Hair-YOLO: A Hair Follicle Detection Model Based on YOLOv8

Abstract

Abstract Hair follicle detection technology has developed rapidly in recent years. Traditional manual detection methods are labor-intensive and inefficient. To address this problem, we propose a real-time hair follicle detection model called Hair-YOLO based on YOLOv8. This model focuses on accurately identifying the number of hairs within each follicle, providing precise data that help doctors assess hair density and follicle health of patients. First of all, we incorporate the Re-parameterization Ghost (RepGhost) module into the backbone, reducing the parameters and computational load. Then, the Deformable Convolution v3 (DCNv3) operator is integrated into the neck network, enhancing adaptation to follicle shapes. Next, we propose a novel Multi-scale Feature Perception Separated and Enhancement Attention (Multi-SEAM) module, building upon the Separated and Enhancement Attention (SEAM) module, to address complex scalp scenarios. Furthermore, we enhance bounding box regression by replacing the standard Complete Intersection over Union (CIoU) loss, with a Modified Point Distance Intersection over Union (MPDIoU) loss. Finally, we construct a new hair follicle dataset and use it for a comparative analysis of Hair-YOLO and established models. Our model shows excellent performance, with a 14.26% increase in mAP@0.5:0.95, a 2.98% increase in Recall, and a 4.31% increase in Precision compared to the baseline.