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{173676,
        author = {Prof. Dr. P.D. Khandait and Kalash Lanjewar and Sohit Patle and Rajwanshi Meshram},
        title = {Deep Learning-Based Cattle Disease Detection: A CNN Approach for Identifying Lumpy Skin Disease and Foot-and-Mouth Disease},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {1068-1077},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=173676},
        abstract = {Increasing prevalence of cow diseases such as Lumpy Skin Disease and Foot-and-Mouth Disease presents a significant challenge to livestock health and agricultural economies. traditional diagnostic Techniques are frequently costly, time-consuming, and prone to human error., necessitating the development of automated solutions. Deep learning, specifically Convolutional Neural Networks , for classifying cow health conditions into three categories: healthy, LSD, and FMD. The methodology involves dataset collection, preprocessing, model training, evaluation, and performance visualization. A diverse dataset of cow images was collected and divided into training and testing sets. Preprocessing operations involved resizing, normalization, and data augmentation for increasing model robustness. Multiple CNN architectures, such as DenseNet121, ResNet50V2, InceptionV3, VGG16, VGG19, and Xception, were tested with pre-trained ImageNet weights for transfer learning. Max Pooling, dense layers with ReLU activation, dropout layers for regularization, and a SoftMax output layer for classification were appended as part of fine-tuning. Adam optimiser, and cross-entropy loss, as well as early stopping, were employed for model training to prevent overfitting. Accuracy, precision, recall, F1-score, and confusion matrices were employed to compare the performance. It was noticed that CNN-based models classify cow diseases effectively, especially with transfer learning and data augmentation. The proposed system can be utilized by farmers and veterinarians to diagnose diseases early and lower costs as well as better manage livestock health. This work improves automated cattle health monitoring using an efficient and scalable approach to disease classification of cattle.},
        keywords = {Convolutional Neural Networks (CNNs), DenseNet121, Image Processing, InceptionV3, ResNet50V2, VGG16, VGG19.},
        month = {March},
        }