Identification and Classification of Sashimi Food Using Multispectral Technology

Food quality inspection is an essential factor in our daily lives. Food inspection is analyzing heterogeneous food data from different sources for perception, recognition, judgment, and monitoring. This study aims to provide an accurate system in image processing techniques for the inspection and classification of sashimi food damage based on detecting external data. The external texture was identified based on the visible and invisible system that was acquired using multispectral technology. We proposed the Grey Level Co-occurrence Matrix (GLCM) model for analysis of the texture features of images and the classification process was performed using Artificial Neural Network (ANN) method. This study showed that multispectral technology is a useful system for the assessment of sashimi food and the experimental also indicates that the invisible channels have the potential in the classification model, since the hidden texture features that are not clearly visible to the human eye.