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 proposes a spectral–spatial combinative deep learning method based on hyperspectral images. It describes a push-broom hyperspectral imaging system using a grating spectrometer module, a SCMOS CCD and an electric displacement platform. The chapter presents the principal components analysis images or key band images as the spatial data and calculate the mean of each spectral band, including the derivative of consecutive spectral bands, as the spectral data. The camera can provide spatial information, but it only has one or three bands; hence, spectral information is insufficient. Otherwise, spectrograph can be considered the spectral information, but it cannot distinguish spatial distribution, so it is just suitable for homogeneous objects. In this problem of the detection of peanut aflatoxin, not only the spatial information but also the spectral information should be considered.
