The Research On Surface Defect Inspection Of Micro-Components

A new approach based on visual attention mechanism was proposed to improve the accuracy and reliability of surface defect detection for industrial product quality control. According to biological structure and function of human visual system, a detection model was built combining multiple scales and frequencies of many filters with multichannel and multifrequency of human visual system. The multichannel representation of the image was obtained through a bank of many filters, corresponding to multiple scales and multiple orientations, full wave rectification of each channel and contrast gain control among the channels were performed sequentially to get orientation feature maps with multiple scales and multiple orientation, the called salient map was the linear combination of these orientation feature maps. The paper obtains the image identification, classification, defect extraction.The paper designs a automatic inspection system, which could high speed and high resolution inspection.