Detection of skin defects on loquat using the hyperspectral imaging combining both band radio and improved three-phase level set segmentation method

Abstract

Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats. The loquats with skin defects will lead to the loquat being easily destroyed during transportation and storage, which will cause the risk of other loquats being infected, affecting the selling price of loquat. In this paper, a method combining band radio image with improved three-phase level set segmentation algorithm (ITPLSSM) is proposed to achieve high accuracy, rapid, and non-destructive detection of skin defects of loquats. Principal component analysis (PCA) was used to find the characteristic wavelength and PC images to distinguish between four types of skin defects. Determine the best band ratio image based on characteristic wavelength. The band ratio image (Q782/944) based on PC2 image is the best segmented image. Based on Pseudo-color image enhancement, morphological processing, and local clustering criteria, the band ratio image (Q782/944) has better contrast between defective area and normal area in loquat. Finally, the ITPLSSM was used to segment the processing band ratio image (Q782/944), with the accuracy is 95.28 %. The proposed ITPLSSM method is effective in distinguishing with four types of skin defects. Meanwhile, it also effectively segments the images with intensity inhomogeneities.