Copyright © 2026 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{200016,
        author = {Dr Ennam Govinda and K.V.S Ganesh and Nattala Nagamani and Setti Sirisha and N.V Ashok Kumar},
        title = {Optimized Deep Learning Framework for Early Detection and Classification of Leaf Diseases},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {1618-1625},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200016},
        abstract = {Plant diseases have a profound impact on agricultural productivity and food security. Early detection and classification of leaf diseases play a crucial role in preventing crop losses and improving yield quality. This paper presents an optimized deep learning framework for the early detection and classification of leaf diseases using advanced convolutional neural networks (CNNs). Several pre-trained models, including ResNet50, InceptionV3, AlexNet, MobileNetV1-V3, and EfficientPNet, were evaluated for performance on tomato leaf disease datasets. Among these, EfficientPNet demonstrated superior accuracy, achieving 98.99% (Small variant) and 99.81% (Large variant). The models were deployed both on a workstation and on a Raspberry Pi 4 to evaluate inference latency. EfficientPNet Small achieved latencies of 66 ms and 251 ms, while EfficientPNet Large recorded 50 ms and 348 ms respectively. This work integrates efficient deep learning architectures with IoT-based deployment, offering a scalable solution for real-time agricultural disease monitoring.},
        keywords = {Deep Learning Convolutional Neural Networks, EfficientNet, Leaf Disease Detection, Image Processing, IoT, Smart Agriculture},
        month = {May},
        }