Copyright © 2025 Authors retain the copyright of this article. This article 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.

@article{169762,
        author = {Mahadevi K C and Ashwini K.S and Smitha H.S},
        title = {Enhanced Plant Health Monitoring with Deep Learning for Leaf Disease Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {7},
        number = {10},
        pages = {369-375},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169762},
        abstract = {Deep neural networks (DNNs) have proven highly effective in classifying various plant diseases, playing a key role in addressing agricultural risks and improving crop yield. When left untreated or unidentified, plant diseases can seriously impact the quality and quantity of produce, posing significant challenges to farmers. Early detection of plant diseases is essential, as it enhances crop quality and minimizes production losses. In response, a modern approach has been developed that incorporates image acquisition techniques and diverse image types for more accurate disease identification. This approach leverages DNN models to evaluate model performance through metrics such as recall, F1 score, accuracy, and precision, ensuring a comprehensive assessment. The variability in results helps distinguish between healthy and diseased plant leaves, providing precise information about bacterial infections. The methodology has been tested on two plant types: pepper and potato leaves, which are commonly susceptible to diseases. Additionally, the model is designed to estimate the infection percentage on each leaf, offering farmers valuable insights into the extent of damage. This combination of DNN-based analysis and detailed performance metrics allows for a robust system that not only identifies the presence of disease but also quantifies its severity. Such advancements in plant disease identification hold the potential to significantly improve crop management practices, reduce the risk of disease spread, and ultimately contribute to a more sustainable agricultural process.},
        keywords = {Deep learning, leaf disease, intelligent recognition, DNN.},
        month = {November},
        }