A Comprehensive Survey on Rice Plant Diseases Detection and Classification

Abstract

Detecting plant diseases through image analysis has emerged as a significant research domain in agriculture and computer science. This paper provides a comprehensive analysis of various image processing tasksand machine learning methods employed for identifying diseases in rice plants using image-based approaches. In addition to reviewing multiple methodologies, this study also highlights essential image processing concepts, machine learning concepts relevant to rice plant disease identification. A detailed analysis of 20 research papers is conducted, encompassing studies on rice plant diseases as well as diseases affecting other crops and fruits. The survey categorizes these studies based on key factors such as dataset size, number of disease classes, preprocessing methods, segmentation techniques, classification models, and their corresponding accuracy. The insights gained from this survey serve as a foundation for designing and developing an improved approach for rice plant disease identification and classification.

Introduction

Agriculture is vital to India’s economy, with about 70% of the population dependent on it, and rice being a key staple crop. Rice production faces significant threats from diseases caused mainly by fungi and bacteria, leading to 10-15% yield losses annually in Asia. Common rice diseases include Leaf Blast, Tungro, Bacterial Blight, Brown Spot, and Leaf Scald. Early and accurate disease detection is critical but challenging for many farmers due to lack of tools and expertise.

Traditional manual disease monitoring is labor-intensive and often ineffective, while incorrect pesticide use can harm ecosystems. Automated disease detection using digital agriculture technologies, such as camera sensors combined with image processing and machine learning, shows promise for timely and accurate diagnosis.

The paper surveys the use of image processing and machine learning techniques for rice disease detection. The general pipeline involves collecting leaf images, preprocessing (noise reduction, contrast enhancement), segmentation to isolate diseased areas, feature extraction (color, texture, shape), and classification using machine learning algorithms.

Challenges in this field include limited datasets, difficulty distinguishing visually similar diseases, shadows, and environmental variations. The paper reviews various rice diseases, image processing methods, machine learning models, and related agricultural applications, highlighting common practices like median filtering, Otsu’s thresholding for segmentation, and classifiers such as SVMs and neural networks.

The survey concludes with an overview of existing literature, discussing strengths and limitations of current techniques, and provides future research directions for improving automated rice disease identification.

Conclusion

The findings in this survey highlight the tremendous advantage that arises when integrating image processing and machine learning methods to significantly increase the accuracy in rice plant disease identification. Image collection is the initial step, and frequently involves creating datasets targeting rice fields using customized collection activities. Major pre-processing techniques, such as noise reduction, contrast enhancement, are very important in solving problems of dust, shadowing, and water drops on leaves. When researchers use techniques such as edge detection and thresholding for segmentation, they can easily isolate important parts of the image, allowing for precise feature extraction. By considering such features as color, texture, and shape, the system can discriminate among several diseases properly. Classification tools in machine learning, such as SVMs and k-NN, are used for these features to be able to secure effective disease categorization and diagnosis. No need for specific assumptions about the data, as it is possible to organize data points by their inherent similarities using clustering algorithms. The combination of these techniques has significantly enhanced the capability of detecting diseases early, which has encouraged rapid measures and increased crop yields.

References

[1] “Agriculture Economics and Importance of Agriculture in National Economy,” AgriInfo, [Online]. Available: http://agriinfo.in/?page=topic&superid=9&topicid=185. [Accessed: Nov. 23, 2015]. [2] “Agriculture Sector in India.” [Online]. Available:http://www.ibef.org/industry/agriculture-india.aspx. [Accessed: 23-Nov-2015]. [3] L. P. Gianessi, “Importance of Pesticides for Growing Rice in South and Southeast Asia,\" pp. 30–33, 2014. [4] “Rice Production (Peace Corps): Chapter 14 - Diseases of rice.”[Online]. Available: http://www.nzdl.org. [Accessed: 23-Nov-2015]. [5] Q. Yao, Z. Guan, and Y. Zhou, \"Application of support vector machine for detecting rice diseases using shape and color texture features,\" in International Conference on Engineering Computation, pp. 79-83, 2009. [6] S. Phadikar, J. Sil, and A. K. Das, \"Classification of Rice Leaf Diseases Based on Morphological Changes,\" International Journal of Information and Electronics Engineering, vol. 2, pp. 460-463, May 2012. [7] D. Groth and L. S. U. Agcenter, “Rice Disease Identification Photo Link.” [8] “IRRI - Rice science for a better world.” [Online]. Available: http://irri.org/. [Accessed: 23-Nov-2015]. [9] A Fakhri, A Nasir, M Nordin, A Rahman, and A R. Mamat, \"A study of image processing in agriculture application under high performance computing environment,\" International Journal of Computer Science and Telecommunications, vol. 3, no. 8, pp. 16-24, August 2012. [10] L. Liu and G. Zhou, \"Extraction of Rice Leaf Disease Image Based on BP Neural Network,\" in Computational Intelligence and Software Engineering, Wuhan, 2009. [11] N. N. Kurniawati, S. Norul, H. Sheikh, and S. Abdullah, \"Investigation on image processing techniques for diagnosing paddy diseases,\" in Soft Computing and Pattern Recognition, 2009. [12] P.L. Sahu, A. Singh, and K.L. Sinha, \"A survey on data mining techniques for classification,\" vol. 2, no. 1, pp. 65-70, 2015. [13] J. Han, M. Kamber, and J. Pei. Data mining: concepts and techniques: concepts and techniques. Elsevier, 2011. [14] K.I. Rahmani, N. Pal, and K. Arora. \"Clustering of Image Data Using K-Means and Fuzzy K-Means.\" International Journal of Advanced Computer Science and Applications 5, no. 7 (2014): 160-163. [15] J. G. A. Barbedo, \"Digital image processing techniques for detecting, quantifying and classifying plant diseases,\" SpringerPlus, vol. 2, pp. 660, 2013. [16] R. Pandey, S. Naik, and R. Marfatia, \"Image Processing and Machine Learning for Automated Fruit Grading System: A Technical Review,\" International Journal of Computer Applications, vol. 81, no. 16, pp. 29–39, Nov. 2013. [17] A. Vibhute and S. K. Bodhe, \"Applications of image processing in agriculture: a survey,\" International Journal of Computer Applications, vol. 52, no. 2, pp. 34–40, Aug. 2012. Academia [18] S. D. Khirade and A. B. Patil, \"Plant Disease Detection Using Image Processing,\" in Proc. Int. Conf. Computing Communication Control and Automation (ICCUBEA), Pune, India, Feb. 2015, pp. 768–771.

Copyright

Copyright © 2025 Moumita Chowdhury. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.