Methodology for Potatoes Defects Detection with Computer Vision

correct detection of external defects on potatoes is the key technology in the realization of automatic potato grading and sorting station. This paper reports a novel inspection approach to external defects of potato in three potato cultivars. Adaptive Intensity Interception (AII) and Fixed Intensity Interception (FII) methods have been proposed to extract the suspect defects. Otsu segmentation combined with morphologic operation was used to remove the normal skin and background. Area threshold and black ratio threshold were used to identify defects in the suspect defects. Experiments have shown FII performed better than AII in a specific circumstance. The correct classification rate of defects, the correct recognition rate of defects and the correct inspection rate of potatoes based on FII are 92.1%, 91.4% and 100% respectively. The results showed this approach was fast, valid and convenient for defect detection on yellow-skin potatoes. Index Terms—Computer vision; Pattern recognition; Potatoes; Defects detection