;To address the issue of inaccurate and missed eye and pupil detection caused by the susceptibility of eye images to light interfer-ence,an improved YOLOv5 based eye and pupil detection algorithm is proposed.First of all,image pre-processing is carried out,and three image enhancement methods are compared.It is decided to use CLAHE(limited contrast Adaptive histogram equalization)method with good effect to enhance the image and improve the contrast;Secondly,the Swin Transformer module is introduced into YOLOv5 network to replace the last C3 module of the backbone network and three C3 modules in the three prediction heads,so as to improve the feature extraction ability of the network and improve the detection accuracy of eye parts;Finally,by introducing a multi-scale feature cross layer fusion mechanism in the YOLOv5 network,two target prediction heads are added to reduce the network's missed detection rate for eye and pupil regions.This article selected 2 400 eye datasets with different levels of illumination from the Data setⅩⅧ in the ELSE standard dataset,of which 1 600 were training sets and 800 were testing sets.The experimental results show that the improved YOLOv5 network can detect the entire part of the eye and the complete pupil,with a high detection confidence.The mAP has increased by 3.2 percentage points,the Recall has increased by 2.7 percentage points,and has good real-time performance.
关键词
眼睛及瞳孔检测/YOLOv5/CLAHE/Swin/Transformer/多尺度特征跨层融合机制
Key words
eye part detection/YOLOv5/CLAHE/Swin Transformer/Multi scale feature cross layer fusion mechanism
维普
万方数据