Based on the traditional experience of liquor-receiving according to liquor hop, Computer vision is used instead of human eyes, the video images of liquor-receiving is captured by CCD, and the images of hops with different liquor degrees are preprocessed by histogram equalization and image corrosion to eliminate the influence of high light noise. Then hops contour is compared with different edge detection algorithms. Besides, the combination of OTSU algorithm and Canny edge detection algorithm can better realize the segmentation of hops and background, and clear edge contour is extracted. Through the pattern recognition of Daqing flower and Xiaoqing flower images, an effective grading basis for liquor-receiving automation is provided. This intelligent grading method can improve the stability and accuracy of the graded liquor-receiving process, and it is easy to realize the intelligent automation of the graded liquor-receiving process.