system using Extended Curvature Gabor classifier bunch for low-resolution face image

We describe a face recognition framework based on Extended Curvature Gabor (ECG) Classifier Bunch. First we extend Gabor wavelet kernels into the ECG wavelet kernels by adding a spatial curvature term to the kernel and adjusting the width of the Gaussian at the kernel, which leads to extraction of numerous feature candidates from a low-resolution image. To handle them efficiently, we divide a pool of feature candidates into plural ECG wavelet coefficient sets according to different kernel parameters. For each ECG wavelet coefficient set, the boosting learning scheme selects significant features. A single ECG classifier is implemented by applying Linear Discriminant Analysis (LDA) to the selected feature, and then, to overcome the accuracy limitation of a single classifier, we propose the ECG classifier bunch that combines plural ECG classifiers by means of the proposed log-likelihood ratio-based score fusion scheme. For evaluations of the proposed method, we use Face Recognition Grand Challenge (FRGC) ver 2.0 experimental protocols and database. The proposed method shows an average of 90.67% verification rate on 2D face images under uncontrolled environmental variations.

Face recognition using Extended Curvature Gabor classifier bunch

We describe a novel face recognition using the Extended Curvature Gabor (ECG) Classifier Bunch. First, we extend Gabor kernels into the ECG kernels by adding a spatial curvature term to the kernel and adjusting the width of the Gaussian at the kernel, which leads to numerous feature candidates being extracted from a single image. To handle large feature candidates efficiently, we divide them into multiple ECG coefficients according to different kernel parameters, and then we independently select the salient features from each ECG coefficient using the boosting method. A single ECG classifier is implemented by applying Linear Discriminant Analysis (LDA) to the selected feature vector. To overcome the accuracy limitation of a single classifier, we propose an ECG classifier bunch that combines multiple ECG classifiers with the fusion scheme. We confirm the generality of the performances of the proposed method using the FRGC version 2.0, XM2VTS, BANCA, and PIE databases. HighlightsWe propose extended curvature Gabor kernels as complementary features.Homogeneous Classifier Bunch increases accuracy in low/mid-resolution images.Parallel boosting method effectively selects salient features from many features.We report the best verification rate using the FRGC version 2.0 database.We have extensive experimental results.

Head gesture recognition based on bayesian network

Head gestures such as nodding and shaking are often used as one of human body languages for communication with each other, and their recognition plays an important role in the development of Human-Computer Interaction (HCI). As head gesture is the continuous motion on the sequential time series, the key problems of recognition are to track multi-view head and understand the head pose transformation. This paper presents a Bayesian network (BN) based framework, into which multi-view model (MVM) and the head gesture statistic inference model are integrated for recognizing. Finally the decision of head gesture is made by comparing the maximum posterior, the output of BN, with some threshold. Additionally, in order to enhance the robustness of our system, we add the color information into BN in a new way. The experimental results illustrate that the proposed algorithm is effective.

Learning with Cascade for Classification of Non-Convex Manifolds

Images of a visual object, such as human face, reside in a complicated manifold in the high dimensional image space, when the object is subject to variations in pose, illumination, and other factors. Viola and Jones have successfully tackled difficult nonlinear classification problem for face detection using AdaBoost learning. Moreover, their simple-to-complex cascade of classifiers structure makes the learning and classification even more effective. While training with cascade has been used effectively in many works [4, 5, 6, 7, 2, 3, 8, 9, 10], an understanding of the role of the cascade strategy is still lacking. In this paper, we analyze the problem of classifying non-convex manifolds using AdaBoost learning with and without using cascade. We explain that the divide-and-conquer strategy in cascade learning has a great contribution on learning a complex classifier for non-convex manifolds. We prove that AdaBoost learning with cascade is effective when a complete or over-complete set of features (or weak classifiers) is available. Experiments with both synthesized and real data demonstrate that AdaBoost learning with cascade leads to improved convergence and accuracy.

Navigation in 3D game by Markov model based head pose estimating

Keyboards, mice, and joy sticks are the most popular controlling and navigation devices in current 3D game. However, they are quite unnatural. In this paper, we propose a novel scheme to estimate the users head pose and the estimation result is used for navigating in game. The novel scheme based on Markov model fusing appearance, color and motion information. The experimental results demonstrate that the proposed approach which is used for 3D game controlling, is real-time and robust, and can give players more immersiveness.