Research on Surface Defect Detection Algorithm of Ice-cream Bars Based on Clustering

Ice-cream bars are widely used in food processing. There are many defects on the surface of ice-cream bars, including knot defects, blue-stain defects, and bark-material defects. The shape and size of these defects are not regular, so that it is difficult to detect them. This paper proposes a surface defect detection algorithm of ice-cream bar based on clustering. The ice-cream bar is divided into many small regions through image pre-processing. Then this paper proposes two region merging strategies and three constraints to combine these small regions. After that, the defect regions are distinguished in HSV color space. At last, this paper establishes the evaluation system of surface defect detection effect for ice-cream bars. According to the defect detection algorithm proposed in this paper, a large number of tests are carried out. The results show that the algorithm can provide high accuracy and has practical application value.