FOOD INSPECTION DEVICE, FOOD INSPECTION METHOD, AND LEARNING METHOD FOR FOOD RECONSTRUCTION NEURAL NETWORK OF FOOD INSPECTION DEVICE

摘要

This invention comprises: a light irradiation means that irradiates an inspection object with light; an image capturing means that captures a video image of the inspection object A; and an identification processing device. The identification processing device includes a food reconstruction neural network that has learned, in advance, only non-defective food items. From the image obtained by the image capturing means, a provisional food image is reconstructed by using the food reconstruction neural network, the difference between the image obtained by the image capturing means and the provisional food image is calculated, and an inspection object having a difference exceeding a preset threshold is identified as a foreign object.