Boosting cattle face recognition under uncontrolled scenes by embedding enhancement and optimization

• Published in: Applied soft computing 2024-10, Vol.164, p.111951, Article 111951
• Main Authors: Xu, Xingshi, Deng, Hongxing, Wang, Yunfei, Zhang, Shujin, Song, Huaibo
• Format: Article
• Language: English
• Subjects: Cattle; Cow face recognition; Embedding enhancement; Individual identification; Precision livestock
• ISSN: 1568-4946
• DOI: 10.1016/j.asoc.2024.111951

Accurate individual cattle identification is crucial for modern precision cattle farming. However, practical applications encounter challenges due to factors such as shooting distance and angles, cattle movements, weather conditions, and cattle face posture. Existing models struggle with low recognition accuracy for low-recognizable images and poor robustness to facial pose variations, presenting urgent problems that need to be addressed. In this study, a novel cattle face recognition method was proposed, aiming to solve the aforementioned issues by analyzing and optimizing the embedding distribution of cattle faces. Firstly, MobileFaceNet was employed as the feature extraction network to sufficiently extract discriminative representations. Secondly, due to the tendency of low-recognizable samples to cluster in specific areas of the embedding space, an Embedding Enhancement Module (EEM) was proposed. This module drives embedding features away from ineffective embedding spaces, thereby enhancing the model's ability to extract identity features from less recognizable cattle faces. Finally, an Embedding Optimization Module (EOM) was proposed, which utilized a Sub-Center method to alleviate the model's learning difficulty during early training stages and achieved "pose-irrelevant" clusters by merging Sub-Centers, enhancing robustness to facial pose variations. Experimental results confirmed the effectiveness of the proposed method, with it outperforming the baseline by up to 2.12 % in accuracy, achieving a recognition accuracy of 98.69 %. Furthermore, the application of the proposed method in cattle farms further demonstrated the significant potential value of this work. •Face recognition in uncontrolled scenes was proposed to identify individual cows.•Embedding enhancement module enhanced recognition accuracy for low-recognizable faces.•Embedding optimization module improved robustness to face posture changes.•Experiments deployed in real scenes showed good performance of the proposed method.