The image of an opaque object is created by observing the reflection of the light incident on its surface. The dichromatic reflection model describes the surface reflection as the sum of two components, diffuse and specular terms. The specular reflection component is usually strong in its intensity and polarized significantly compared to the diffuse components. On the other hand, the intensity of the diffuse component is weak and it tends to be unpolarized except near occluding contours. Thus, the observation of an object through a rotating polarizer approximately yields images containing constant diffuse component and specular component of different intensity. In this paper, we show that diffuse and specular components of surface reflection can be separated as two independent components when we apply Independent Component Analysis to the images observed through a polarizer of different orientations. We give a separation simulation of artificial data and also give some separation results of real scenes.

This paper presents a face matching method through information theoretical attention points. The attention points are selected as the points where the outputs of Gabor filters applied to the contrast-filtered image (Gabor features) have rich information. The information value of Gabor features of the certain point is used as the weight and the weighed sum of the correlations is used as the similarity measure for the matching. To cope with the scale changes of a face, several images with different scales are generated by interpolation from the input image and the best match is searched. By using the attention points given from the information theoretical point of view, the matching becomes robust under various environments. This matching method is applied to face detection of a known person and face classification. The effectiveness of the proposed method is confirmed by experiments using the face images captured over years under the different environments.

A human continuously directs his eyes toward interesting points to recognize an object. Such eye movement or visual attention plays an important role in human vision. To simulate such eye movements, the paper proposes a virtual active vision head with binocular fish-eye lenses. Moving objects are detected within the wide angle of view obtained through the fish-eye lens by comparing the input image with the background image estimated by an adaptive M-estimator. The location of the moving object is used as a visual cue to achieve the saccadic eye movement. The proposed virtual active vision system was implemented on a PC cluster. Two PCs are used to capture images through the left and right fish-eye lenses and a PC with four processors is used for image processing. Real time gaze control is achieved on the proposed virtual binocular active vision system.

We propose MICA (multimodal independent component analysis) that extends ICA (independent component analysis) to the case that there is a pair of information sources. MICA extracts statistically dependent pairs of features from the sources, where the components of feature vector extracted from each source are independent. Therefore, the cost function is constructed to optimize this degree of pairwise dependence as well as optimizing the cost function of ICA. We approximate the cost function by two dimensional Gram-Charlier expansion and propose a gradient descent algorithm derived by Amari's natural gradient The relation between MICA and traditional CCA (canonical correlation analysis) is similar to the relation between ICA and PCA (principal component analysis).

The problem of recognizing and localizing objects that can vary in parameterized ways is considered. To achieve this goal, a concept of parameterized point pattern is introduced to model parameterized families of such objects, and a parameterized point pattern matching algorithm is proposed. A parameterized point pattern is a very flexible concept that can be used to model a large class of parameterized objects, such as a pair of scissors with rotating blades. The proposed matching algorithm is formulated as a tree search procedure, and it generates all maximum matchings satisfying a condition called delta -boundedness. Several pruning methods based on the condition of delta -boundedness and their efficient computing techniques are given. The proposed matching algorithm is applied to a real shape matching problem in order to check the validity of the approach.>

In many applications of computer vision, the following problem is encountered. Two point patterns (sets of points) (x/sub i/) and (x/sub i/); i=1, 2, . . ., n are given in m-dimensional space, and the similarity transformation parameters (rotation, translation, and scaling) that give the least mean squared error between these point patterns are needed. Recently, K.S. Arun et al. (1987) and B.K.P. Horn et al. (1987) presented a solution of this problem. Their solution, however, sometimes fails to give a correct rotation matrix and gives a reflection instead when the data is severely corrupted. The proposed theorem is a strict solution of the problem, and it always gives the correct transformation parameters even when the data is corrupted.>

An approximate solution to the weighted-graph-matching problem is discussed for both undirected and directed graphs. The weighted-graph-matching problem is that of finding the optimum matching between two weighted graphs, which are graphs with weights at each arc. The proposed method uses an analytic instead of a combinatorial or iterative approach to the optimum matching problem. Using the eigendecompositions of the adjacency matrices (in the case of the undirected-graph-matching problem) or Hermitian matrices derived from the adjacency matrices (in the case of the directed-graph-matching problem), a matching close to the optimum can be found efficiently when the graphs are sufficiently close to each other. Simulation results are given to evaluate the performance of the proposed method.>

A logic programming language offers several kinds of parallelism for its execution. Among these, this paper concentrates on OR-parallelism which is an alternative to the backtracking mechanism of a serial interpreter, and proposes an abstract model for OR-parallel interpretation. It consists of tokens and five kinds of function units mutually connected as a process graph. The overall processing is done by the flows of tokens among these units. We also present a mechanism for token labeling, which makes this process graph reentrant. A simulation result is given to show how efficiently the model works in terms of parallelism.