lAPR Workshop on CV-Special Hardware and Industrial Applications OCT.12-14, 1988, Tokyo A NEW SCHEME FOR PRACTICAL FLEXIBLE AND INTELLIGENT VISION SYSTEMS

We propose a new scheme for practical vision systems which are simple in structure, directly and adaptively trainable for various purposes. The feature extraction consists of two stages: At first, general and primitive features which are shift-invariant and additive are extracted over the retinal image plane. Then those features are linearly combined on the bases of multivari-ate analysis methods so as to provide new effective features for each task. Such a system can adaptively and automatically learn the task from the given supervised training examples and show an intelligent performance. Some examples of practical applications to object recognition and measurements are exper-imentally shown. which is simple in structure and directly and a d a p tively trainable for various purposes. The basic idea is similar to Perceptron [I] or neural networks (for example, see 12)) but more practical being based on closed-form solutions for statistical performance cri-teria without employing such slow iterative learning processes. The basic idea of the system has already been pre-sented in [3] and registered as patents (for example, [4]). A hardware implementation (named AISS) has been developed in cooperation with OKK Inc. and the detail will be presented in a different paper [5] to-gether with actual demonstration at this conference