Research on a High-Efficiency Goat Individual Recognition Method Based on Machine Vision.

Simple Summary: Precision animal farming is premised on individual identity recognition, and most existing research use images of front faces to recognize the individual identity of goats because of the inertia of human face recognition. However, due to the rapidity of goat head movement and the high convex of the face structure, a qualified front face image is often not easy to capture under natural conditions. Finding appearances that are easier to capture and more accurate in identifying individual goat identities is valuable for practical precision production. This study revealed the ability of the 54 goats' five outward appearances and their fusion to mark their individual identity. The results showed the side body image provided the highest accuracy, followed by the back body and front face images, with minimal differences between the side face views. The highest accuracy was achieved with the side body image using MobileViT when only one appearance image was used. Two appearances generally outperform one appearance in recognition accuracy; when three or more appearances were utilized for fusion, any of the models have an accuracy of 100%. These findings form a solid foundation for developing practical goat identification systems. Accurate identification of individual goat identity is necessary for precision farming. Previous studies have primarily focused on using front face images for goat identification, leaving the potential of other appearances and multi-source appearance fusion unexplored. In this study, we used a self-developed multi-view appearance image acquisition platform to capture five different appearances (left face, right face, front face, back body, and side body) from 54 Wanlin white goats. The recognition ability of different goat appearance images and its multi-source appearance fusion for its identity recognition was then systematically examined based on the four basic network models, namely, MobileNetV3, MobileViT, ResNet18, and VGG16, and the best combination of goat appearance and network was screened. When only one kind of goat appearance image was used, the combination of side body image and MobileViT was the best, with an accuracy of 99.63%; under identity recognition based on multi-source image appearance fusion, all recognition models after outlook fusion of two viewpoints generally outperformed single viewpoint appearance identity recognition models in recognizing the identity of individual goats; when three or more kinds of goat appearance images were utilized for fusion, any of the four models were capable of identifying the identity of an individual goat with 100% accuracy. Based on these results, a goat individual identity recognition strategy was proposed that balances accuracy, computation, and time, providing new ideas for goat individual identity recognition in complex farming contexts. [ABSTRACT FROM AUTHOR]