《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (8): 2588-2594.DOI: 10.11772/j.issn.1001-9081.2023081198

• 多媒体计算与计算机仿真 • 上一篇    下一篇

基于图像增强的低照度人脸检测

李钟华, 白云起, 王雪津(), 黄雷雷, 林初俊, 廖诗宇   

  1. 福建理工大学 计算机科学与数学学院,福州 350118
  • 收稿日期:2023-09-06 修回日期:2023-10-18 接受日期:2023-11-03 发布日期:2024-08-22 出版日期:2024-08-10
  • 通讯作者: 王雪津
  • 作者简介:李钟华(1976—),男,福建南平人,副教授,博士,主要研究方向:人工智能、图像处理
    白云起(1999—),男,河南焦作人,硕士研究生,主要研究方向:图像处理、计算机视觉
    王雪津(1989—),女,福建莆田人,副教授,博士,主要研究方向:图像处理、计算机视觉 wxj2021@fjut.edu.cn
    黄雷雷(1999—),男,河南周口人,硕士研究生,主要研究方向:图像处理、计算机视觉
    林初俊(1999—),男,福建宁德人,硕士研究生,主要研究方向:图像处理、计算机视觉
    廖诗宇(1999—),男,湖南衡阳人,硕士研究生,主要研究方向:图像处理、计算机视觉。
  • 基金资助:
    福建省自然科学基金资助项目(2022J01954);福建省中青年教师教育科研项目(JAT210288)

Low illumination face detection based on image enhancement

Zhonghua LI, Yunqi BAI, Xuejin WANG(), Leilei HUANG, Chujun LIN, Shiyu LIAO   

  1. School of Computer Science and Mathematics,Fujian University of Technology,Fuzhou Fujian 350118,China
  • Received:2023-09-06 Revised:2023-10-18 Accepted:2023-11-03 Online:2024-08-22 Published:2024-08-10
  • Contact: Xuejin WANG
  • About author:LI Zhonghua, born in 1976, Ph. D., associate professor. His research interests include artificial intelligence, image processing.
    BAI Yunqi, born in 1999, M. S. candidate. His research interests include image processing, computer vision.
    HUANG Leilei, born in 1999, M. S. candidate. His research interests include image processing, computer vision.
    LIN Chujun, born in 1999, M. S. candidate. His research interests include image processing, computer vision.
    LIAO Shiyu, born in 1999, M. S. candidate. His research interests include image processing, computer vision.
  • Supported by:
    Natural Science Foundation of Fujian Province(2022J01954);Educational Research Project of Middle-Aged and Young Teachers of Fujian Province(JAT210288)

摘要:

针对人脸检测模型在低照度环境下出现的检测性能明显降低这一问题,提出一种基于图像增强的低照度人脸检测方法。首先,采用图像增强方法对低照度图像预处理,以增强人脸的有效特征信息;其次,在模型主干网络后引入注意力机制,以提升网络对人脸区域的关注,并同时降低非均匀光照与噪声带来的负面影响;此外,引入注意力边界框损失函数WIoU(Wise Intersection over Union),以提升网络对低质量人脸的检测准确率;最后,使用更有效的特征融合模块代替模型原有结构。在低照度人脸数据集DARK FACE上的实验结果表明,所提方法的平均检测精度AP@0.5相较于原始YOLOv7模型提升了2.4个百分点,精度平均值AP@0.5:0.95提升了1.4个百分点,并且不引入额外参数与计算量。另外,在其他2个低照度人脸数据集上的结果也表明所提方法的有效性与鲁棒性,证明所提方法适用于不同场景下的低照度人脸检测。

关键词: 人脸检测, 图像增强, 注意力机制, 损失函数, 低照度环境

Abstract:

In response to the issue of significantly reduced detection performance of face detection models in low-light conditions, a low-light face detection method based on image enhancement was developed. Firstly, image enhancement techniques were applied to preprocess low-light images, enhancing the effective facial features. Secondly, an attention mechanism was introduced after the model’s backbone network to increase the network’s focus on facial regions and reduce the negative impact of non-uniform lighting and noise simultaneously. Furthermore, an attention-based bounding box loss function — Wise Intersection over Union (WIoU) was incorporated to improve the network’s accuracy in detecting low-quality faces. Finally, a more efficient feature fusion module was used to replace the original model structure. Experimental results on the low-light face dataset DARK FACE compared to the original YOLOv7 model indicate that the improved method achieves an increase of 2.4 percentage points in average detection precision AP@0.5 and an increase of 1.4 percentage points in mean value of average precision AP@0.5:0.95, all without introducing additional parameters or computational complexity. Additionally, the results on two other low-light face datasets confirm the effectiveness and robustness of the proposed method, approving the applicability of the method for low-light face detection in diverse scenarios.

Key words: face detection, image enhancement, attention mechanism, loss function, low illumination environment

中图分类号: