Computer vision-based approaches to cattle identification: A comparative evaluation of body texture, QR code, and numerical labelling

<br />Cattle identification systems are advancing tomeet the growing demands ofprecision livestock management, traceability, and ethical animal treatment. This study investigates three methods: body texture recognition, QR code collars, and numerical labelling, implemented using the YOLOv8 convolutional neural network. Each method was evaluated interms ofaccuracy, scalability, adaptability todynamic herd changes, and operational efficiency under various environmental conditions. Body texture recognition, while leveraging unique natural patterns and achieving amean Average Precision (mAP50–95) of0.78 proved limited byits reliance onfrequent dataset retraining toaccommodate changes inherd composition and susceptibility tomisidentification inlarger herds. QRcode collars demonstrated adaptability indynamic herds byenabling pre-trained convolutional neural networks toassign reserved codes tonew animals without retraining, while removing animals involves simply deleting their codes from the system. This approach also achieved anmAP50–95 of0.71, which was lower than the body texture-based approach, but offered greater flexibility in herd management. Despite this adaptability, this method demonstrated significant challenges inreal-world environments. Occlusion caused byfeeders, barriers, oranimal movements, along with low-resolution imaging and poor lighting conditions, can compromise detection accuracy, particularly inlarger herds with obstructive barn layouts. The numerical labelling method emerged asthe most effective solution todynamic cattle identification, achieving the highest mAP50–95 of0.84. Itprovided ascalable and highly accurate approach that integrates seamlessly with automated systems. Unlike traditional body marking techniques such asear notching and branding, numerical labelling isless invasive, painless, and highly scalable, aligning with ethical livestock management practices while maintaining consistent accuracy across diverse environmental conditions.