Creature Recognition and Identitication by Image Processing Based on Expert System for Control of a Micromanipulator

Abstract

This paper describes an automatic organism recognition and identification method, using image processing based on an expert system for application in a micromanipulator system. Since organisms under a microscope all appear different, are in motion and have time-dependent shapes, the conventional pdttem-matching method used for industrial products can hardly be applied. The proposed new method is based on segmentation of the organism images (organism image segmentation method; OISM) and takes advantage of characteristic segment features which are independent of individual size and length. Their complicated shapes are divided into basic shape segments (defined in this paper), such as lines, circles, and ovals. The relations between segments are analyzed and described automatically in the data base of the expert system. Organisms can then be expressed simply in a set of segments their individual differences can be avoided. Tracking the movement of an organism by its image is also shown in thid paper. The effectiveness of this method is confirmed by experimental results.