4AC-YOLOv5: an improved algorithm for small target face detection

Abstract

In real scenes, small target faces often encounter various conditions, such as intricate background, occlusion and scale change, which leads to the problem of omission or misdetection of face detection results. To solve this puzzle, an improved algorithm of small target face detection 4AC-YOLOv5 is proposed. First, the algorithm by introducing a new layer to detect faces at a much smaller size, through the fusion of more shallow information, enhance the network perception of small objects, the accuracy of small target detection is improved; second, to improve the neck structure, to add the adaptive feature fusion network AFPN to replace FPN + PAN, to prevent the large information gap between non-adjacent Level to some extent, and to fully retain and integrate different scale characteristic information; and finally, improve the C3 module and propose a new multiscale residual module C3_MultiRes. Improving the expressive power of the network by introducing a multibranched structure and gradually increasing resolution somewhat reduces the complexity of the model calculation. The experimental results show that the precision of the improved model reached 94.54%, 93.08% and 84.98% in easy, medium and hard levels of WiderFace data set, respectively, and the results of detection are better than the original network. 4AC-YOLOv5 can meet the requirements of small target face detection in complex environment.