Research on Image Segmentation for Identification of Surface Mount Components

In conventional inspection algorithms, thresholds are usually decided by estimation during several experiments. The decision made by this labor intensive, and therefore costly, procedure often also involves subjective judgments. A thresholding algorithm based on mean-pseudo-trough is proposed taking full consideration of the characteristics of surface mount components. By introducing pseudo-troughs in the local neighbor of peaks and averaging these troughs, local domain features of pixels are taking into consideration. The algorithm is verified on 180 images of three types of surface mount components. The experimental results show that the algorithm is simple and fast, the resulting threshold leads to good image segmentation.