A color selection method for crops based on machine vision

The traditional crop classification uses artificial method all along, which has high cost and low efficiency. An automatic sorting method based on machine vision is proposed in this paper. Firstly, the non-uniformity correction of the CCD original signal is performed. Then the correction signal is converted from RGB color space to HSV space. The floodfill algorithm can obtain target pixel threshold value. The threshold segmentation data of the HSV color space is used to extract the target material. Finally all the pixels of the full image are divided to determine the location of the target material. The purpose of sorting the color and size of the material is achieved.