SAM-GAN: An improved DCGAN for rice seed viability determination using near-infrared hyperspectral imaging

Abstract

Viability is a significant indicator of rice seeds, affecting rice yield and quality. Existing viability determination methods cannot meet the requirements of rapidity, non-destructive and accuracy. In this study, near-infrared hyperspectral imaging was used to detect the viability of natural aging seeds. Generative Adversarial Network (GAN) is the main means of coping with Few-shot learning. Considering that natural aging seed samples were difficult to obtain and the number was scarce, this study used Spectral Angle Mapper Generative Adversarial Network (SAM-GAN) to generate rice seed spectral data based on the spectra of obtained natural aging seeds to solve the problem of sample scarcity. SAM-GAN is based on Deep Convolution GAN (DCGAN), introduced by SAM. SAM-GAN was compared with Wasserstein Generative Adversarial Nets with Gradient Penalty (WGAN-GP) and DCGAN, and the Convolutional Neural Network (CNN) model was established by three modeling methods: real data modeling, fake data modeling and mixed modeling of real data and fake data. The experimental results show that the accuracy of the CNN model established by mixing real data with fake data generated by SAM-GAN reaches nearly 100%. This study provides an effective method for rapid, non-destructive and accurate determination of rice seed viability with a limited sample number.