Accurate animal identification is vital for precision livestock farming, yet existing biometric methods often struggle with subtle inter-animal similarities and the lack of public datasets, especially for indigenous breeds. This study introduces a curated bovine facial dataset comprising 3,680 images from 184 Indian cows, generated through automated video frame extraction, sharpness-based filtering, YOLOv11 face detection, and clustering for quality and diversity. Three CNN architectures—ResNet-50, Inception-V3, and EfficientNet-B4—were evaluated using cross-entropy loss. EfficientNet-B4 achieved the highest closed-set accuracy (97.28%), while ResNet-50 showed superior open-set robustness with the lowest EER (0.0550). The results underscore architectural trade-offs in cattle biometrics and identify ResNet-50 as the most reliable model for secure livestock monitoring and traceability.