Xinwen Hou

Learning spatially localized, parts-based representation

In this paper, we propose a novel method, called local non-negative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns. An objective function is defined to impose a localization constraint, in addition to the non-negativity constraint in the standard NMF. This gives a set of bases which not only allows a non-subtractive (part-based) representation of images but also manifests localized features. An algorithm is presented for the learning of such basic components. Experimental results are presented to compare LNMF with the NMF and PCA methods for face representation and recognition, which demonstrates advantages of LNMF.

A Hybrid Approach to Detect and Localize Texts in Natural Scene Images

Text detection and localization in natural scene images is important for content-based image analysis. This problem is challenging due to the complex background, the non-uniform illumination, the variations of text font, size and line orientation. In this paper, we present a hybrid approach to robustly detect and localize texts in natural scene images. A text region detector is designed to estimate the text existing confidence and scale information in image pyramid, which help segment candidate text components by local binarization. To efficiently filter out the non-text components, a conditional random field (CRF) model considering unary component properties and binary contextual component relationships with supervised parameter learning is proposed. Finally, text components are grouped into text lines/words with a learning-based energy minimization method. Since all the three stages are learning-based, there are very few parameters requiring manual tuning. Experimental results evaluated on the ICDAR 2005 competition dataset show that our approach yields higher precision and recall performance compared with state-of-the-art methods. We also evaluated our approach on a multilingual image dataset with promising results.

Direct appearance models

Active appearance model (AAM), which makes ingenious use of both shape and texture constraints, is a powerful tool for face modeling, alignment and facial feature extraction under shape deformations and texture variations. However, as we show through our analysis and experiments, there exist admissible appearances that are not modeled by AAM and hence cannot be reached by AAM search; also the mapping from the texture subspace to the shape subspace is many-to-one and therefore a shape should be determined entirely by the texture in it. We propose a new appearance model, called direct appearance model (DAM), without combining from shape and texture as in AAM. The DAM model uses texture information directly in the prediction of the shape and in the estimation of position and appearance (hence the name DAM). In addition, DAM predicts the new face position and appearance based on principal components of texture difference vectors, instead of the raw vectors themselves as in AAM. These lead to the following advantages over AAM: (1) DAM subspaces include admissible appearances previously unseen in AAM, (2) convergence and accuracy are improved, and (3) memory requirement is cut down to a large extent. The advantages are substantiated by comparative experimental results.

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

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.

A Robust System to Detect and Localize Texts in Natural Scene Images

In this paper, we present a robust system to accurately detect and localize texts in natural scene images. For text detection, a region-based method utilizing multiple features and cascade AdaBoost classifier is adopted. For text localization, a window grouping method integrating text line competition analysis is used to generate text lines. Then within each text line, local binarization is used to extract candidate connected components (CCs) and non-text CCs are filtered out by Markov Random Fields (MRF) model, through which text line can be localized accurately. Experiments on the public benchmark ICDAR 2003 Robust Reading and Text Locating Dataset show that our system is comparable to the best existing methods both in accuracy and speed.

Regularized margin-based conditional log-likelihood loss for prototype learning

The classification performance of nearest prototype classifiers largely relies on the prototype learning algorithm. The minimum classification error (MCE) method and the soft nearest prototype classifier (SNPC) method are two important algorithms using misclassification loss. This paper proposes a new prototype learning algorithm based on the conditional log-likelihood loss (CLL), which is based on the discriminative model called log-likelihood of margin (LOGM). A regularization term is added to avoid over-fitting in training as well as to maximize the hypothesis margin. The CLL in the LOGM algorithm is a convex function of margin, and so, shows better convergence than the MCE. In addition, we show the effects of distance metric learning with both prototype-dependent weighting and prototype-independent weighting. Our empirical study on the benchmark datasets demonstrates that the LOGM algorithm yields higher classification accuracies than the MCE, generalized learning vector quantization (GLVQ), soft nearest prototype classifier (SNPC) and the robust soft learning vector quantization (RSLVQ), and moreover, the LOGM with prototype-dependent weighting achieves comparable accuracies to the support vector machine (SVM) classifier.

Face alignment using view-based direct appearance models

Accurate face alignment is the prerequisite for many computer vision problems, such as face recognition, synthesis and 3D face modeling. In this article, a novel appearance model, called direct appearance model (DAM), is proposed and its extended view‐based models are applied for multiview face alignment. Similar to the active appearance model (AAM), DAM also makes ingenious use of both shape and texture constraints; however, it does not combine them as in AAM; texture information is used directly to predict the shape and estimate the position and appearance (hence the name DAM). The way that DAM models shapes and textures has the following advantages as compared with AAM: (1) DAM subspaces include admissible appearances previously unseen in AAM, (2) it can converge more quickly and has higher accuracy, and (3) the memory requirement is cut down to a large extent. Extensive experiments are presented to evaluate the DAM alignment in comparison with AAM.

Learning locality preserving graph from data.

Machine learning based on graph representation, or manifold learning, has attracted great interest in recent years. As the discrete approximation of data manifold, the graph plays a crucial role in these kinds of learning approaches. In this paper, we propose a novel learning method for graph construction, which is distinct from previous methods in that it solves an optimization problem with the aim of directly preserving the local information of the original data set. We show that the proposed objective has close connections with the popular Laplacian Eigenmap problem, and is hence well justified. The optimization turns out to be a quadratic programming problem with n(n - 1)/2 variables (n is the number of data points). Exploiting the sparsity of the graph, we further propose a more efficient cutting plane algorithm to solve the problem, making the method better scalable in practice. In the context of clustering and semi-supervised learning, we demonstrated the advantages of our proposed method by experiments.

Learning Boosted Asymmetric Classifiers for Object Detection

Object detection can be posted as those classification tasks where the rare positive patterns are to be distinguished from the enormous negative patterns. To avoid the danger of missing positive patterns, more attention should be payed on them. Therefore there should be different requirements for False Reject Rate (FRR) and False Accept Rate (FAR) , and learning a classifier should use an asymmetric factor to balance between FRR and FAR. In this paper, a normalized asymmetric classification error is proposed for the task of rejecting negative patterns. Minimizing it not only controls the ratio of FRR and FAR, but more importantly limits the upper-bound of FRR. The latter characteristic is advantageous for those tasks where there is a requirement for low FRR. Based on this normalized asymmetric classification error, we develop an asymmetric AdaBoost algorithm with variable asymmetric factor and apply it to the learning of cascade classifiers for face detection. Experiments demonstrate that the proposed method achieves less complex classifiers and better performance than some previous AdaBoost methods.

Multi-view face pose estimation based on supervised ISA learning

Independent subspace analysis (ISA) is able to learn view-subspaces unsupervisedly from (view-unlabeled) multi-view face examples (S.Z. Li et al., 2001). We explain underlying reasons for the emergent formation of ISA view-subspaces. Based on the analysis, we present a supervised method for more effective learning of view-subspace, assuming that view-labeled face examples are available. The models thus learned give more accurate pose estimation than those obtained with the unsupervised ISA.