Image-Based Morphological Analysis and Time-Series Monitoring of Rice: A Review of Image Processing, Machine Learning and Emerging Approaches

Ramkishore Kushwaha; Dr Saurabh Mandloi

doi:10.69980/redvet.v25i1.2524

Ramkishore Kushwaha PhD Scholar, School of computer Science, SAM Global University, Raisen (M.P.), INDIA
Dr Saurabh Mandloi Associate Professor , School of computer Science, SAM Global University, Raisen (M.P.), INDIA

DOI: https://doi.org/10.69980/redvet.v25i1.2524

Keywords: Rice, computer vision, image processing, morphological analysis, grain phenotyping, deep learning, U-Net, time-series monitoring, growth modeling

Abstract

Rice is one of the world's most important food crops, and accurate assessment of its morphological characteristics is essential for crop improvement, grain-quality evaluation, and yield estimation. Conventional measurement techniques are time-consuming, labor-intensive, and susceptible to human error. Recent advances in computer vision, machine learning, deep learning, and Internet of Things (IoT) technologies have enabled automated and non-destructive rice phenotyping. Early image-processing methods used thresholding, edge detection, contour extraction, and morphological operations to measure grain length, width, area, perimeter, and shape. More recent approaches employ convolutional neural networks (CNNs), U-Net segmentation, object detection, and high-throughput imaging platforms for automated characterization of rice grains, panicles, and plants. Smartphone-based imaging has also demonstrated the potential for affordable rice-quality assessment. However, most grain-level studies focus on static or post-harvest images, while comparatively limited research addresses repeated non-destructive imaging and quantitative modeling of individual grain development. This review examines the evolution of image-based rice analysis, compares conventional and AI-based techniques, identifies existing research gaps, and proposes an integrated framework incorporating image acquisition, preprocessing, segmentation, morphological feature extraction, temporal tracking, and growth modeling. The proposed framework provides a foundation for developing intelligent, cost-effective, and non-destructive rice phenotyping systems.

References

1.Kuo, T.-Y., Chung, C.-L., Chen, S.-Y., Lin, H.-A., & Kuo, Y.-F. (2016). Identifying rice grains using image analysis and sparse-representation-based classification. Computers and Electronics in Agriculture, 127, 716–725. https://doi.org/10.1016/j.compag.2016.07.020
2.Boschetti, M., Busetto, L., Manfron, G., Laborte, A., Asilo, S., Pazhanivelan, S., & Nelson, A. (2017). PhenoRice: A method for automatic extraction of spatio-temporal information on rice crops using satellite data time series. Remote Sensing of Environment, 194, 347–365. https://doi.org/10.1016/j.rse.2017.03.029
3.Aznan, A., Gonzalez Viejo, C., Pang, A., & Fuentes, S. (2021). Computer vision and machine learning analysis of commercial rice grains: A potential digital approach for consumer perception studies. Sensors, 21(19), 6354. https://doi.org/10.3390/s21196354 DOI.org
4.Yang, Q., Shi, L., Han, J., Yu, J., & Huang, K. (2020). A near real-time deep learning approach for detecting rice phenology based on UAV images. Agricultural and Forest Meteorology, 287, 107938. https://doi.org/10.1016/j.agrformet.2020.107938 DOI.org
5.Image Processing Techniques for Diagnosing Rice Plant Disease: A Survey. (2020). Procedia Computer Science, 167, 516–530. https://doi.org/10.1016/j.procs.2020.03.308
6.Manavalan, R. (2020). Automatic identification of diseases in grains crops through computational approaches: A review. Computers and Electronics in Agriculture, 105802. https://doi.org/10.1016/j.compag.2020.105802 DOI.org
7.Convolutional Neural Networks in Computer Vision for Grain Crop Phenotyping: A Review. (2022). Agronomy, 12(11), 2659. https://doi.org/10.3390/agronomy12112659
8.A VI-based phenology adaptation approach for rice crop monitoring using UAV multispectral images. (2022). Field Crops Research, 277, 108419. https://doi.org/10.1016/j.fcr.2021.108419
9.Tang, Z., Chen, Z., Gao, Y., Xue, R., Geng, Z., Bu, Q., Wang, Y., Chen, X., Jiang, Y., Chen, F., Yang, W., Hu, W., et al. (2023). A strategy for the acquisition and analysis of image-based phenome in rice during the whole growth period. Plant Phenomics, 5, 0058. https://doi.org/10.34133/plantphenomics.0058
10.Zhou, Q., Guo, W., Chen, N., Wang, Z., Li, G., Ding, Y., Ninomiya, S., Mu, Y., et al. (2023). Analyzing nitrogen effects on rice panicle development by panicle detection and time-series tracking. Plant Phenomics, 5, 0048. https://doi.org/10.34133/plantphenomics.0048
11.Lei, L., Yang, Q., Yang, L., Shen, T., Wang, R., et al. (2024). Deep learning implementation of image segmentation in agricultural applications: A comprehensive review. Artificial Intelligence Review, 57, 149. https://doi.org/10.1007/s10462-024-10775-6
12.Murphy, K. M., Ludwig, E., Gutierrez, J., & Gehan, M. A. (2024). Deep learning in image-based plant phenotyping. Annual Review of Plant Biology, 75, 771–795. https://doi.org/10.1146/annurev-arplant-070523-042828 DOI.org
13.Sun, J., Jia, H., Ren, Z., Cui, J., Yang, W., & Song, P. (2024). Accurate rice grain counting in natural morphology: A method based on image classification and object detection. Computers and Electronics in Agriculture. https://doi.org/10.1016/j.compag.2024.109490 DOI.org
14.Predicting rice diseases using advanced technologies at different scales: Present status and future perspectives. (2023). aBIOTECH, 4, 359–371. https://doi.org/10.1007/s42994-023-00126-4