Machine vision based online detection of PCB defect

• Published in: Microprocessors and microsystems Vol. 82; p. 103807
• Main Authors: Liu, Zhichao, Qu, Baida
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier B.V 01.04.2021; Elsevier BV
• Subjects: Algorithms; Color imagery; Defect detection; Design defects; Design optimization; Image contrast; Image enhancement; Image management; Image quality; Image retrieval; Inspection; Machine vision; Mathematical analysis; Mathematical morphology; Morphology; Object recognition; Pattern recognition; PCB defect; Sharpening; Vision systems; Visual detection algorithm; Machine vision; Visual detection algorithm; Mathematical morphology; PCB defect; Defect detection
• ISSN: 0141-9331; 1872-9436
• DOI: 10.1016/j.micpro.2020.103807

The traditional PCB defect on-line detection has the problems of long detection time and poor accuracy of detection results. Therefore, a key technology of PCB defect online detection based on machine vision is proposed. Firstly, image retrieval is carried out by using visual detection algorithm, image smoothing, image contrast enhancement, image sharpening and other preprocessing operations are carried out by using gray-scale transformation algorithm to simplify the operation process and improve the image quality; secondly, PC is analyzed B. the causes and types of defects. The original color image is processed and binarized by the hybrid recognition method of mathematical morphology and pattern recognition. Then the reference image obtained by mathematical morphology method is used as a template for system self inspection. Finally, the image aberration detection algorithm is introduced to segment the threshold value of PCB defect image, remove redundant points and mark PCB image defect recognition results, improve the visual detection algorithm and optimize the hardware design to achieve PCB image defect detection and recognition. The experimental results show that the method has high detection accuracy and short detection time, and can effectively control the stable operation of the online detection system, which provides a reference for related research in this field.