Computer Vision Inspection for IC Wafer Based on Character of Pixels Distribution

There are many vital defects in the process of fabrication of IC wafer. The redundancy material defect is an important factor of reducing the yield of IC, it mainly causes circuits to be connection failure, so it is important to recognize the redundancy material defect and ascertain the circuit´s failure style. In this paper, a simple and doable method of vision inspection for the redundancy material defect is presented. According to the image character of taken images, in order to improve image quality, the method of light compensation and morphological filter is used to eliminate the disturbed noise. Then, the projection theorem and the inspection method based on character of pixels distribution are used to recognize the connection circuits.