Real-Time Contour Vectorizer For Greylevel Images

Abstract

A real -time VME -bus preprocessor is presented for the extraction of a symbolic scene description from greylevel images. The hardwired pipeline processor consists of two stages. The first stage extracts the thinned greylevel contours using the local edge direction and a novel gradient maximum tracker which does not rely on thresholding. The second stage of the contour vectorizer breaks down the pixel -based contour image into a set of vectors describing the contours in terms of straight -line polygones.

A vision guided life-science laboratory robot

“…Given that the XYZ system will take around 13s to pick, transfer and deposit material from a single plaque, the two subsystems are well matched when operating at 5-10 plaques per dish, which is in the expected operating range (Courtney 1989). Alternative, real-time image processing techniques, involving large kernal convolvers and HIS colour space classifiers have been applied to the same task by our co-researchers at the TCCIP (Massen et al 1988). APSCIR has also been investigated as a colony harvesting machine for assisting in the isolation of antibiotic producers for the pharmaceutical industry.…”