Defects detection of mobile phone touch screen circuit based on machine vision

At present, the defects detection of mobile phone touch screen circuit still depends on the artificial visual inspection, and the development of a mobile phone touch screen circuit defects detection system based on machine vision can realize the automatic detection of the mobile phone touch screen circuit. In the image processing, the binary image is gotten by the Maximum Between-Class Variance algorithm (Otsu Method), and some connected regions are marked through the Breadth First Search (BFS) algorithm. Then the image denoising used Blob analysis. An algorithm based on the analysis of local connectivity is proposed to search and locate defects of a short circuit, short broken circuit, and microfracture. Morphological method and fast circuit calculation method based on normal is used to detect and distinguish circuit defects of lateral erosion. The experimental results show that the system can detect and distinguish various defects of mobile phone touch screen circuit more accurately and quickly, and has a good application prospect.