Computer vision detection of defective apples using automatic lightness correction and weighted RVM classifier

• Lightness correction method was present to solve the uneven distribution of lightness.
• Preliminary classification according to the number of defect candidate region was used.
• Relevant feature and their weights were also analyzed by using I-RELIEF algorithm.
• Weighted probabilistic prediction RVM classifier was used for the classification step.

Automatic detection of defective apples by computer vision system is still not available due to the uneven lightness distribution on the surface of apples and the similarity between the true defects, stems and calyxes. This paper presents a novel automatic defective apple detection method by using computer vision system combining with automatic lightness correction, number of the defect candidate (including true defect, stem and calyx) region counting, and weighted relevance vector machine (RVM) classifier. Automatic lightness correction was used to solve the problem of the uneven lightness distribution, especially in the edge area of the apples. According to the fact that the calyx and stem cannot appear at the same view of image, some apples could be classified as sound (N = 0, N is the number of defect candidate region) or defective (N ⩾ 2) apples based on the number of defect candidate region in the preliminary step without any other complex processing. For the rest uncertain apples (N = 1), further discrimination was conducted. Average color, statistical, and average textural features were extracted from each candidate region, the relevant features and their weights were also analyzed by using I-RELIEF algorithm. Finally, the defect candidate regions are classified as true defect or stem/calyx by the weighted RVM classifier, and the apples would be finally classified as sound or defective class according to the category of the candidate regions. The result with 95.63% overall detection accuracy for the 160 samples indicated that the proposed algorithm was effective and suitable for the defective apples detection. The limitation of our research is the one single limited inspection view of the apples. Future work will be focused on whole surface and fast on-line inspection.