Multiple Skin Disease Detection for Cattle Using Deep Learning

We developed a web-based tool that identifies eight cattle skin conditions from a photograph. A two-stage trained MobileNetV2 does the classification, and a Flask site makes it usable by someone with no technical background: log in, upload, read the answer. The 75% rule keeps doubtful outputs from being shown as diagnoses, and because the model, the disease list and the hosting are separate parts, each can be changed without touching the others. Our tests indicate that this kind of system can give a quick, inexpensive first opinion where a veterinarian is far away, as long as its limits are stated plainly.  

[1]    N. Umapathi, B. Vivekanandam and B. K. Mishra, “A deep learning framework for early detection and treatment of livestock skin diseases,” SGS Engineering & Sciences, vol. 1, no. 4, 2025. [2]   K. Yiğitarslan and I. Kırbaş, “Classification of digital dermatitis with image processing and machine learning methods,” Advances in Artificial Intelligence Research, 2023. [3]  M. Z. Shakeel et al., “A deep learning tool for early detection and control of lumpy skin disease,” Journal of Computational Biology and Informatics, 2023. [4]  W. Abdullah, S. Tanwar and M. Abouhawwash, “Deep learning-based detection of lumpy skin disease in livestock using CNNs,” Sustainable Machine Intelligence Journal, 2025. [5]     A. Krizhevsky, I. Sutskever and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Advances in Neural Information Processing Systems (NIPS), 2012. [6]  Y. LeCun, Y. Bengio and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015. [7]   C. Shorten and T. M. Khoshgoftaar, “A survey on image data augmentation for deep learning,” Journal of Big Data, vol. 6, art. 60, 2019. [8]   M. Genemo, “Detecting high-risk area for lumpy skin disease in cattle using deep learning feature,” Advances in Artificial Intelligence Research (AAIR), 2023. [9]  M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2018. [10]     OIE (World Organisation for Animal Health), Manual of Diagnostic Tests and Vaccines for Terrestrial Animals: Cattle Diseases, 2023.