Tharanya, M and Chakraborty, D and Pandravada, A and Babu, R and Gangashetti, M and Paidi, S and Choudhary, S and Sivasakthi, K and Anbazhagan, K and Vaditandra, B and Waininger, M and Weule, M and Hufnagel, E and Claußen, J and Vaněk, J and Wittenberg, T and Kholova, J and Gerth, S (2025) Utilizing X-ray radiography for non-destructive assessment of paddy rice grain quality traits. Plant Methods (TSI), 21. pp. 1-15. ISSN 1746-4811
![[img]](http://oar.icrisat.org/style/images/fileicons/application_pdf.png) |
PDF
- Published Version
Available under License ["licenses_description_cc_attribution" not defined]. Download (5MB) |
Abstract
Background Agricultural systems are under extreme pressure to meet the global food demand, hence necessitating faster crop improvement. Rapid evaluation of the crops using novel imaging technologies coupled with robust image analysis could accelerate crops research and improvement. This proof-of-concept study investigated the feasibility of using X-ray imaging for non-destructive evaluation of rice grain traits. By analyzing 2D X-ray images of paddy grains, we aimed to approximate their key physical Traits (T) important for rice production and breeding: (1) T1 chaffiness, (2) T2 chalky rice kernel percentage (CRK%), and (3) T3 head rice recovery percentage (HRR%). In the future, the integration of X-ray imaging and data analysis into the rice research and breeding process could accelerate the improvement of global agricultural productivity. Results The study indicated, computer-vision based methods (X-ray image segmentation, features-based multi-linear models and thresholding) can predict the physical rice traits (chaffiness, CRK%, HRR%). We showed the feasibility to predict all three traits with reasonable accuracy (chaffiness: R2 = 0.9987, RMSE = 1.302; CRK%: R2 = 0.9397, RMSE = 8.91; HRR%: R2 = 0.7613, RMSE = 6.83) using X-ray radiography and image-based analytics via PCA based prediction models on individual grains. Conclusions Our study demonstrated the feasibility to predict multiple key physical grain traits important in rice research and breeding (such as chaffiness, CRK%, and HRR%) from single 2D X-ray images of whole paddy grains. Such a non-destructive rice grain trait inference is expected to improve the robustness of paddy rice evaluation, as well as to reduce time and possibly costs for rice grain trait analysis. Furthermore, the described approach can also be transferred and adapted to other grain crops.
| Item Type: | Article |
|---|---|
| Divisions: | Global Research Program - Accelerated Crop Improvement |
| CRP: | UNSPECIFIED |
| Uncontrolled Keywords: | Computer vision, Image data analysis, Quality control, Rice breeding, Rice phenotyping, X-ray imaging |
| Subjects: | Others > Plant Breeding Others > Rice |
| Depositing User: | Mr Nagaraju T |
| Date Deposited: | 24 Sep 2025 06:36 |
| Last Modified: | 24 Sep 2025 06:36 |
| URI: | http://oar.icrisat.org/id/eprint/13341 |
| Official URL: | https://link.springer.com/article/10.1186/s13007-0... |
| Projects: | Precision Agriculture and Digitalization in the Czech Republic |
| Funders: | Corteva, Ministry of Agriculture of the Czech Republic, Department of Science and Technology, Science and Engineering Research Board |
| Acknowledgement: | The authors express their gratitude for the valuable discussions held with experts from the Fraunhofer Institute of Integrated Circuits IIS, IIRR, CZU, IRRI, and ICRISAT during the research. They extend special thanks to IRRI for granting permission to use the Zaccharia rice milling machine at the outset of the project. Additionally, the authors would like to thank Ms. Rekha Baddam for her assistance with logistics. |
| Links: |
Actions (login required)
 |
View Item |
Altmetric
Altmetric