Non-destructive detection of bruises in pomegranate fruit by Vis-NIR and SWIR hyperspectral imaging

Fresh pomegranate fruit is susceptible to bruising, a common type of mechanical damage during harvest and at all stages of postharvest handling. Detecting such damages in pomegranate fruit is very important for quality inspection systems. This study investigated the detection of bruises in fresh pomegranate fruit using hyperspectral cameras equipped with sensors. Ninety sample pomegranates were divided into three groups of 30 samples, each representing dropping induced bruising levels: 100, 60, and 0 cm (no drop). Two hyperspectral imaging setups were examined: visible and near-infrared (400 to 1000 nm) and short wavelength infrared (1000 to 2500 nm). Principal components analysis (PCA) of the input hyperspectral data cube was performed using the singular value decomposition (SVD) method for extracting principal components. The overall accuracy of classifications was 88.9 and 66.7% for the SWIR and Vis-NIR data, respectively. This study demonstrated the potential of using hyperspectral imaging technology in sensing and classifying bruise severity in pomegranate fruit.