Chi Fang

Face authentication test on the BANCA database

This work details the results of a face authentication test (FAT2004) (http://www.ee.surrey.ac.uk/banca/icpr2004) held in conjunction with the 17th International Conference on Pattern Recognition. The contest was held on the publicly available BANCA database (http://www.ee.surrey.ac.uk/banca) according to a defined protocol (E. Bailly-Bailliere et al., June 2003). The competition also had a sequestered part in which institutions had to submit their algorithms for independent testing. 13 different verification algorithms from 10 institutions submitted results. Also, a standard set of face recognition software packages from the Internet (http://www.cs.colostate.edu/evalfacerec) were used to provide a baseline performance measure.

Head Pose Estimation Based on Random Forests for Multiclass Classification

Head pose estimation remains a unique challenge for computer vision system due to identity variation, illumination changes, noise, etc. Previous statistical approaches like PCA, linear discriminative analysis (LDA) and machine learning methods, including SVM and Adaboost, cannot achieve both accuracy and robustness that well. In this paper, we propose to use Gabor feature based random forests as the classification technique since they naturally handle such multi-class classification problem and are accurate and fast. The two sources of randomness, random inputs and random features, make random forests robust and able to deal with large feature spaces. Besides, we implement LDA as the node test to improve the discriminative power of individual trees in the forest, with each node generating both constant and variant number of children nodes. Experiments are carried out on two public databases to show the proposed algorithm outperforms other approaches in both accuracy and computational efficiency.

Iris Localization with Dual Coarse-to-fine Strategy

Iris-based personal recognition is highly dependent on the accurate iris localization. In this paper, an effective and efficient iris localization algorithm is proposed to overcome the drawback of the traditional localization methods which are time-consuming and sensitive to the occlusion caused by eyelids and eyelashes. The coarse-to-fine strategy is deployed in both the inner boundary localization and the outer boundary localization. In the coarse localization of the inner boundary, the lower contour of the pupil is introduced to estimate the parameters of the pupil since it is stable even when the iris image is seriously occluded. While in the coarse localization of the outer boundary, the average intensity signals on both sides of the pupil are utilized to estimate the parameters of the sclera after the fine localization of the inner boundary. In the fine stage, the Hough transform is adopted to localize both boundaries precisely with the gradient information. Experimental results indicate that the proposed method is more effective and efficient

Robust Image Restoration via Adaptive Low-Rank Approximation and Joint Kernel Regression

In recent years, image priors based on nonlocal self-similarity and low-rank approximation have been proven as powerful tools for image restoration. Many restoration methods group similar patches as a matrix and recover the underlying low-rank structure from the corrupted matrix via rank minimization. However, both the nonlocally redundant and low-rank properties are highly content dependent, and whether they can faithfully characterize a wide range of natural images still remains unclear. In this paper, we analyze these two properties and provide quantifications of them in a data-driven and parametric way, respectively, obtaining the new measures of regional redundancy and nonlocal patch rank. Leveraging these prior leads to an adaptive image restoration method with content-awareness. In particular, our method iteratively removes outliers and recovers latent fine details. To handle outliers, we propose an adaptive low-rank and sparse matrix approximation algorithm to encourage the estimated nonlocal rank in the patch matrix. The guidance of regional redundancy further gives rise to the “denoise” quality. In the detail recovery step, we propose an adaptive joint kernel regression algorithm using the redundancy measure to determine the confidence of each regression group. It also bridges the gap between our online and offline dictionary learning schemes. Experiments on synthetic and real-world images show the efficacy of our method in image deblurring and super-resolution tasks, especially when subject to practical outliers such as rain drops.

Generalized joint kernel regression and adaptive dictionary learning for single-image super-resolution

This paper proposes a new approach to single-image super-resolution (SR) based on generalized adaptive joint kernel regression (G-AJKR) and adaptive dictionary learning. The joint regression prior aims to regularize the ill-posed reconstruction problem by exploiting local structural regularity and nonlocal self-similarity of images. It is composed of multiple locally generalized kernel regressors defined over similar patches found in the nonlocal range which are combined, thus simultaneously exploiting both image statistics in a natural manner. Each regression group is then weighted by a regional redundancy measure we propose to control their relative effects of regularization adaptively. This joint regression prior is further generalized to the range of multi-scales and rotations. For robustness, adaptive dictionary learning and dictionary-based sparsity prior are introduced to interact with this prior. We apply the proposed method to both general natural images and human face images (face hallucination), and for the latter we incorporate a new global face prior into SR reconstruction while preserving face discriminativity. In both cases, our method outperforms other related state-of-the-art methods qualitatively and quantitatively. Besides, our face hallucination method also outperforms the others when applied to face recognition applications. HighlightsAdaptive joint kernel regression simultaneously exploits local and nonlocal image priors.The generalization to multi-scales and rotations encourages better super-resolution results.Dictionary prior learned online and offline interacts with the regional redundancy adaptively.A discriminative global face prior based on Partial Least Squares for face super-resolution.State-of-the-art performance for both generic and face images also with high face recognition rates.

Pose robust face tracking by combining view-based AAMs and temporal filters

Active appearance models (AAMs) are useful for face tracking for the advantages of detailed face interpretation, accurate alignment and high efficiency. However, they are sensitive to initial parameters and may easily be stuck in local minima due to the gradient-descent optimization, which makes the AAM based face tracker unstable in the presence of large pose deviation and fast motion. In this paper, we propose to combine the view-based AAMs with two novel temporal filters to overcome the limitations. First, we build a new view space based on the shape parameters of AAMs, instead of the model parameters controlling both the shape and appearance, for the purpose of pose estimation. Then the Kalman filter is used to simultaneously update the pose and shape parameters for a better fitting of each frame. Second, we propose a temporal matching filter which is twofold. The inter-frame local appearance constraint is incorporated into AAM fitting, where the mechanism of the active shape model (ASM) is also implemented in a unified framework to find more accurate matching points. Moreover, we propose to initialize the shape with correspondences found by a random forest based local feature matching. By introducing the local information and temporal correspondences, the twofold temporal matching filter improves the tracking stability when confronted with fast appearance changes. Experimental results show that our algorithm is more pose robust than basic AAMs and some state-of-art AAM based methods, and that it can also handle large expressions and non-extreme illumination changes in test video sequences.

A new biologically inspired active appearance model for face age estimation by using local ordinal ranking

In this paper, a new facial feature called Biologically Inspired Active Appearance Model (BIAAM) is proposed for face age estimation by using a novel age function learning algorithm, called Local Ordinal Ranking (LOR). In BIAAM, appearance variations are encoded by extracting Bio Inspired Feature from normalized shape-free images with a mean shape mask. The proposed LOR divides the training set into several groups according to age labels and applies Ordinal Hyperplanes Ranker for each group to determine the final predicting age. A multiple linear regression function is used to decide which group a query sample belongs to. Experimental evaluation on the FG-NET aging database with mean absolute error 4.18 years demonstrates that our method outperforms other state-of-the-art algorithms.

Pose adaptive LDA based face recognition

In this paper, a novel method based on pose adaptive linear discriminant analysis (PALDA) is proposed to deal with pose variation problems in face recognition when each person has only one frontal training sample. The basic idea of the PALDA method is described as follows: first, the pose style of the test sample is estimated by one pose classifier; then, the corresponding LDA feature, which is robust to the variation between the estimated pose style and the frontal pose style, is extracted. Since human faces are very similar objects with similar geometrical shape and configuration, the facial images from the same pose style are similar to each other. So an effective pose classifier is designed. The variations of each specific personpsilas facial images, due to changes of pose, are also rather similar to each other, so varieties of LDA projection matrixes, each of which is robust to one variation between one specific pose style and the frontal pose style, are trained with offline face samples containing various poses. The comparison with other pose robust face recognition methods on CMUPie database has confirmed the effectiveness and the robustness of the proposed method.

Asymmetric Real Adaboost

A cost-sensitive extension of real Adaboost denoted as asymmetric real Adaboost(RAB) is proposed. The two main differences between Asymmetric RAB and the naive RAB are (1) a Chernoff measurement is used to evaluate the best weak classifier during training, rather than a Bhattacharyya measurement used in naive RAB, and (2) the weights are updated separately for positives and negatives at each boosting step. The upper bound on training error is also provided. Experiment results are shown to demonstrate its cost-sensitivity when selecting weak classifiers, and also show that it outperforms previously proposed cost-sensitive extensions of Discrete Adaboost(DAB) and several extensions of Real Adaboost. Besides, it also consumes much less time than previously proposed DAB extensions.

Face age estimation by using Bisection Search Tree

Age estimation via face images has recently attracted a lot of researches in computer vision, due to its many potential applications. In this paper, a novel Bisection Search Tree (BST) algorithm is proposed for face age estimation, based on the idea of Divide and Conquer. Different from those conventional classification or regression approaches, the BST first constructs a binary tree according to the whole age range of training set, and then learns decision functions for all non-leaf nodes to determine which child node a test sample will be passed to. Gabor wavelet face representation and dimensionality reduction by using Linear Discriminative Analysis are also adopted in this paper. Experimental results on two public aging databases, MORPH-II and MEDS-II, show that the BST method is effective for age estimation and outperforms other state-of-the-art approaches.