Holstein Cattle Face Re-Identification Unifying Global and Part Feature Deep Network with Attention Mechanism

SIMPLE SUMMARY: Automated and non-intrusive recognition of individual livestock such as a cow or a pig is a vital requirement for obtaining individual information, something which has played a significant role in the intelligent management and welfare of livestock. However, individual cow identification remains a demanding task mainly due to the quite yet subtle inter-class differences in an open herd setting. The objective of this study is to develop a novel unified global and part feature deep network model (GPN) to learn more discriminative and robust features that can facilitate cow face representation for re-identification and verification. The results of various contrast experiments on collecting the large-scale cow face dataset show that the proposed GPN model outperforms the existing representative re-identification methods, and the further improved GPN-ST model has a higher accuracy rate (up by 2.8% and 2.2% respectively) in Rank-1 and mAP, compared with the GPN model. In conclusion, using the proposed framework can effectively ameliorate the performance of cow face re-identification. ABSTRACT: In precision dairy farming, computer vision-based approaches have been widely employed to monitor the cattle conditions (e.g., the physical, physiology, health and welfare). To this end, the accurate and effective identification of individual cow is a prerequisite. In this paper, a deep learning re-identification network model, Global and Part Network (GPN), is proposed to identify individual cow face. The GPN model, with ResNet50 as backbone network to generate a pooling of feature maps, builds three branch modules (Middle branch, Global branch and Part branch) to learn more discriminative and robust feature representation from the maps. Specifically, the Middle branch and the Global branch separately extract the global features of middle dimension and high dimension from the maps, and the Part branch extracts the local features in the unified block, all of which are integrated to act as the feature representation for cow face re-identification. By performing such strategies, the GPN model not only extracts the discriminative global and local features, but also learns the subtle differences among different cow faces. To further improve the performance of the proposed framework, a Global and Part Network with Spatial Transform (GPN-ST) model is also developed to incorporate an attention mechanism module in the Part branch. Additionally, to test the efficiency of the proposed approach, a large-scale cow face dataset is constructed, which contains 130,000 images with 3000 cows under different conditions (e.g., occlusion, change of viewpoints and illumination, blur, and background clutters). The results of various contrast experiments show that the GPN outperforms the representative re-identification methods, and the improved GPN-ST model has a higher accuracy rate (up by 2.8% and 2.2% respectively) in Rank-1 and mAP, compared with the GPN model. In conclusion, using the Global and Part feature deep network with attention mechanism can effectively ameliorate the efficiency of cow face re-identification.