Research on Appearance Quality of Nectarine Based on Machine Vision

Aiming at the problem of complex surface defect types of nectarines and low efficiency of manual sorting, a surface defect detection method based on pseudo color color space features is proposed. First, image acquisition is carried out for nectarines to be detected through the image acquisition platform, and the acquired image is denoised by linear gray-scale transformation and bilateral filtering. Then, the principle of gray-scale image color space conversion is used to transform it into pseudo color color space, and the pseudo color enhancement method is adopted to further increase the discrimination between defects and non defects, and the defect area is obtained by otsu threshold segmentation. Finally, the influence of non defect area is removed by mathematical morphology processing. The experiment is simulated in MATLAB software, and the experimental results show that the method has high recognition and segmentation ability for surface defects of nectarines of various quality levels.