Cherry Recognition Based on Color Channel Transform

摘要

Cherry recognition is the key technology of vision system of cherry picking robot. The image processing function in Open CV is used to segment the mature cherry image taken under natural lighting conditions. In this paper, the RGB color channel is converted into the M channel algorithm in CMYK mode to increase the contrast between the fruit and the background, and then the binarization process is realized by threshold segmentation to obtain the segmentation result. Regarding the noise removal part, the morphological filtering opening and closing operation is used to eliminate other noise of the image. On this basis, Canny edge detection is performed and the contour is searched, and finally the contour is displayed. The experimental results show that the algorithm based on color channel transformation has the advantages of high efficiency and stability, and can meet the requirements of cherry fruit recognition. This algorithm creates good preconditions for the next step of positioning and picking.