Automated vision positioning system for dicing semiconductor chips using improved template matching method

This study proposes an automated vision positioning system to realize high-efficient and high-precision positioning and dicing of semiconductor chips in an automatic dicing saw. In this method, image pyramid construction was established to improve the searching speed of feature images by using the pyramid hierarchical search strategy. Hough transformation was used to obtain the approximate angle of the feature images of the semiconductor chips. The improved template matching approach based on the initial angle was proposed to rapidly calculate rotation angle and feature position. Polynomial fitting was adopted to achieve sub-pixel positioning accuracy. Experimental results showed that the proposed algorithm can realize high-precision and real-time recognition under the weak light, strong light, uneven illumination, and rotation angle. The success rate is 99.25%, and the time consumed is only 1/4 of the normalized cross-correlation algorithm. The vision positioning and dicing experiment of the semiconductor chips was carried out on a high-precision dicing saw. The results confirm that the improved algorithm could be used for high-precision and real-time dicing semiconductor chips.