CANINE INJURY DETECTION: A COMPARATIVE ANALYSIS OF IMAGE CLASSIFICATION MODELS
Authors/Creators
Contributors
Researcher (5):
Description
The swift and accurate detection of canine injuries
is crucial for timely medical intervention and enhancing public
safety. This study presents a comprehensive analysis of three
image classification models—Convolutional Neural Networks
(CNN), Random Forest, and Support Vector Machines (SVM)—
for detecting injuries in dogs. Utilizing a meticulously curated
dataset of over 2000 images, the research emphasizes robust data
gathering, cleaning, and preprocessing techniques. Experimental
results reveal that CNN outperforms with an accuracy of 75.78%,
followed closely by Random Forest and SVM. The findings
highlight the strengths and limitations of each model, offering
valuable insights into their applicability in real-world scenarios.
This research underscores the potential of advanced machine
learning models in promoting animal welfare and lays a
foundation for further advancements in the field of computer
vision applications in veterinary care.