LSR-YOLO: A High-Precision, Lightweight Model for Sheep Face Recognition on the Mobile End

Abstract

The accurate identification of sheep is crucial for breeding, behavioral research, food quality tracking, and disease prevention on modern farms. As a result of the time-consuming, expensive, and unreliable problems of traditional sheep-identification methods, relevant studies have built sheep face recognition models to recognize sheep through facial images. However, the existing sheep face recognition models face problems such as high computational costs, large model sizes, and weak practicality. In response to the above issues, this study proposes a lightweight sheep face recognition model named LSR-YOLO. Specifically, the ShuffleNetv2 module and Ghost module were used to replace the feature extraction module in the backbone and neck of YOLOv5s to reduce floating-point operations per second (FLOPs) and parameters. In addition, the coordinated attention (CA) module was introduced into the backbone to suppress non-critical information and improve the feature extraction ability of the recognition model. We collected facial images of 63 small-tailed Han sheep to construct a sheep face dataset and further evaluate the proposed method. Compared to YOLOv5s, the FLOPs and parameters of LSR-YOLO decreased by 25.5% and 33.4%, respectively. LSR-YOLO achieved the best performance on the sheep face dataset, and the mAP@0.5 reached 97.8% when the model size was only 9.5 MB. The experimental results show that LSR-YOLO has significant advantages in recognition accuracy and model size. Finally, we integrated LSR-YOLO into mobile devices and further developed a recognition system to achieve real-time recognition. The results show that LSR-YOLO is an effective method for identifying sheep. The method has high recognition accuracy and fast recognition speed, which gives it a high application value in mobile recognition and welfare breeding.

Improved Wildlife Recognition through Fusing Camera Trap Images and Temporal Metadata

“…Xie et al [39] introduced SE attention in YOLOv5 to improve big mammal species detection from a UAV viewpoint. Zhang et al [43] introduced a coordinated attention (CA) module in YOLOv5s to suppress non-critical information on the face of sheep to recognize the identity of sheep in real time. Given the different lighting conditions and backgrounds present in camera trap images, to better extract wildlife features, we compared the performance of the model after adding different attention modules and found that the addition of the SE attention mechanism can further improve wildlife recognition by 0.09%.…”

Recognition model for coated red clover seeds using YOLOv5s optimized with an attention module

“…The YOLO framework effectively distinguishes target and background areas to achieve target recognition [30,31] . The YOLOv5s is composed of inputs, backbone, neck, head, and output.…”

Contextualized Small Target Detection Network for Small Target Goat Face Detection

“…To evaluate the performance of the proposed model more fairly and accurately, this paper used precision (P), recall (R), F1-Score(F1), and AP for the performance evaluation and comparison [30]. The formulae for each metric used in this paper are presented below:…”