TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture,Layout, and Context

This paper details a new approach for learning a discriminative model of object classes, incorporating texture, layout, and context information efficiently. The learned model is used for automatic visual understanding and semantic segmentation of photographs. Our discriminative model exploits texture-layout filters, novel features based on textons, which jointly model patterns of texture and their spatial layout. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating the unary classifier in a conditional random field, which (i) captures the spatial interactions between class labels of neighboring pixels, and (ii) improves the segmentation of specific object instances. Efficient training of the model on large datasets is achieved by exploiting both random feature selection and piecewise training methods. High classification and segmentation accuracy is demonstrated on four varied databases: (i) the MSRC 21-class database containing photographs of real objects viewed under general lighting conditions, poses and viewpoints, (ii) the 7-class Corel subset and (iii) the 7-class Sowerby database used in He et al. (Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 695–702, June 2004), and (iv) a set of video sequences of television shows. The proposed algorithm gives competitive and visually pleasing results for objects that are highly textured (grass, trees, etc.), highly structured (cars, faces, bicycles, airplanes, etc.), and even articulated (body, cow, etc.). J. Shotton is now working at Toshiba Corporate Research & Development Center, Kawasaki, Japan.     

Pose-Invariant Facial Expression Recognition Using Variable-Intensity Templates

In this paper, we propose a method for pose-invariant facial expression recognition from monocular video sequences. The advantage of our method is that, unlike existing methods, our method uses a simple model, called the variable-intensity template, for describing different facial expressions. This makes it possible to prepare a model for each person with very little time and effort. Variable-intensity templates describe how the intensities of multiple points, defined in the vicinity of facial parts, vary with different facial expressions. By using this model in the framework of a particle filter, our method is capable of estimating facial poses and expressions simultaneously. Experiments demonstrate the effectiveness of our method. A recognition rate of over 90% is achieved for all facial orientations, horizontal, vertical, and in-plane, in the range of ±40 degrees, ±20 degrees, and ±40 degrees from the frontal view, respectively. Electronic Supplementary Material  The online version of this article () contains supplementary material, which is available to authorized users.     

Optimal Local Basis: A Reinforcement Learning Approach for Face Recognition

This paper presents a novel learning approach for Face Recognition by introducing Optimal Local Basis. Optimal local bases are a set of basis derived by reinforcement learning to represent the face space locally. The reinforcement signal is designed to be correlated to the recognition accuracy. The optimal local bases are derived then by finding the most discriminant features for different parts of the face space, which represents either different individuals or different expressions, orientations, poses, illuminations, and other variants of the same individual. Therefore, unlike most of the existing approaches that solve the recognition problem by using a single basis for all individuals, our proposed method benefits from local information by incorporating different bases for its decision. We also introduce a novel classification scheme that uses reinforcement signal to build a similarity measure in a non-metric space. Experiments on AR, PIE, ORL and YALE databases indicate that the proposed method facilitates robust face recognition under pose, illumination and expression variations. The performance of our method is compared with that of Eigenface, Fisherface, Subclass Discriminant Analysis, and Random Subspace LDA methods as well.     

Action Recognition Using a Bio-Inspired Feedforward Spiking Network

We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (Proceedings of the 11th international conference on computer vision, pp. 1–8, 2007) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience.     

Median MSD-based method for face recognition

An improved maximum scatter difference (MSD) criterion is proposed in this paper. A weakness of existing MSD model is that the class mean vector in the expressions of within-class scatter matrix and between-class scatter matrix is estimated by class sample average. Under the non-ideal conditions such as variations of expression, illumination, pose, and so on, there will be some outliers in the sample set, so the class sample average is not sufficient to provide an accurate estimate of the class mean using a few of given samples. As a result, the recognition performance of traditional MSD model will decrease. To address this problem, also to render MSD model rather robust, within-class median vector rather than within-class mean vector is used in the original MSD method. The results of experiments conducted on CAS-PEAL and FERET face database indicate the effectiveness of the proposed approach.     

Expertise and Intuition: A Tale of Three Theories

Several authors have hailed intuition as one of the defining features of expertise. In particular, while disagreeing on almost anything that touches on human cognition and artificial intelligence, Hubert Dreyfus and Herbert Simon agreed on this point. However, the highly influential theories of intuition they proposed differed in major ways, especially with respect to the role given to search and as to whether intuition is holistic or analytic. Both theories suffer from empirical weaknesses. In this paper, we show how, with some additions, a recent theory of expert memory (the template theory) offers a coherent and wide-ranging explanation of intuition in expert behaviour. It is shown that the theory accounts for the key features of intuition: it explains the rapid onset of intuition and its perceptual nature, provides mechanisms for learning, incorporates processes showing how perception is linked to action and emotion, and how experts capture the entirety of a situation. In doing so, the new theory addresses the issues problematic for Dreyfus’s and Simon’s theories. Implications for research and practice are discussed.

Complete discriminant evaluation and feature extraction in kernel space for face recognition

This work proposes a method to decompose the kernel within-class eigenspace into two subspaces: a reliable subspace spanned mainly by the facial variation and an unreliable subspace due to limited number of training samples. A weighting function is proposed to circumvent undue scaling of eigenvectors corresponding to the unreliable small and zero eigenvalues. Eigenfeatures are then extracted by the discriminant evaluation in the whole kernel space. These efforts facilitate a discriminative and stable low-dimensional feature representation of the face image. Experimental results on FERET, ORL and GT databases show that our approach consistently outperforms other kernel based face recognition methods.

Machine learning multi-classifiers for peptide classification

In this paper, we study the performance improvement that it is possible to obtain combining classifiers based on different notions (each trained using a different physicochemical property of amino-acids). This multi-classifier has been tested in three problems: HIV-protease; recognition of T-cell epitopes; predictive vaccinology. We propose a multi-classifier that combines a classifier that approaches the problem as a two-class pattern recognition problem and a method based on a one-class classifier. Several classifiers combined with the “sum rule” enables us to obtain an improvement performance over the best results previously published in the literature.

A hybrid approach for identification of concurrent control chart patterns

Control chart patterns (CCPs) are widely used to identify the potential process problems in modern manufacturing industries. The earliest statistical techniques, including chart and R chart, are respectively used for monitoring process mean and process variance. Recently, pattern recognition techniques based on artificial neural network (ANN) are very popular to be applied to recognize unnatural CCPs. However, most of them are limited to recognize simple CCPs arising from single type of unnatural variation. In other words, they are incapable to handle the problem of concurrent CCPs where two types of unnatural variation exist together within the manufacturing process. To facilitate the research gap, this paper presents a hybrid approach based on independent component analysis (ICA) and decision tree (DT) to identify concurrent CCPs. Without loss of generality, six types of concurrent CCPs are used to validate the proposed method. Experimental results show that the proposed approach is very successful to handle most of the concurrent CCPs. The proposed method has two limitations in real application: it needs at least two concurrent CCPs to reconstruct their source patterns and it may be incapable to handle the concurrent pattern incurred by two correlated process (“upward trend” and “upward shift”).     

基于校准靶的C形臂相机模型自动校准方法

根据校准靶标志点影像的特点,提出一种自动的离线C形臂相机模型校准方法。应用聚类算法实现标志点信息的自动识别,通过行列索引表简化标志点网格姿态的识别,自动建立标志点在影像坐标系和空间坐标系下坐标的对应关系,经几何变形校正后,实现C形臂相机的校准。实验数据证明,该方法具有良好的鲁棒性,误差小于1 mm,可应用于基于术中C形臂X线影像的手术导航系统。