For automatic lipreading, there are many competing methods for feature extraction. Often, because of the complexity of the task these methods are tested on only quite restricted datasets, such as the letters of the alphabet or digits, and from only a few speakers. In this paper we compare some of the leading methods for lip feature extraction and compare them on the GRID dataset which uses a co...

visual stimulation with precise control of stimulus has transformed the field of psychophysics since the introduction of personal computers. luminance and chromatic features of stimulus, timing, and position of the stimulus are the main features that could be defined using programs written specifically for psychophysical experiments. in this manuscript, software used for the psychophysical expe...

In this work we present the computational algorithm that combines perceptual and cognitive information during the visual search for object features. The algorithm is initially driven purely by the bottomup information but during the recognition process it becomes more constrained by the top-down information. Furthermore, we propose a concrete model for integrating information from successive sa...

A system is developed that can learn semantics of words from the visual features extracted from an agent’s perceptual environment. The system is given a static visual scene paired with true statements describing the scene in natural language. When given a novel static scene, the system is able to output the words associated with that scene.

When using visual video features in an interactive video index environment, it is necessary to visualize the meaning and impact of features to people that are not image processing experts, such as video librarians. Projection of feature values on the original video data is an important method to visualize the relation between the feature and the video. We describe the characteristics of feature...

This paper addresses the problem of automatic synthesis of visual detectors. We present a method using genetic techniques to learn visual features and a program which combines and integrates the features in non-linear ways. The method is integrated in a face tracking system to generate a variety of new visual perceptual processes.