1 March 1990 On the Recognition-by-Components Approach Applied to Computer Vision
Author Affiliations +
Proceedings Volume 1192, Intelligent Robots and Computer Vision VIII: Algorithms and Techniques; (1990) https://doi.org/10.1117/12.969722
Event: 1989 Symposium on Visual Communications, Image Processing, and Intelligent Robotics Systems, 1989, Philadelphia, PA, United States
Abstract
The human visual system is usually able to recognize objects as well as their spatial relations without the support of depth information like stereo vision. For this reason we can easily understand cartoons, photographs and movies. It is the aim of our current research to exploit this aspect of human perception in the context of computer vision. From a monocular TV image we obtain information about the type of an object observed in the scene and its position relative to the camera (viewpoint). This paper deals with the theory of human image understanding as far as used in this system and describes the realization of a vision system based on these principles.
© (1990) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H. Bassmann, H. Bassmann, Ph. W. Besslich, Ph. W. Besslich, } "On the Recognition-by-Components Approach Applied to Computer Vision", Proc. SPIE 1192, Intelligent Robots and Computer Vision VIII: Algorithms and Techniques, (1 March 1990); doi: 10.1117/12.969722; https://doi.org/10.1117/12.969722
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT

The Use of Projection to Extract Range Map
Proceedings of SPIE (February 28 1990)
Interweaving reason, action, and perception
Proceedings of SPIE (October 31 1992)

Back to Top