山竹的计算机视觉分级方法

grading method of mangosteen by size and color was proposed based on computer vision. Taking the blue rollers as background in mangosteen images, the images were pre-segmented by double thresholds in RGB color space. After using morphological operation, contour trace and region fill, the whole mangosteen target was obtained. Lastly, the peduncle, pedicel and pericarp were identified by 2G-R-B and G factors. According to the centroid of peduncle and pedicel and the centroid of pericarp, the fruit posture was judged, and the diameter was extracted as the size grading criteria. Meanwhile, the difference between Saturation and Hue of pericarp area in HIS color space was the color grading criteria. A grading experiment was carried out by 200 mangosteens. The results indicated that the accuracy of diameter measurement was ±1.8 mm, and the maximal scale of neighbor grade mixed by color was 10.2%.