Author:
Revathy P, Nandhini S, Nivetha G RPublished in
Journal of Science Technology and Research( Volume , Issue )
[1] Sengupta, S.; Das, A.K. Dimension Reduction Using Clustering Algorithm and Rough Set Theory. In International Conference on Swarm, Evolutionary, and Memetic Computing; Springer: Berlin/Heidelberg, Germany, 2012; Volume 7677, pp. 705–712
[2] Ramesh, S.; Vydeki, D. Rice Blast Disease Detection and Classification usingMachine Learning Algorithm. In Proceedings of the IEEE International Conferenceon Micro-Electronics and Telecommunication Engineering, Ghaziabad, India, 20–21 September 2018.
[3] Bakar, M.N.A.; Abdullah, A.H.; Rahim, N.A.; Yazid, H.; Misman, S.N.; Masnan, M.J. Rice Leaf Blast Disease Detection Using Multi-Level Colour Image Thresholding. J. Telecommun. Electron. Comput. Eng. JTEC 2018, 10, 1–6.
[4] Larijani, M.R.; Asli-Ardeh, E.A.; Kozegar, E.; Loni, R.Evaluation of image processing technique in identifying rice blast disease in field conditions based on KNN algorithm improvement by k-means. Food Sci. Nutr. 2019, 7, 3922–3930. [CrossRef] [PubMed].
[5] Shreekanth, K.N.; Suresha, M.; Naik, H. A Novel Segmentation and Identification of Diseases in Paddy Leaves Using Color Image Fusion Technique. In Proceedings of the IEEE International Conference on Image Information Processing (ICIIP), Shimla, India, 15–17 November 2019.
[6] Nidhis, A.D.; Pardhu, C.N.V.; Reddy, K.C.; Deepa,K. Cluster Based Paddy Leaf Disease Detection, Classification and Diagnosis in Crop Health Monitoring Unit. In Lecture Notes in Computational Vision and Biomechanics; Springer Nature: Cham, Switzerland, 2019.
[7] Kawcher, A.; Shahidi, T.; Syed, M.I.A.; Sifat, M. Rice Leaf Disease Detection Using Machine Learning Techniques. In Proceedings of the IEEE International Conference on Sustainable Technologies for Industry 4.0 (STI), Dhaka, Bangladesh, 24–25 December 2019;pp. 24–25.
ABSTRACT:
Outbreaks of plant diseases reduce agricultural yield and threaten food stability. Web App for Automatic Detection of plant leaf disease is a major step forward in agricultural automation. Rapid and accurate identification of infected leaves improves productivity and crop quality. Traditional detection methods often fail due to limited accuracy and manual intervention. This project introduces a machine learning-based solution that automates disease detection from rice plant leaves using dilated CNN. The approach eliminates the need for manual feature selection by extracting disease-specific features directly from images. The dataset includes images of Bacterial leaf blight, Brown spot, and Leaf smut. We preprocess the images, split them for training and testing, and feed them into a dilated CNN model for classification. The system achieves high prediction accuracy and is integrated into a web-based application. This helps farmers detect disease early and prevent crop loss, supporting precision agriculture.
INTRODUCTION:
Agriculture holds a vital role in the Indian economy and ranks second globally in rice production. Maintaining crop health is crucial for food quality and profit. However, plant diseases significantly reduce both yield and quality. To address this issue, we developed a Web App for Automatic Detection of rice plant leaf diseases using dilated convolutional neural networks (CNNs). This deep learning technique efficiently processes large datasets and learns patterns without manual intervention. Dilated CNN increases the receptive field without adding more parameters, enabling better disease localization from leaf images. The image dataset used includes Bacterial leaf blight, Brown spot, and Leaf smut. We remove image backgrounds during preprocessing and train the model with optimized dilation rates. The trained model can predict diseases from new images with high accuracy. This paper details our proposed system, methodology, and results, emphasizing how machine learning can transform traditional agricultural practices.
