Robot vision by a contour sensor with associative memory

作者:

Highlights:

摘要

Advancing automation can only cope with the rising cost of labour.For visual inspection a minicomputer sustained optical contour sensor checks automatically whether all contours of an assembled part are present and lie within prefixed tolerances.Automation of welding or machining often requires high precision feeding of parts, causing prohibitive costs and thus rendering automation uneconomical. The optical contour sensor catches edges without mechanical contact and controls the machining or welding process relative to these edges.With associative retrieval of data stored in a training phase, the contour sensor recognizes and positions straight parts in arbitrary orientations on a conveyor belt, even if they touch and partly cover each other. This allows automation of many pick-and-place operations at the inputs of automated production lines.

论文关键词:Contour detection,Pattern recognition,Graph structures,Visual inspection,Robot vision

论文评审过程:Received 10 February 1983, Revised 6 May 1983, Available online 19 May 2003.

论文官网地址:https://doi.org/10.1016/0031-3203(84)90044-X