Deborah Walters

Selection of image primitives for general-purpose visual processing

The results of psychophysical experiments suggest the existence of a hierarchy of visual features based on the relations between image contours. The human visual system appears to be preattentively, selectively sensitive to image contours which contain certain of these features. These results can be used to develop computer vision algorithms for: (1) the selective enhancement of image contours which correlate with their perceptual significance; and (2) the segmentation of boundary images into sets which have a high probability of depicting a single object. The extreme simplicity of the algorithms, as well as their ability to generate perceptually significant results, demonstrate the advantages of using psychophysical results to uncover image invariants which correlate with the structure of the physical world that is of value for visual perception.

Embodied interaction in social virtual environments

The interaction models found in typical desktop virtual environments designed for social interactions need to be improved in order to provide an adequate sense of embodiment and appropriate levels of abstraction for collaborative tasks. In order to improve the kinds of user interfaces available in social desktop virtual environments, new mechanisms for embodied interaction are needed. Such mechanisms would allow the dynamic generation of user interface displaying currently available high-level actions that can be performed on objects. This paper evaluates the kinds of interactions currently available in social desktop virtual environments, explores how these interactions effect the end-user experience, and suggests possible solutions for improving a users sense of embodiment and presence in such environments.

The Dynamics of Recurrent Behavior Networks

If behavior networks, which use spreading activation to select actions, are analogous to connectionist methods of pattern recognition, then we suggest that recurrent behavior networks, which use energy minimization, are analogous to Hopfield networks. Hopfield networks memorize patterns by making them attractors. We argue that, similarly, each behavior of a recurrent behavior network should be an attractor of the network, to inhibit fruitless, repeated switching between different behaviors in response to small changes in the environment and in motivations. We demonstrate that the performance in a test domain of the Do the Right Thing recurrent behavior network is improved by redesigning it to create desirable attractors and basins of attraction. We further show that this performance increase is correlated with an increase in persistence and a decrease in undesirable behavior switching.

General Ribbons

General ribbons are presented as a mathematical model of stylus-generated images which is based on the image formation process. One purpose of the model is to provide a formal basis for the development of thinning algorithms for the stroke components of stylus-generated images. Before the stroke components can be thinned they must be segmented from the blob components of the image, which do not require thinning. The second purpose of the model is to provide a formal basis for the development of blob/stroke segmentation algorithms. Two blob/stroke segmentation algorithms based on the model are presented.

General Ribbon-Based Thinning Algorithms for Stylus-Generated Images

Thinning algorithms for stylus-generated images are presented which are based on the general ribbon model of stylus-generated images. These algorithms have several advantages over existing thinning algorithms, including the existence of a formal specification of the desired output of a thinning algorithm; the preservation of image features which have been shown to be the most perceptually significant for the human perception of stylus-generated images; and the ability to deal easily with images which contain both stroke and blob objects.

Object Interpretation Using Boundary Based Perceptually Valid Features

An important perceptual task for both human and machine vision is to be able to interpret images in terms of distinct objects. This paper presents a technique for object interpretation in line drawings. The method is based on the use of features which have special perceptual significance for human vision. By using such features, and by devising an orientation-boundary representation, a simple, efficient algorithm can be used to interpret line drawings which can contain both straight and curved lines, and can depict any type of object.

Integration Of Detector Responses For Texture Segmentation

Machine vision algorithms designed to model the human preattentive perception of texture boundaries often define the texture of a region on the basis of a single perceptual property. In addition, humans can segment textures even when the regions are spatially non-homogeneous in the texture properties of the primitive texture elements. This paper proposes a model of texture segmentation, and a texture segmentation algorithm based on the model, which can produce segmentations which agree with human perception.

Automated Fake Color Separation: Combining Computer Vision And Computer Graphics

A system is described for the automation of the color separation process. In current color separation systems, humans must visually segment line-art images, and using pen and ink, delineate the segments in a manner that enables a computer graphics system to be used interactively to color in each segment. The goal of this research was to remove the labor-intensive human visual segmentation, by adding rudimentary visual processing capabilities to the computer graphics system. This is possible through the use of computer vision algorithms which incorporate general knowledge about line-art, and are based on image features that are used by the human visual system in the early stages of visual processing. A major color separation company is planning the hardware implementation of a vision-graphics system based on these algorithms, and the State University of New York is applying for two patents based on this research.

Teaching using off-the shelf on-line materials

The use of off-the-shelf on-line materials presents several challenges. In this session panelists report on their experiences in evaluating, installing and using such materials. Both positive and negative aspects of such use are discussed. The aim of the session is to provide useful information to those considering using (and those already using) on-line materials in their teaching. The session presents information in three mini-presentations, followed by a general discussion session.