• Rishi Yadav
• Dr. Ravi Singh Pippal

Rice is a fundamental crop in India, holding the largest area under cultivation including both brown and white varieties. It plays a crucial role in the nation's economy by providing employment and contributing significantly to the Gross Domestic Product (GDP). With advancements in technology, particularly in the era of machine learning (ML), there has been a shift towards automating the process of detecting diseases in rice plants using image-based analysis. Traditional methods which rely on human vision are being supplemented by ML classifiers that promise earlier detection of diseases, thereby enabling timely preventive measures and minimizing productivity losses. The integration of deep learning techniques has further improved the accuracy of these systems, marking a substantial progress in the fields of agriculture and farming productivity. In this paper comparative analysis of pre-trained models are presented for detection of microbial diseases in rice plants. In proposed model bacterial, viral and fungal diseases are detected using rice plant images. The model has achieved highest accuracy of 90% with ResNet50 model and 89% with inceptionv3 model. As compared to existing model, the proposed model has achieved 8% improvement in detection accuracy and approx. 3sec in execution time. Therefore, the proposed model outperformed better.

Rice Plant Diseases, Image Processing, Bacterial, Viral, Fungal, Deep Learning.

"Enhanced Detection of Microbial Diseases in Rice Plants Using Pre-Trained Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 8, page no.e700-e707, August-2024, Available :http://www.jetir.org/papers/JETIR2408472.pdf

"Enhanced Detection of Microbial Diseases in Rice Plants Using Pre-Trained Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 8, page no. ppe700-e707, August-2024, Available at : http://www.jetir.org/papers/JETIR2408472.pdf