Surface defect detection of carbon fiber prepreg based on image processing

With the application of automatic laying technology in the aerospace field more and more widely, how to ensure the laying quality of components in the laying process has become one of the focus issues. So far, the defect detection of carbon fiber pre rubber materials are mainly artificial vision, which has low detection efficiency, high false detection rate and missed detection rate, and high labor intensity, which is unfavorable to workers. Therefore, the research of automatic defect detection based on machine vision is of great significance. In this paper, the actual collected carbon fiber prepreg image was taken as the research object, and a detection method of carbon fiber prepreg defect based on Gabor filter based on scale transformation was proposed. The image texture compression algorithm proposed in this paper was used to determine the final defect area by setting the threshold value. By adjusting the parameter value to 1, the best image segmentation result is obtained.