Detection of early bruises on peaches (Amygdalus persica L.) using hyperspectral imaging coupled with improved watershed segmentation algorithm

Bruise is the most common type of damage to peaches in a major cause of quality loss. However, fast and nondestructive detection of early bruises on peaches is a challenging task. In this study, short-wave near infrared (SW-NIR) and long-wave near infrared (LW-NIR) hyperspectral imaging technologies were observed and compared the ability to discriminate bruised from sound regions. Principal components analysis (PCA) was utilized to select the effective wavelengths for each type of imaging mode. SW-NIR imaging mode was more suitable for detection of early bruises on peaches. A novel improved watershed segmentation algorithm based on morphological gradient reconstruction and marker extraction was developed and applied to the multispectral PC images. The detection results indicated that for all test peaches used in this experiment, 96.5% of the bruised and 97.5% of sound peaches were accurately identified, respectively. A proposed algorithm was superior to the common segmentation methods including Ostu and the global threshold value method. This study demonstrated that SW-NIR hyperspectral imaging coupled with the proposed improved watershed segmentation algorithm could be a potential approach for detection of early bruises on peaches.