Database/Software Article | Open Access

Volume 2025 |Article ID 100099 | https://doi.org/10.1016/j.plaphe.2025.100099

Global rice multiclass segmentation dataset (RiceSEG): comprehensive and diverse high-resolution RGB-annotated images for the development and benchmarking of rice segmentation algorithms

Junchi Zhou,¹ Haozhou Wang,² Yoichiro Kato,² Tejasri Nampally,³ P. Rajalakshmi,⁴ M. Balram,⁵ Keisuke Katsura,⁶ Hao Lu,⁷ Yue Mu,¹ Wanneng Yang,⁸ Yangmingrui Gao,¹ Feng Xiao,¹ Hongtao Chen,¹ Yuhao Chen,¹ Wenjuan Li,⁹ Jingwen Wang,¹⁰ Fenghua Yu,¹¹ Jian Zhou,¹² Wensheng Wang,¹³ Xiaochun Hu,¹⁴ Yuanzhu Yang,¹⁴ Yanfeng Ding,¹ Wei Guo ,² and Shouyang Liu ¹

¹Engineering Research Center of Plant Phenotyping, Ministry of Education, Jiangsu Collaborative Innovation Center for Modern Crop Production, Sanya Institute of Nanjing Agricultural University, Academy for Advanced Interdisciplinary Studies, Nanjing Agricultural University, Nanjing, China
²Graduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo, Japan
³Department of Artificial Intelligence, Indian Institute of Technology, Hyderabad, India
⁴Department of Electrical Engineering, Indian Institute of Technology, Hyderabad, India
⁵Institute of Biotechnology, Professor Jayashankar Telangana Agricultural State University, Hyderabad, India
⁶Graduate School of Agriculture, Kyoto University, Kyoto, Japan
⁷Key Laboratory of Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
⁸National Key Laboratory of Crop Genetic Improvement, National Center of Plant Gene Research, and Hubei Key Laboratory of Agricultural Bioinformatics, Huazhong Agricultural University, Wuhan, China
⁹State Key Laboratory of Efficient Utilization of Arid and Semiarid Arable Land in Northern China, The Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, China
¹⁰Center for Geospatial Information, Shenzhen Institutes of Advanced Technology, Chinese Academy of Science, Shenzhen, China
¹¹School of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang, China
¹²Rice Research Institute, Jilin Academy of Agricultural Sciences, Changchun, China
¹³Institute of Crop Sciences/National Key Facility for Crop Gene Resources and Genetic Improvement, Chinese Academy of Agricultural Sciences, Beijing, China
¹⁴Yuan Long Ping High-Tech Agriculture Co., Ltd., Changsha, China

Abstract

The development of computer vision-based rice phenotyping techniques is crucial for precision field management and accelerated breeding, which facilitate continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into ecophysiological processes. However, owing to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both because of a lack of large, representative collections of rice field images and because of the time-intensive nature of the annotation. To address this gap, we created the first comprehensive multiclass rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing more than 6000 genotypes across all growth stages. From these original images, 3078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the subdataset from China spans all major genotypes and rice-growing environments from northeastern to southern regions. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and when multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops. The RiceSEG dataset is publicly available at www.global-rice.com.