Abstract: Aiming at the problems of single classification method and high classification cost of kiwifruit in China, this paper proposes a classification method based on kiwifruit surface defects. A set of kiwifruit image acquisition system is built. The K-means clustering segmentation algorithm was used to segment the surface defects, and then the color contrast was used to determine whether it was a residual fruit. Then, the shape features of normal fruit were extracted and SVM classifier was designed to further determine its grade. This method has the advantages of low cost, simple algorithm and high efficiency, which opens a new way for fruit classification, and is of great significance to promote the development of fruit classification industry in China and enhance international competitiveness.

Key words: kiwifruit, surface defect identification, fruit classification