RICE GRAIN TRAIT ESTIMATION USING COLOR SPACE CONVERSION AND DEEP LEARNING-BASED IMAGE SEGMENTATION

Chu Bảo Minh; Tô Thị Mai Hương; Trần Giang Sơn

doi:10.34238/tnu-jst.10191

RICE GRAIN TRAIT ESTIMATION USING COLOR SPACE CONVERSION AND DEEP LEARNING-BASED IMAGE SEGMENTATION

About this article

Received: 23/04/24 Revised: 10/06/24 Published: 11/06/24

Authors

1. Chu Bao Minh, University of Science and Technology of Hanoi - Vietnam Academy of Science and Technology
2. To Thi Mai Huong, University of Science and Technology of Hanoi - Vietnam Academy of Science and Technology
3. Tran Giang Son , University of Science and Technology of Hanoi - Vietnam Academy of Science and Technology

Abstract

Accurately extracting traits from rice grains is of importance for effective crop management and yield estimation, providing valuable understanding for improving agricultural practices. However, manual intervention in these tasks is labor-intensive, time-consuming, and error-prone. This research proposes a new approach that leverages low-cost digital cameras and deep learning technology for counting and extracting rice grain traits. Our study introduces a preprocessing step to separate rice grain regions from the input image background using color space conversion. After that, a deep learning image segmentation model based on YOLOv8 is utilized for the extraction of both the number and morphological traits of the grains. The accuracy of the proposed method was experimented on 88 different rice varieties provided by the Plant Resource Center in Hanoi. The experimental results show that the proposed approach is high-accurate and high-throughput for low-cost extraction of rice grain traits from color digital images, which is potentially helpful in facilitating effective evaluation in rice breeding programs and functional gene identification of rice varieties.

Keywords

Rice grain traits; Color space conversion; Deep learning; Image segmentation; YOLOv8

Full Text:

PDF

References

[1] M. Tester and P. Langridge, "Breeding technologies to increase crop production in a changing world," Science, vol. 327, no. 5967, pp. 818-822, 2010, doi: 10.1126/science.1183700.

[2] Q. Zhang, "Strategies for developing green super rice," Proceedings of the National Academy of Sciences, vol. 104, no. 42, pp. 16402-16409, 2007, doi: 10.1073/pnas.0708013104.

[3] J. Crossa et al., "Genomic selection in plant breeding: methods, models, and perspectives," Trends in Plant Science, vol. 22, no.11, pp. 961-975, 2017, doi: 10.1016/j.tplants.2017.08.011.

[4] M. Watt et al., "Phenotyping: new windows into the plant for breeders," Annual Review of Plant Biology, vol. 71, pp. 689-712, 2020, doi: 10.1146/annurev-arplant-042916-041124.

[5] D. Sun et al., "Advances in optical phenotyping of cereal crops," Trends in Plant Science, vol. 27, no.2, pp. 191-208, 2022, doi: 10.1016/j.tplants.2021.07.015.

[6] C. L. Huang et al., "Development of a whole-feeding and automatic rice thresher for single plant," Mathematical and Computer Modelling, vol. 58, no. 3-4, pp. 684-690, 2013, doi: 10.1016/j.mcm.2011.10.033.

[7] A. P. Whan et al., "GrainScan: a low cost, fast method for grain size and colour measurements," Plant methods, vol. 10, pp. 1-10, 2014, doi: 10.1186/1746-4811-10-23.

[8] S. Y. Tan et al., "Segmentation and counting algorithm for touching hybrid rice grains," Computers and Electronics in Agriculture, vol. 162, pp. 493-504, 2019, doi: 10.1016/j.compag.2019.04.030.

[9] S. B. Liu et al., "Estimating maize seedling number with UAV RGB images and advanced image processing methods," Precision Agriculture, vol. 23, no. 5, pp. 1604-1632, 2022, doi: 10.1007/s11119-022-09899-y.

[10] W. Wu et al., "Image analysis-based recognition and quantification of grain number per panicle in rice," Plant Methods, vol. 15, pp. 1-14, 2019, doi: 10.1186/s13007-019-0510-0.

[11] Kumar, J. Praveen, and S. Domnic, "Image based leaf segmentation and counting in rosette plants," Information Processing in Agriculture, no. 6, no. 2, pp. 233-246, 2019, doi: 10.1016/j.inpa.2018.09.005.

[12] W. N. Yang et al., "Crop phenomics and high-throughput phenotyping: past decades, current challenges, and future perspectives," Molecular plant, vol. 13, no. 2, pp. 187-214, 2020, doi: 10.1016/j.molp.2020. 01.008.

[13] D. Wang et al., "The development of a vision-based phenotypic analysis algorithm for measuring spikelet-related traits in rice," Plant Physiology Journal, vol. 58, no. 5, pp. 957-971, 2022, doi: 10.13592/j.cnki.ppj.200009.

[14] L. Su and P. Chen, "A method for characterizing the panicle traits in rice based on 3D micro-focus X-ray computed tomography," Computers and Electronics in Agriculture, vol. 166, 2019, Art. no. 104984, doi: 10.1016/j.compag.2019.104984.

[15] W. J. Hu et al., "Nondestructive 3D image analysis pipeline to extract rice grain traits using X-ray computed tomography," Plant Phenomics, 2020, doi: 10.34133/2020/3414926.

[16] L. J. Yu et al., "An integrated rice panicle phenotyping method based on X-ray and RGB scanning and deep learning," The Crop Journal, vol. 9, no. 1, pp. 42-56, 2021, doi: 10.1016/j.cj.2020.06.009.

[17] J. Terven, D.-M Córdova-Esparza, and J.-A. Romero-González, "A comprehensive review of yolo architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680-1716, 2023, doi:10.3390/make5010007.

[18] G. Jocher, A. Chaurasia, and J. Qiu, “Ultralytics YOLO (Version 8.0.0),” 2023. [Computer software]. Available: https://github.com/ultralytics/ultralytics. [Accessed March 10, 2024].

[19] T. Tanabata et al., "SmartGrain: high-throughput phenotyping software for measuring seed shape through image analysis," Plant physiology, vol. 160, no. 4, pp. 1871-1880, 2012, doi: 10.1104/pp.112.205120.

[20] Y. W. Lu et al., "High-throughput and separating-free phenotyping method for on-panicle rice grains based on deep learning," Frontiers in Plant Science, vol. 14, 2023, Art. no. 1219584, doi: 10.3389/fpls.2023.1219584.

DOI: https://doi.org/10.34238/tnu-jst.10191

Refbacks

There are currently no refbacks.



Remember me