1 January 1987 Recognition Of Partially Occluded Workpieces By A Knowledge-Based System
Author Affiliations +
Proceedings Volume 0858, Signal Acquisition and Processing; (1987) https://doi.org/10.1117/12.968292
Event: IECON, Cambridge, 1987, Cambridge, MA, United States
A knowledge-based system is presented that is oriented toward partially occluded 2-D workpiece recognition in TV camera images. The generalized Hough transform is employed to extract elementary edge patterns. Intrinsic and relational information regarding elementary patterns is computed and then stored inside a net of frames. A similar net of frames is employed for workpiece model representation, for an easy matching with the previous net. A set of production rules provide the heuristics to find hints for locating focus-of-attention regions, while other production rules specify modalities for applying a hypothesis-generation-and-test process. Experimental results on a set of 20 workpieces are reported.
© (1987) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
S. B. Serpico, S. B. Serpico, G. Vernazza, G. Vernazza, S. Dellepiane, S. Dellepiane, P. Angela, P. Angela, } "Recognition Of Partially Occluded Workpieces By A Knowledge-Based System", Proc. SPIE 0858, Signal Acquisition and Processing, (1 January 1987); doi: 10.1117/12.968292; https://doi.org/10.1117/12.968292


Back to Top