计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (2): 191-201.doi: 10.11896/jsjkx.231100166

• 计算机图形学&多媒体 • 上一篇    下一篇

基于多任务联合学习的弱光场景人脸检测算法

张霞1, 苏昭辉1,2, 陈路1,2   

  1. 1 山西大学计算机与信息技术学院 太原 030006
    2 山西大学大数据科学与产业研究院 太原 030006
  • 收稿日期:2023-11-27 修回日期:2024-04-29 出版日期:2025-02-15 发布日期:2025-02-17
  • 通讯作者: 陈路(chenlu@sxu.edu.cn)
  • 作者简介:(zhangxia@sxu.edu.cn)
  • 基金资助:
    国家自然科学基金(62072291,62373233,62003200);山西省科技重大专项计划(202201020101006);中央引导地方科技发展资金(YDZJSX20231B001)

Face Detection Algorithm Based on Multi-task Joint Learning in Weak Light Scenes

ZHANG Xia1, SU Zhaohui1,2, CHEN Lu1,2   

  1. 1 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China
    2 Institute of Big Data Science and Industry,Shanxi University,Taiyuan 030006,China
  • Received:2023-11-27 Revised:2024-04-29 Online:2025-02-15 Published:2025-02-17
  • About author:ZHANG Xia,born in 1977,Ph.D,asso-ciate professor,is a member of CCF(No.22705M).Her main research interests include artificial intelligence,machine learning and image processing.
    CHEN Lu,born in 1991,Ph.D,asso-ciate professor,is a member of CCF(No.E0588M).His main research interests include robotic grasping and image enhancement.
  • Supported by:
    National Natural Science Foundation of China(62072291,62373233,62003200),Science and Technology Major Project of the Ministry of Science and Technology of Shanxi Province,China(202201020101006) and Central Government Guiding Funds for Local Science and Technology Development(YDZJSX20231B001).

PDF (PC)

136

摘要： 弱光场景中的人脸检测指在弱光条件下使用图像处理技术检测人脸。目前,大多数弱光环境下的人脸检测算法通常先将弱光图像进行增强再进行人脸检测,忽略了人脸检测和图像增强任务之间的特征相关性,从而影响了模型泛化能力。受EnlightenGAN算法的启发,文中提出一种适用于弱光环境人脸检测的多任务联合学习算法:首先融合人脸检测和图像增强的输入层共享表示;其次将人脸注意力网络和EnlightenGAN相结合,在全局-局部判别器的基础上增加用于人脸区域判定的局部判别器;最后在自正则化注意力图的基础上增加光照权重参数,通过调节使人脸检测的精度达到最佳值。在DARK FACE数据集上的实验结果表明,与现有算法相比,所提算法的人脸检测精度提升了1.92%,同时能够很好地提升弱光图像视觉质量。

关键词: 弱光环境, 人脸检测, 图像增强, 多任务联合学习, 局部判别器

Abstract: In weak light scenes,face detection refers to the use of image processing techniques to detect faces.Currently,most face detection algorithms in weak light environments typically enhance the weak light images before performing face detection,neglecting the feature correlation between face detection and image enhancement,thereby affecting the generalization ability of the model.Inspired by the EnlightenGAN algorithm,this paper proposes a Multitask joint learning algorithm for face detection in weak light environments.First,it integrates the input layer shared representation of face detection and image enhancement.Se-cond,it combines the face attention network with EnlightenGAN,adding a local discriminator for face region determination based on the global-local discriminator.Finally,it introduces illumination weight parameters on the basis of self-regularized attention maps,adjusting them to optimize the accuracy of face detection.Experimental results on the DARK FACE dataset demonstrate that,compared with existing algorithms,the proposed algorithm achieves a 1.92% improvement in face detection accuracy,while also effectively enhances the visual quality of images captured under weak light conditions.

Key words: Weak light environment, Face detection, Image enhancement, Multi-task joint learning, Local discriminator

中图分类号: 

  • TP391
[1]XIE C,TANG H,FEI L,et al.IRNet:An improved zero-shotretinex network for low-light image enhancement[J].Electro-nics,2023,12(14):3162-3169.
[2]WEI C,WANG W,YANG W,et al.Deep retinex decomposition for low-light enhancement[DB/OL].(2020-12-17) [2023-10-12].https://doi.org/10.48550/arXiv.1808.04560.
[3]CHEN C,CHEN Q,XU J,et al.Learning to see in the dark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:3291-3300.
[4]LIU W,REN G,YU R,et al.Image-adaptive YOLO for object detection in adverse weather conditions[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2022.
[5]QI D,TAN W,YAO Q,et al.YOLO5Face:why reinventing a face detector[C]//European Conference on Computer Vision.Cham:Springer Nature Switzerland.2022:228-244.
[6]CHEN Z,YANG C,CHANG J,et al.DDOD:Dive Deeper into the Disentanglement of Object Detector[J].IEEE Transactions on Multimedia,2023,22(1):77-84.
[7]CARION N,MASSA F,SYNNAEVE G,et al.End-to-end object detection withtransformers[C]//European Conference on Computer Vision.Cham:Springer International Publishing.2020:213-229.
[8]SONG H,SUN D,CHUN S,et al.Vidt:An efficient and effective fully transformer-based object detector[DB/OL].(2021-11-29) [2023-10-12].https://doi.org/10.48550/arXiv.2110.03921.
[9]BEAL J,KIM E,TZENG E,et al.Toward transformer-basedobject detection[DB/OL].(2020-12-17) [2023-10-12].https://doi.org/10.48550/arXiv.2012.09958.
[10]HAI J,XUAN Z,YANG R,et al.R2rnet:Low-light image enhancement via real-low to real-normal network[J].Journal of Visual Communication and Image Representation,2023,90:103712.
[11]LIU X,MA W,MA X,et al.LAE-Net:a locally-adaptive embedding network for low-light image enhancement[J].Pattern Re-cognition,2023,133:109039.
[12]YU N,LI J,HUA Z,Fla-net:multi-stage modular network for low-light image enhancement[J].The Visual Computer,2023,39(4):1251-1270.
[13]REN X,YANG W,CHENG W H,et al.LR3M:Robust low-light enhancement via low-rank regularized retinex model[J].IEEE Transactions on Image Processing,2020,29:5862-5876.
[14]FAN S,LIANG W,DING D,et al.LACN:A lightweight attention-guided ConvNeXt network for low-light image enhancement[J].Engineering Applications of Artificial Intelligence,2023,117:105632.
[15]GUO C,LI C,GUO J,et al.Zero-reference deep curve estimation for low-light image enhancement[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:1780-1789.
[16]LAI X,CHEN H.Enhanced MSRCR optical frequency segmented filter algorithm for a low-light vehicle environment[J].Proceedings of the Institution of Mechanical Engineers,Part D:Journal of Automobile Engineering,2022,236(9):2070-2086.
[17]WANG W,YANG W,LIU J.Hla-face:Joint high-low adapta-tion for low light face detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2021:16195-16204.
[18]LIANG J,WANG J,QUAN Y,et al.Recurrent exposure gene-ration for low-light face detection[J].IEEE Transactions on Multimedia,2021,24:1609-1621.
[19]JIANG Y,GONG X,LIU D,et al.Enlightengan:Deep light enhancement without paired supervision[J].IEEE Transactions on Image Processing,2021,30:2340-2349.
[20]WANG J,YUAN Y,YU G,Face attention network:An effective face detector for the occluded faces[DB/OL].(2017-11-12) [2023-10-12].https://doi.org/10.48550/arXiv.1711.07246.
[21]ALEXIA J M.The relativistic discriminator:a key element mis-sing from standard gan[DB/OL].(2018-09-10) [2023-10-12].https://doi.org/10.48550/arXiv.1807.00734.
[22]MAO X D,LI Q,XIE H R,et al.Least squares generative adversarial networks[C]//ICCV.2017:2813-2821.
[23]JUSTIN J,ALEXANDREA A,LI F F.Perceptual losses forreal-time style transfer and super-resolution[C]//Computer Vision－ECCV 2016:14th European Conference,Amsterdam,The Netherlands,October 11－14,2016,Proceedings,Part II 14.Springer International Publishing,2016:694-711.
[24]RICHARD W B,ANTHONY S E,SCHEIRER W J.Psyphy:A psychophysics driven evaluation framework for visual recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,41(9):2280-2286.
[25]RONNEBERGER O,FISCHER P,BROX T.U-net:Convolu-tional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention(MICCAI 2015).18th International Conference,Munich.Germany,October 5－9,2015,Proceedings,Part III 18.Springer International Publishing,2015:234-241.
[26]YANG S,LUO P,LOY C C,et al.Wider face:A face detection benchmark[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:5525-5533.
[27]YANG W,YUAN Y,REN W,et al.Advancing image understanding in poor visibility environments:A collective benchmark study[J].IEEE Transactions on Image Processing,2020,29:5737-5752.
[28]DANG-NGUYEN D T,PASQUINI C,CONOTTER V,et al.Raise:A raw images dataset for digital image forensics[C]//Proceedings of the 6th ACM Multimedia Systems Conference.2015:219-224.
[29]DENG J K,GUO J,ZHOU Y X,et al.Retinaface:Single-stage dense face localisation in the wild[J].arXiv:1905.00641,2019.
[30]KALANTARI N K,RAMAMOORTHI R.Deep high dynamicrange imaging of dynamic scenes[J].ACM Trans. Graph.,2017,36(4):144:1-144:12.
[31]CAI J,GU S,ZHANG L,Learning a deep single image contrast enhancer from multi-exposure images[J].IEEE Transactions on Image Processing,2018,27(4):2049-2062.
[32]ZHANG Y,ZHANG J,GUO X,Kindling the darkness:A practical low-light image enhancer[C]//Proceedings of the 27th ACM International Conference on Multimedia.2019:1632-1640.
[33]GUO X,LI Y,LING H,LIME:Low-light image enhancement via illumination map estimation[J].IEEE Transactions on Image Processing,2016,26(2):982-993.
[34]WANG Z,BOVIK A C,SHEIKH H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[35]LEE C,LEE C,LEE Y Y,et al.Power-constrained contrast enhancement for emissive displays based on histogram equalization[J].IEEE Transactions on Image Processing,2011,21(1):80-93.
[36]WANG S,ZHENG J,HU H M,et al.Naturalness preserved enhancement algorithm for non-uniform illumination images[J].IEEE Transactions on Image Processing,2013,22(9):3538-3548.
[37]MITTAL A,SOUNDARARAJAN R,BOVIK A C.Making a“completely blind” image quality analyzer[J].IEEE Signal Processing Letters,2012,20(3):209-212.
[38]FU X,ZENG D,HUANG Y,et al.A fusion-based enhancing method for weakly illuminated images[J].Signal Processing,2016,129:82-96.
[39]NAJIBI M,SAMANGOUEI P,CHELLAPPA R,et al.Ssh:Single stage headless face detector[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:4875-4884.
[40]DENG J,GUO J,VERVERAS E,et al.Retinaface:Single-shot multi-level face localisation in the wild[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2020:5203-5212.
[41]TANG X,DU D K,HE Z,et al.Pyramidbox:A context-assisted single shot face detector[C]//Proceedings of the European Conference on Computer Vision(ECCV).2018:797-813.
[42]LI J,WANG Y,WANG C,et al.DSFD:dual shot face detector[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:5060-5069.
[43]WANG S,ZHENG J,HU H M,et al.Naturalness preserved enhancement algorithm for non-uniform illumination images[J].IEEE transactions on image processing,2013,22(9):3538-3548.
[44]FU X,ZENG D,HUANG Y,et al.A weighted variational model for simultaneous reflectance and illumination estimation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Eecognition.2016:2782-2790.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发