Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network

Yaoyao Fan; Ting An; Qingyan Wang; Guang Yang; Wenqian Huang; Zheli Wang; Chunjiang Zhao; Xi Tian

doi:10.3389/fpls.2023.1248598

Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network

Front Plant Sci. 2023 Aug 29:14:1248598. doi: 10.3389/fpls.2023.1248598. eCollection 2023.

Authors

Yaoyao Fan^{1

2}, Ting An², Qingyan Wang², Guang Yang², Wenqian Huang², Zheli Wang², Chunjiang Zhao^{1

2}, Xi Tian²

Affiliations

¹ College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang, China.
² Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China.

Abstract

The viability of Zea mays seed plays a critical role in determining the yield of corn. Therefore, developing a fast and non-destructive method is essential for rapid and large-scale seed viability detection and is of great significance for agriculture, breeding, and germplasm preservation. In this study, hyperspectral imaging (HSI) technology was used to obtain images and spectral information of maize seeds with different aging stages. To reduce data input and improve model detection speed while obtaining more stable prediction results, successive projections algorithm (SPA) was used to extract key wavelengths that characterize seed viability, then key wavelength images of maize seed were divided into small blocks with 5 pixels ×5 pixels and fed into a multi-scale 3D convolutional neural network (3DCNN) for further optimizing the discrimination possibility of single-seed viability. The final discriminant result of single-seed viability was determined by comprehensively evaluating the result of all small blocks belonging to the same seed with the voting algorithm. The results showed that the multi-scale 3DCNN model achieved an accuracy of 90.67% for the discrimination of single-seed viability on the test set. Furthermore, an effort to reduce labor and avoid the misclassification caused by human subjective factors, a YOLOv7 model and a Mask R-CNN model were constructed respectively for germination judgment and bud length detection in this study, the result showed that mean average precision (mAP) of YOLOv7 model could reach 99.7%, and the determination coefficient of Mask R-CNN model was 0.98. Overall, this study provided a feasible solution for detecting maize seed viability using HSI technology and multi-scale 3DCNN, which was crucial for large-scale screening of viable seeds. This study provided theoretical support for improving planting quality and crop yield.

Keywords: 3D convolution neural network; YOLOv7 model; hyperspectral imaging; maize seeds; viability detection.

Grants and funding

This study was supported by China Postdoctoral Science Foundation (2022M720492), Postdoctoral Scientific Research Fund of Beijing Academy of Agricultural and Forestry Sciences (2022-ZZ-018), Beijing Postdoctoral Science Foundation (2023-117).