ABSTRACT
Aflatoxin is a kind of virulent and strong carcinogenic substance, and it is found widely in peanuts, maize, and other agricultural products. This chapter aims to establishe a hyperspectral imagery system using grating module, SCOMS camera and an electric displacement platform and acquired 146 hyper spectral image cubes of 73 peanut samples before and after contaminated with aflatoxin. It proposes a reshaped image method of pixel spectral for the convolutional neural network method. Identification of peanuts containing aflatoxin in nature is difficult in a nondestructive way and requires professional knowledge, because it takes long time for Aspergillus flavus to grow in nature. The chapter concludes that positive significance for next sorter machine designing. According to the design idea of sorting machine, this model can be integrated into the upper computer system, which can quickly complete the design of sorting machine for aflatoxin testing.
