| abstract |
The invention discloses a fabric defect detection method based on a genetic algorithm optimized neural network, and belongs to the field of data processing. The invention includes: initializing Gabor filtering parameters; collecting fabric defect images; marking to obtain defect categories and borders containing defects, and establishing a PascalVOC data set; sending the PascalVOC data set into a Faster-RCNN network training model for training, and calculating mAP; As the fitness function of the genetic algorithm, mutation, crossover and selection are performed to obtain the Gabor parameters of the offspring until the number of iterations reaches the set maximum value, and the optimal genotype, that is, the optimal filtering parameters of the fabric defect image, is output; the corresponding Faster‑ The RCNN model outputs the location, type and accuracy of fabric defects. The invention can well separate the defect from the background, and the fabric detection model has high accuracy and good versatility for defect detection. |