A Vision Defect Detection Algorithm based on Topological Mapping for High -Resolution Flexible Integrated Circuit Substrates

The conventional methods of visual defect detection heavily rely on the standard templates and features of an image. But the standard templates are difficult to obtain or even don't exist in many application fields, especially for the flexible Integrated Circuit (IC) substrates based on micro vision. To find a solution for the above problems, the authors have proposed a novel defect detection approach based on topology mapping. Firstly, topological mapping on the pixel values of the image is performed to remove the noise. Then, a morphological operation is used to clear small spots. Furthermore, binarization is introduced to display the defect of corrosion and remove the black background and surface texture structure of the substrate image. The experiments are implemented to prove that the proposed method has higher Peak Signal to Noise Ratio and produces better quality of image, which confirms the efficiency of the proposed algorithm.