Flexible circuit board defect detection method based on skeleton generation and fusion configuration

• Main Authors: HU YILONG, ZHAO XINYUE, HE ZAIXING
• Format: Patent
• Language: Chinese; English
• Published: 29.09.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention discloses a flexible circuit board defect detection method based on skeleton generation and fusion configuration. The method comprises the following steps: firstly, acquiring a real defect-free template image of the flexible circuit board; then, a Gerber file of a production file of the flexible circuit board is analyzed and converted to form a virtual defect-free template image; and then flexible circuit board surface defects with different characteristics and sizes are constructed through skeleton generation and defect configuration. Thirdly, performing offline color enhancement on the defect-free template image, and performing defect data image fusion configuration to obtain a defect data image; and finally, constructing a data set in combination with the defect information, and training the deep neural network model so as to carry out defect detection on the flexible circuit board. Compared with the prior art, the method has the advantages that the problems of few defect samples and long acq