Grainalyze: A Hybrid Approach for Consumer Level Assessment of Rice Quality Based on Grain Morphology

Rice is a staple food in the Philippines, and its quality significantly affects consumer preference, market value, and grain grading standards across different regions and local agricultural markets today. However, conventional rice quality assessment commonly relies on manual inspection by trained personnel, making the process time-consuming, subjective, and often inaccessible to ordinary consumers.
This study proposes Grainalyze, a mobile-based artificial intelligence-assisted system for rice grain quality assessment using instance segmentation and image-based analysis. Image-based rice quality assessment using computer vision and machine learning techniques has been widely explored in previous studies [1], [7]. A total of 3,885 source images of rice grains were prepared and expanded to 10,135 images through preprocessing and augmentation, then annotated into four grain quality classes: whole grain, broken grain, chalky grain, and discolored grain.
The study evaluated Mask R-CNN alongside YOLOv8n-seg, YOLOv8s-seg, and U-Net using standard performance metrics, including Precision, Recall, F1 Score, mean Average Precision, and inference speed. Deep learning-based segmentation approaches have demonstrated strong performance in rice grain classification tasks [11], [19]. Results show that Mask R-CNN achieved the best overall segmentation performance, obtaining 89.89% mean Average Precision, 96.88% precision, 89.89% recall, and a 93.26% F1 Score, demonstrating the most reliable balance between segmentation accuracy and detection performance among the evaluated models.
The findings demonstrate that integrating instance segmentation with coin-based measurement calibration, rule-based broken grain detection, Logistic regression for chalky grain identification, and LAB/HSV-based discoloration analysis can provide an effective and accessible approach for automated rice grain quality assessment using smartphone-captured images.

Artificial Intelligence, Rice Quality Assessment

1. N. K. Aznan et al., “Computer vision and machine learning analysis of commercial rice grain quality,” Sensors, vol. 21, no. 19, p. 6416, 2021. [Google Scholar] [Crossref]

2. J. M. Dela Cruz and R. P. Santos, “Rice paddy disease detection using image processing,” Undergraduate thesis, University of Mindanao, 2022. [Google Scholar] [Crossref]

3. N. V. Delmo, R. L. Tuaño, and R. G. Del Rosario, “Grain size distribution and head rice yield of some rice breeding lines using flatbed scanning and digital image analysis,” Transactions of the National Academy of Science and Technology Philippines, 2021. [Google Scholar] [Crossref]

4. N. R. Eclarin, “Detection of typhoon damaged regions on UAV captured rice field images using an ensemble of CNN and artificial neural network,” Undergraduate thesis, Ateneo de Manila University, 2023. [Google Scholar] [Crossref]

5. M. J. Hasan, M. M. Rahman, M. Z. Islam, and M. A. Rahman, “Classification of rice varieties using deep learning,” International Journal of Electrical and Computer Engineering, vol. 11, no. 5, pp. 4047–4054, 2021. [Google Scholar] [Crossref]

6. X. He et al., “Rapid appearance quality of rice based on machine vision and convolutional neural network,” Foods, vol. 12, no. 15, p. 2865, 2023. [Google Scholar] [Crossref]

7. R. Kumar, V. Singh, and S. Kumar, “Machine learning and image processing–based classification of milled rice grains,” Computers and Electronics in Agriculture, vol. 204, p. 107540, 2023. [Google Scholar] [Crossref]

8. A. R. Kurade, S. R. Patil, and P. S. Kulkarni, “Automated rice quality assessment using image processing and machine learning techniques,” Journal of Agriculture and Food Research, vol. 15, p. 100598, 2024. [Google Scholar] [Crossref]

9. A. R. Kurade et al., “An automated image processing module for quality assessment of rice grains,” Journal of Food Engineering, vol. 345, p. 111234, 2023. [Google Scholar] [Crossref]

10. P. Lin, J. Zhang, and X. Li, “Rice grain quality classification based on deep convolutional neural network,” Computers and Electronics in Agriculture, vol. 185, p. 106139, 2021. [Google Scholar] [Crossref]

11. Y. Liu, H. Zhang, X. Wang, and J. Chen, “Rice grain quality detection and classification using deep learning–based image segmentation and thresholding techniques,” Applied Sciences, vol. 12, no. 22, p. 11701, 2022. [Google Scholar] [Crossref]

12. Philippine Center for Postharvest Development and Mechanization, “PHilMech annual report 2022,” 2022. [Google Scholar] [Crossref]

13. Philippine Rice Research Institute, “Automated digital image acquisition for rice grain size and shape measurement,” 2020. [Google Scholar] [Crossref]

14. Philippine Rice Research Institute, “Crisis resilient rice farming,” PhilRice Magazine, 2020. [Google Scholar] [Crossref]

15. Philippine Rice Research Institute, “Image-based measurement of rice grain physical properties,” Rice-Based Biosystems Journal, 2021. [Google Scholar] [Crossref]

16. Philippine Rice Research Institute, “DA-PhilRice R&D highlights—Los Baños branch station,” 2023. [Google Scholar] [Crossref]

17. Philippine Rice Research Institute, “New mobile app speeds up rice grain quality checks,” 2025. [Google Scholar] [Crossref]

18. S. Rani, A. Sharma, and D. Singh, “Rice grain quality analysis using image processing and artificial intelligence techniques,” Computers and Electronics in Agriculture, vol. 218, p. 107678, 2025. [Google Scholar] [Crossref]

19. M. I. Sarker, M. S. Hossain, and K. Andersson, “Rice variety classification using machine learning and image processing techniques,” Artificial Intelligence in Agriculture, vol. 9, pp. 45–54, 2024. [Google Scholar] [Crossref]

20. H. Velesaca, T. Toulkeridis, and L. Pilla, “Computer vision–based food grain classification: A comprehensive survey,” Computers and Electronics in Agriculture, vol. 189, p. 106389, 2021. [Google Scholar] [Crossref]

21. Y. Wang, D. Chen, Y. Zhang, and Z. Liu, “Chalkiness degree recognition of rice grains using image processing and machine learning,” Computers and Electronics in Agriculture, vol. 174, p. 105496, 2020. [Google Scholar] [Crossref]

• Breeding for a Greener Future: Selective Breeding and Crossbreeding Approaches to Minimize Methane Emissions in Ruminant Livestock
• Determinants of Adoption of Post-Harvest Losses Prevention Techniques among Banana/Plantain Marketers in Lagos State, Nigeria
• Enhancing Rice Yield Prediction Using UAV-Based Multispectral Imaging and Machine Learning Algorithms
• Seed-Borne Fungi of Groundnuts (Arachis Hypogaea) and Their Management with Ginger (Zingiber Officinale) Extract In Makurdi, Nigeria
• The Influence of Landforms and Slope on Agricultural Cropping Patterns in Chhatrapati Sambhajinagar District