Home / Current Issue / Paper 1709140
CNN-Based Classification for Lumpy Skin Disease Detection (Bovine-HealthGuard)
Subject area: Science,Engineering and Technology · Area of research: Science (Computer Science)
Abstract
Lumpy Skin Disease (LSD) is a disease that affects cattle all over the world, characterized by distinctive skin nodules caused by the nettling virus. This disease poses significant financial challenges due to its negative effects on milk production, skin quality, and overall cattle health, Although LSD originated in sub-Saharan Africa, recent outbreaks in Europe and the Middle East. The disease continues to have an incredible ability to spread across cattle worldwide. In order to prevent animal disease outbreaks, technological solutions are urgently required, as the present conventional methods for LSD detection are time-consuming and require skilled experts. By examining into the epidemiology, patterns of transmission, and economic effects of LSD, this study seeks to improve on detection of lumpy skin disease. With the implementation of the trending technology - Deep Learning, (Convolutional Neural Networks (CNNs)) on lumpy skin disease image datasets for detection. Image preprocessing were utilized and resized to 640x640 pixels on YOLOv5 model and 200x200 pixels on Xception and ResNet models. Regions of interest were identified as an adaptive thresholding segmentation, while noise was reduced and image intensity was balanced using Gaussian filtering and histogram equalization. Experimental results demonstrated that YOLOv5 outperformed the two other models with 82.89% of accuracy compared to ResNet and Xception. The study shows that the importance of web integration to enable the detection of widespread lumpy skin diseases in a real time application.
Keywords
Lumpy Skin, Convolutional Neural Network, Image Processing, Bovine-Health guard, Disease Detection.
How to cite this paper
@article{1709140,
author = {Toyin Okebule},
title = {CNN-Based Classification for Lumpy Skin Disease Detection (Bovine-HealthGuard)},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {8},
number = {12},
pages = {966-974},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1709140.pdf},
abstract = {Lumpy Skin Disease (LSD) is a disease that affects cattle all over the world, characterized by distinctive skin nodules caused by the nettling virus. This disease poses significant financial challenges due to its negative effects on milk production, skin quality, and overall cattle health, Although LSD originated in sub-Saharan Africa, recent outbreaks in Europe and the Middle East. The disease continues to have an incredible ability to spread across cattle worldwide. In order to prevent animal disease outbreaks, technological solutions are urgently required, as the present conventional methods for LSD detection are time-consuming and require skilled experts. By examining into the epidemiology, patterns of transmission, and economic effects of LSD, this study seeks to improve on detection of lumpy skin disease. With the implementation of the trending technology - Deep Learning, (Convolutional Neural Networks (CNNs)) on lumpy skin disease image datasets for detection. Image preprocessing were utilized and resized to 640x640 pixels on YOLOv5 model and 200x200 pixels on Xception and ResNet models. Regions of interest were identified as an adaptive thresholding segmentation, while noise was reduced and image intensity was balanced using Gaussian filtering and histogram equalization. Experimental results demonstrated that YOLOv5 outperformed the two other models with 82.89% of accuracy compared to ResNet and Xception. The study shows that the importance of web integration to enable the detection of widespread lumpy skin diseases in a real time application.},
keywords = {Lumpy Skin, Convolutional Neural Network, Image Processing, Bovine-Health guard, Disease Detection.},
month = {June},
}