AUTHOR=Zhang Han , Hou Qiling , Luo Bin , Tu Keling , Zhao Changping , Sun Qun 

TITLE=Detection of seed purity of hybrid wheat using reflectance and transmittance hyperspectral imaging technology

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1015891

DOI=10.3389/fpls.2022.1015891

ISSN=1664-462X

ABSTRACT=Chemical hybridization (CHA) and genic male sterility (GMS) systems are two main methods of hybrid wheat production, due to the influence of the growth stage and the environmental weather, female plants are usually not wholly sterile, and hybrid wheat seeds are inevitably mixed with a certain number of parent seeds, especially female seeds. So seed purity has been the key factor in popularizing hybrid wheat. However, the traditional seed purity detection or variety identification methods are time-consuming, laborious, and destructive purity. In order to establish a non-destructive classification method for hybrid and female parent seeds, three hybrid wheat varieties (Jingmai 9, Jingmai 11, Jingmai 183) and their parent seeds were sampled. The transmission and reflection spectrum of all seeds were collected by hyperspectral imaging technology, and the classification model was established by the partial least squares discriminant analysis (PLS-DA) combined with various preprocessing methods. The results showed that the transmission spectrum could significantly improve the classification effect of hybrids and female parents compared to the reflectance spectrum. Specifically, using transmission spectrum combined with a characteristic wavelength screening algorithm, the Detrend-CARS-PLS-DA model was established, and the accuracy rates on the validation sets of Jingmai 9, Jingmai 11, and Jingmai 183 were 95.69%, 98.25%, 97.25%, respectively. It could be concluded that transmission hyperspectral imaging combined with a machine learning algorithm can effectively distinguish female parent seeds from hybrid seeds. These results can provide a reference for rapid seed purity detection in the hybrid production process. Due to the non-destructive and fast characteristics of hyperspectral imaging, the detection of hybrid wheat seed purity can be improved by online sorting, in the future.