Detection of Early Bruises on Apples Using Hyperspectral Reflectance Imaging Coupled with Optimal Wavelengths Selection and Improved Watershed Segmentation Algorithm

Abstract

Bruise caused by mechanical collision during the harvesting and storage and transportation period is difficult to detect using traditional machine vision technologies because there is no obvious appearance between bruised and sound tissues. In this paper, the visible near infrared hyperspectral reflectance images of healthy apples and bruised apples happened in 6, 12 and 24 h were obtained. In order to reduce hyperspectral data dimension, optimal wavelengths selection algorithms including principal component analysis (PCA) and band ratio methods were utilized to select the effective wavelengths and enhance the contrast between bruised and sound tissues. Then pseudo-color image transformation technology combining with improved watershed segmentation algorithm (IWSA) were employed to recognize the bruise spots. The result showed that band ratio images obtained better detection performance than that of PCA. The G component derived from pseudo-color image of  followed by IWSA obtained the best segmentation performance for bruise spots. Finally, a multispectral imaging system for detection of bruised apple were developed to verify the effectiveness of the proposed two-band ratio algorithm, which obtained a recognition rates of 93.3 %, 92.2 % and 92.5 % for healthy, bruised and overall apples, respectively. Therefore, the bruise detection algorithm proposed in this study has potential to detect bruised apple in online practical application.

Keywords: Hyperspectral imaging, Bruise detection, Band ratio image, Apple, Improved watershed segmentation algorithm