/pdf/convex-analysisnoer-san-nojin-zhan-nituite-5dl2rbmoyr.pdf

Convex Analysisの二,三の進展について

The capacity to estimate the head pose of another person is a common human ability that presents a unique challenge for computer vision systems. Compared to face detection and recognition, which have been the primary foci of face-related vision research, identity-invariant head pose estimation has fewer rigorously evaluated systems or generic solutions. In this paper, we discuss the inherent difficulties in head pose estimation and present an organized survey describing the evolution of the field. Our discussion focuses on the advantages and disadvantages of each approach and spans 90 of the most innovative and characteristic papers that have been published on this topic. We compare these systems by focusing on their ability to estimate coarse and fine head pose, highlighting approaches that are well suited for unconstrained environments.

Head Pose Estimation in Computer Vision: A Survey

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Local binary pattern (LBP) is a nonparametric descriptor, which efficiently summarizes the local structures of images. In recent years, it has aroused increasing interest in many areas of image processing and computer vision and has shown its effectiveness in a number of applications, in particular for facial image analysis, including tasks as diverse as face detection, face recognition, facial expression analysis, and demographic classification. This paper presents a comprehensive survey of LBP methodology, including several more recent variations. As a typical application of the LBP approach, LBP-based facial image analysis is extensively reviewed, while its successful extensions, which deal with various tasks of facial image analysis, are also highlighted.

/pdf/local-binary-patterns-and-its-application-to-facial-image-1kaldi7ot7.pdf

Local Binary Patterns and Its Application to Facial Image Analysis: A Survey

We present a novel unified framework for both static and space-time saliency detection. Our method is a bottom-up approach and computes so-called local regression kernels (i.e., local descriptors) from the given image (or a video), which measure the likeness of a pixel (or voxel) to its surroundings. Visual saliency is then computed using the said "self-resemblance" measure. The framework results in a saliency map where each pixel (or voxel) indicates the statistical likelihood of saliency of a feature matrix given its surrounding feature matrices. As a similarity measure, matrix cosine similarity (a generalization of cosine similarity) is employed. State of the art performance is demonstrated on commonly used human eye fixation data (static scenes (N. Bruce & J. Tsotsos, 2006) and dynamic scenes (L. Itti & P. Baldi, 2006)) and some psychological patterns.

Static and space-time visual saliency detection by self-resemblance.

Scale invariant feature transform (SIFT) proposed by Lowe has been widely and successfully applied to object detection and recognition. However, the representation ability of SIFT features in face recognition has rarely been investigated systematically. In this paper, we proposed to use the person-specific SIFT features and a simple non-statistical matching strategy combined with local and global similarity on key-points clusters to solve face recognition problems. Large scale experiments on FERET and CAS-PEAL face databases using only one training sample per person have been carried out to compare it with other non person-specific features such as Gabor wavelet feature and local binary pattern feature. The experimental results demonstrate the robustness of SIFT features to expression, accessory and pose variations.

/pdf/person-specific-sift-features-for-face-recognition-1geof170y4.pdf

Person-Specific SIFT Features for Face Recognition

Correlation is one of the most widely used similarity measures in machine learning like Euclidean and Mahalanobis distances. However, compared with proposed numerous discriminant learning algorithms in distance metric space, only a very little work has been conducted on this topic using correlation similarity measure. In this paper, we propose a novel discriminant learning algorithm in correlation measure space, Correlation Discriminant Analysis (CDA). In this framework, based on the definitions of within-class correlation and between-class correlation, the optimum transformation can be sought for to maximize the difference between them, which is in accordance with good classification performance empirically. Under different cases of the transformation, different implementations of the algorithm are given. Extensive empirical evaluations of CDA demonstrate its advantage over alternative methods.

Discriminant analysis in correlation similarity measure space

This paper presents a high performance ........ pose estimation system based on the newly-proposed sparse Bayesian regression technique (Relevance Vector Machine, RVM) and sparse representation of facial patterns. In our system, after localizing 20 key facial points, sparse features of these points are extracted to represent facial property, and then..RVM is utilized to learn the relation between the sparse representation and yaw and pitch angle. Because RVM requires only a very few kernel functions, it can guarantee better generalization, faster speed and less memory in a practical implementation. To thoroughly evaluate the performance of our system, we compare it with conventional methods such as CCA, Kernel CCA, SVR on a large database; In experiments, we also investigate the influence of the facial points localization error on pose estimation by using manually labelled results and automatically localized results separately, and the influence of different features on pose estimation such as geometrical features and texture features. These experimental results demonstrate that our system can estimate face pose more accurately, robustly and fast than those based on conventional methods.

Sparse Bayesian Regression for Head Pose Estimation

Vocabulary tree-based method is one of the most popular methods for content-based image retrieval due to its efficiency and effectiveness However, for existing vocabulary tree methods, the retrieval precision in large scale image database has never been acceptable especially for image datasets with high variations In this paper, we propose a novel tree fusion framework: Feature Forest, utilizing and fusing different kind of local visual descriptors to achieve a better retrieval performance In the offline-learning stage, our framework first establishes different feature vocabulary trees based on different features and uses the average covariance to build vocabulary tree adaptively In the online-query stage, we use the ratio of the resulting score to the standard score to fuse retrieval results of each vocabulary tree adaptively The evaluations show the effectiveness of our approach compared with single vocabulary-tree based methods on different databases.

Scalable image retrieval based on feature forest

Linear Discriminant Analysis (LDA) is frequently used for dimension reduction and has been successfully utilized in many applications, especially face recognition. In classical LDA, however, the definition of the between-class scatter matrix can cause large overlaps between neighboring classes, because LDA assumes that all classes obey a Gaussian distribution with the same covariance. We therefore, propose an adaptive nonparametric discriminant analysis (ANDA) algorithm that maximizes the distance between neighboring samples belonging to different classes, thus improving the discriminating power of the samples near the classification borders. To evaluate its performance thoroughly, we have compared our ANDA algorithm with traditional PCA+LDA, Orthogonal LDA (OLDA) and nonparametric discriminant analysis (NDA) on the FERET and ORL face databases. Experimental results show that the proposed algorithm outperforms the others.

Yong Ma

Papers

Person-Specific SIFT Features for Face Recognition

Discriminant analysis in correlation similarity measure space

Sparse Bayesian Regression for Head Pose Estimation

Scalable image retrieval based on feature forest

An adaptive nonparametric discriminant analysis method and its application to face recognition