Computer vision detection of surface defect on oranges by means of a sliding comparison window local segmentation algorithm

• Published in: Computers and electronics in agriculture 2017-05, Vol.137, p.59-68
• Main Authors: Rong, Dian, Rao, Xiuqin, Ying, Yibin
• Format: Article
• Language: English
• Subjects: Agricultural production; Algorithms; Citrus fruits; Computer vision; Defect detection; Image contrast; Image local segmentation; Image processing; Image segmentation; Infestation; Inspection; Orange surface defect; Pixels; Scars; Sliding; Studies; Surface defects; Vision systems; Windows (computer programs)
• ISSN: 0168-1699; 1872-7107
• DOI: 10.1016/j.compag.2017.02.027

The gray-level image after removing background, (b) the binary image. [Display omitted] •Successful detections of various types of surface defects.•Avoiding additionalimage lightness correction process.•Image detection algorithm is novel and practical. Automatic detection of defective oranges by computer vision system is not easy because of the uneven lightness distribution on the surface of oranges. It means that the methods onlydirectly using global segmentation provide unsatisfactory results when orange images present faint defect characters or inhomogeneous surface. The contrast between sound and defective regions can be used to produce more accurate segmentation results, which is more capable of detecting pixels lying around the defect boundary on orange surface based on the local segmentation method. In this paper, we study and propose a sliding comparison window local segmentation algorithm and also presents the detailed image processing procedure including removal of background pixels, image binarization using local segmentation, image subtraction, image morphological modification, removal of stem end pixels for detecting surface defect in an orange gray-level image. This method is an original contribution that allows successful segmentation of various types of surface defects (e.g., insect injury, wind scarring, thrips scarring, scale infestation, canker spot, dehiscent fruit, copper burn, phytotoxicity).The image segmentation algorithm was tested with 1191 samples of oranges. The proposed algorithm was able to correctly detect 97% of the defective orange. Future work will be focused on whole surface and fast on-line inspection.