🤖 AI Summary
To address the absence of tamper-resistant livestock identification in Bangladesh—hindering the deployment of sustainable livestock insurance—this study proposes an AI-based biometric identification system leveraging nasal-labial groove texture in cattle. We first empirically validate, at scale (826 cattle, 32,374 images), the individual uniqueness of nasal-labial patterns, establishing a fingerprint-analogous biometric paradigm. We then introduce a novel end-to-end framework integrating YOLOv5 for nasal-labial region detection and FaceNet for metric learning, enhanced by CLAHE preprocessing and L2-distance-based matching. The system achieves 96.489% accuracy, 97.334% F1-score, 87.993% true positive rate (TPR), and only 0.098% false positive rate (FPR). Designed for edge deployment, it delivers a low-cost, tamper-proof identification solution tailored to smallholder farmers, thereby enabling scalable and trustworthy livestock insurance programs.
📝 Abstract
Absence of tamper-proof cattle identification technology was a significant problem preventing insurance companies from providing livestock insurance. This lack of technology had devastating financial consequences for marginal farmers as they did not have the opportunity to claim compensation for any unexpected events such as the accidental death of cattle in Bangladesh. Using machine learning and deep learning algorithms, we have solved the bottleneck of cattle identification by developing and introducing a muzzle-based cattle identification system. The uniqueness of cattle muzzles has been scientifically established, which resembles human fingerprints. This is the fundamental premise that prompted us to develop a cattle identification system that extracts the uniqueness of cattle muzzles. For this purpose, we collected 32,374 images from 826 cattle. Contrast-limited adaptive histogram equalization (CLAHE) with sharpening filters was applied in the preprocessing steps to remove noise from images. We used the YOLO algorithm for cattle muzzle detection in the image and the FaceNet architecture to learn unified embeddings from muzzle images using squared $L_2$ distances. Our system performs with an accuracy of $96.489%$, $F_1$ score of $97.334%$, and a true positive rate (tpr) of $87.993%$ at a remarkably low false positive rate (fpr) of $0.098%$. This reliable and efficient system for identifying cattle can significantly advance livestock insurance and precision farming.