A low-cost vision system combining conventional and artificial intelligence techniques for complex image inspection and verification

Abstract

A hybrid image processing technique is described which combines traditional feature extraction and windowing with a new artificial intelligence technique based on weightless neural networks. This technique is a unique way of compressing and then analysing complex data. Described here is its application to the measuring of light scattered for machine surfaces as well as the inspection of complex and highly coloured images. These examples illustrate the distinctive nature of the system. It is called WISE (Windowed Image Shaped Extraction) because it describes the stages of image processing.

Notes

‡ To whom correspondence should be addressed.