International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Agrovision AI: Unified Platform for Disease Detection and Crop Yield Estimation |
|---|---|
| ABSTRACT | AgroVision AI presents an integrated plant leaf disease detection and agricultural advisory system combining deep learning, mobile deployment, and multilingual AI assistance. A custom VGG-style Convolutional Neural Network (five-block architecture) was trained on a refined subset of the PlantVillage dataset, consisting of 21 disease classes and 38,585 images. Initial performance degradation caused by missing normalization and limited training epochs was resolved by introducing a Rescaling layer, data-augmentation strategies, and extending training to 25 epochs with a low learning rate. The optimized model enables accurate disease classification and is deployed within a React Native mobile application that supports real-time image capture, prediction, and language translation across five regional languages. The system further integrates Gemini-based treatment recommendations and an AI-driven crop yield estimator, providing farmers with a complete decision-support framework. This work demonstrates how lightweight deep learning models and multilingual interfaces can enhance accessibility and reliability in precision agriculture. |
| AUTHOR | KOUSHIK A, N V NRUTYA, NITISH R MALADAKAR, TEJASWINI K J, MOHAMED MUTHAHIR R U.G. Student, Department of CS&E, Bapuji Institute of Engineering and Technology, Davanagere, Karnataka, India Professor, Department of CS&E, Bapuji Institute of Engineering and Technology, Davanagere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312147 |
| pdf/147_Agrovision AI Unified Platform for Disease Detection and Crop Yield Estimation.pdf | |
| KEYWORDS | |
| References | [1] A. Upadhyay et al., “Deep Learning and Computer Vision in Plant Disease Detection,” Artificial Intelligence Review, vol. 58, p. 92, 2025. [2] I. Bouacida et al., “Innovative Deep Learning Approach for Cross-Crop Plant Disease Detection,” Information Processing in Agriculture, vol. 12, no. 1, pp. 54–67, 2025. [3] S. Duhan et al., “RTR_Lite_MobileNetV2: A Lightweight Model for Plant Disease Detection,” Current Plant Biology, vol. 42, p. 100459, 2025. [4] A. Y. Ashurov et al., “Enhancing Plant Disease Detection Using Depthwise CNN with SE Integration,” Frontiers in Plant Science, vol. 15, p. 1505857, 2025. [5] K. I. Roumeliotis et al., “Plant Disease Detection through Multimodal LLMs and CNNs,” arXiv, 2025. [6] Z. Zeng et al., “AI-Driven Smart Agriculture Using Hybrid Transformer-CNN,” Scientific Reports, vol. 15, p. 25408, 2025. [7] C. Pal et al., “A Lightweight and Explainable CNN Model for Plant Disease Diagnosis,” Scientific Reports, vol. 15, p. 30720, 2025. [8] K. N. Rahman et al., “A Real-Time Monitoring System for Accurate Plant Leaf Disease Detection,” Crop Design, vol. 4, no. 1, p. 100092, 2025. [9] T. D. Salka et al., “Plant Leaf Disease Detection Using CNN Models: A Review,” Artificial Intelligence Review, vol. 58, p. 322, 2025. [10] A. González-Briones et al., “Advanced CNN Architectures for Enhanced Plant Disease Detection,” International Journal of Computational Intelligence Systems, vol. 18, p. 120, 2025. |
