High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning

Plant Methods

Peng He¹  Minjuan Wang²  Si Yang³  Lihua Zheng⁴  Shi Sun⁵  Tingting Wu⁵ 

[1] College of Information Engineering, Northwest A&F University, 712100, Yangling, China;College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China;College of Information Science and Engineering, Shandong Agriculture and Engineering University, 251100, Jinan, China;Key Laboratory of Agricultural Informatization Standardization, Ministry of Agriculture and Rural Affairs, China Agricultural University, 100083, Beijing, China;College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China;Key Laboratory of Agricultural Informatization Standardization, Ministry of Agriculture and Rural Affairs, China Agricultural University, 100083, Beijing, China;College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China;Key Laboratory of Modern Precision Agriculture System Integration Research, Ministry of Education, China Agricultural University, 100083, Beijing, China;Institute of Crop Sciences, Chinese Academy of Agricultural Sciences, 100081, Beijing, China;

关键词: Seed phenotyping;    High throughput;    Instance segmentation;    Deep learning;    Mask R-CNN;   

DOI  :  10.1186/s13007-021-00749-y

来源: Springer

【 摘 要 】

BackgroundEffective soybean seed phenotyping demands large-scale accurate quantities of morphological parameters. The traditional manual acquisition of soybean seed morphological phenotype information is error-prone, and time-consuming, which is not feasible for large-scale collection. The segmentation of individual soybean seed is the prerequisite step for obtaining phenotypic traits such as seed length and seed width. Nevertheless, traditional image-based methods for obtaining high-throughput soybean seed phenotype are not robust and practical. Although deep learning-based algorithms can achieve accurate training and strong generalization capabilities, it requires a large amount of ground truth data which is often the limitation step.ResultsWe showed a novel synthetic image generation and augmentation method based on domain randomization. We synthesized a plenty of labeled image dataset automatedly by our method to train instance segmentation network for high throughput soybean seeds segmentation. It can pronouncedly decrease the cost of manual annotation and facilitate the preparation of training dataset. And the convolutional neural network can be purely trained by our synthetic image dataset to achieve a good performance. In the process of training Mask R-CNN, we proposed a transfer learning method which can reduce the computing costs significantly by finetuning the pre-trained model weights. We demonstrated the robustness and generalization ability of our method by analyzing the result of synthetic test datasets with different resolution and the real-world soybean seeds test dataset.ConclusionThe experimental results show that the proposed method realized the effective segmentation of individual soybean seed and the efficient calculation of the morphological parameters of each seed and it is practical to use this approach for high-throughput objects instance segmentation and high-throughput seeds phenotyping.

【 授权许可】

CC BY