Work

Non-destructive viability detection of naturally-aged large-sample rice seeds using hyperspectral imaging and deep learning

Year: 2025

Type: article

Abstract: Precise prediction of rice seed viability is fundamental to enhancing grain yield and ensuring food quality. Traditional viability detection methods are time-consuming, labor-intensive, and seed-consuming, necessitating the development of non-destructive, intelligent, high-throughput detection technologies. Hyperspectral imaging (HSI), as a non-destructive technique, has been widely applied to seed viability detection. The spectral information from different seed components, as well as the number of varieties/germplasms, are key factors influencing detection performance. Therefore, we propose a Mobile Inverted Bottleneck U-Net (MBUNet) for segmenting the combined embryo and endosperm regions in rice hyperspectral images, enabling analysis of how spectral information from different seed components affects model performance. Furthermore, we propose a novel Dual Branch Spectral Transformer Network (DBST-Net) to effectively capture spectral differences between viable and non-viable seeds across 600 naturally aged rice varieties/germplasms, encompassing 58,129 samples. The DBST-Net integrates a multiscale CNN module and a Transformer module to extract local and global spectral features, respectively, while the Multi-Level Feature Fusion Attention (MFFA) module enables deep interaction between these features. Experimental results show that MBUNet achieves a mean Intersection over Union (mIoU) of 95.62 % on the rice seed hyperspectral dataset, outperforming five other segmentation models. Under imbalanced condition of viable and non-viable samples, the DBST-Net achieves the highest classification accuracy of 97.54 % among eight classification methods. The viability-sensitive region analysis reveals that the spectral information of the embryo exhibits the strongest correlation with viability prediction. The transfer experiment demonstrates that the DBST-Net possesses excellent generalization capability. This study provides a novel solution for non-destructive intelligent viability detection of large-sample cross-variety/germplasm rice seeds, offering technical support for safeguarding grain quality. • Proposed MBUNet for precise segmentation of embryo-containing key regions in rice seeds. • Proposed DBST-Net to achieve high-precision viability detection across 600 naturally-aged rice varieties/germplasms. • DBST-Net integrates the local feature extraction of CNN with the global modeling ability of Transformer. • The embryo region with the highest spectral viability prediction is a potential key sensitive area for viability. • DBST-Net demonstrates exceptional transfer generalization ability.

Source: Journal of Agriculture and Food Research

DOI: 10.1016/j.jafr.2025.102333