Machine Vision with a CMOS-Based Hyperspectral Imaging Sensor Enables Sensing Meat Freshness

Abstract

Imaging spectral information of materials and analysis of its properties have become an intriguing tool for consumer electronics used for food inspection, beauty care, etc. Those sensory physical quantities are difficult to quantify. Hyperspectral imaging cameras, which capture the figure and spectral information simultaneously, can be a good candidate for nondestructive remote sensing. In this study, with the aid of a hyperspectral imaging system (HIS) and machine learning (ML) techniques, meat freshness is converted into a measurable physical quantity, i.e., the freshness index (FI). Herein, the FI is defined as meat fluorescence, which has a strong correlation with the bacterial density. Combined with ML techniques, hyperspectral data are processed more efficiently. By employing linear discriminant and quadratic component analyses, the FI can be estimated from its decision boundary after hyperspectral data are obtained in an unknown freshness state. We demonstrate that the HIS integrated with ML performs as the artificial eye and brain, which is advanced machine vision for consumer electronics, including refrigerators and smartphones. Advanced sensing versatility utilized by computational sensing systems allows hyper-personalization and hyper-customization of human life.