基于掩膜生成网络的遮挡人脸检测方法

doi:10.19678/j.issn.1000-3428.0059772

摘要/Abstract

摘要： 针对复杂遮挡条件下人脸检测精度低的问题，提出一种基于掩膜生成网络（MGN）的遮挡人脸检测方法。对人脸训练集进行预处理，将训练人脸划分为25个子区域，并为每个子区域分别添加遮挡。将一系列添加遮挡的人脸图像和原始人脸图像作为图像对依次输入MGN进行训练，以生成对应各个遮挡子区域的遮挡掩膜字典。通过组合相关字典项生成与检测人脸遮挡区域相对应的组合特征掩膜，并将该组合特征掩膜与检测人脸深层特征图相点乘，以屏蔽由局部遮挡引起的人脸特征元素损坏。在AR和MAFA数据集上进行实验，结果表明，该方法的检测精度高于MaskNet、RPSM等方法，且检测速度较快。

关键词: 遮挡人脸检测, 卷积神经网络, 掩膜生成网络, 遮挡掩膜, 组合特征掩膜

Abstract: To address the low accuracy of occluded face detection,an occluded face detection method based on Mask Generation Network(MGN) is proposed.The method pre-processes the dataset for face training by dividing each face image into 25 sub-regions and adding occlusions for each sub-region.Then the occluded face images and original face images are sequentially input into the MGN for training to generate an occlusion mask dictionary corresponding to each occluded sub-region.Next,related dictionary entries are combined to generate a combined feature mask corresponding to the occluded region of the to-be-detected face.The combined feature mask is multiplied with the deep feature map of the to-be-detected face to shield the facial feature element damage caused by local occlusion.The experimental results on AR and MAFA datasets show that the proposed method exhibits a higher detection accuracy than MaskNet,RPSM and other methods while keeping a high detection speed.

Key words: occluded face detection, Convolutional Neural Network(CNN), Mask Generation Network(MGN), occluded mask, combined feature mask

中图分类号:

TN911.73

连泽宇, 田景文. 基于掩膜生成网络的遮挡人脸检测方法[J]. 计算机工程, 2021, 47(11): 292-297,304.

LIAN Zeyu, TIAN Jingwen. Occluded Face Detection Method Based on Mask Generation Network[J]. Computer Engineering, 2021, 47(11): 292-297,304.

http://www.ecice06.com/CN/Y2021/V47/I11/292

图/表 6

20211113145809

20211113145811

20211113145814

20211113145817

20211113145821

20211113145824

参考文献

[1] 任婕,侯博建,姜远.多示例学习下的深度森林架构[J].计算机研究与发展,2019,56(8):1670-1676. REN J,HOU B J,JIANG Y.Deep forest for multiple instance learning[J].Journal of Computer Research and Development,2019,56(8):1670-1676.(in Chinese)
[2] SHI B,BAI X,LIU W,et al.Face alignment with deep regression[J].IEEE Transactions on Neural Networks and Learning Systems,2018,29(1):183-194.
[3] VILLAMIZAR M,SANFELIU A,MORENO-NOGUER F.Online learning and detection of faces with low human supervision[J].The Visual Computer,2019,35(3):349-370.
[4] JIANG J,MA J,CHEN C,et al.Noise robust face image super-resolution through smooth sparse representation[J].IEEE Transactions on Cybernetics,2017,47(11):3991-4002.
[5] LI H,LIN Z,SHEN X,et al.A convolutional neural network cascade for face detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:5325-5334.
[6] 魏赟,孙硕.生成对抗网络进行感知遮挡人脸还原的算法研究[J].小型微型计算机系统,2020,41(2):416-420. WEI Y,SUN S.Research on perceptual occlusion face restoration algorithms based on generative adversarial networks[J].Journal of Chinese Computer Systems,2020,41(2):416-420.(in Chinese)
[7] 李婷婷,胡玉龙,魏枫林.基于GAN改进的人脸表情识别算法及应用[J].吉林大学学报(理学版),2020,58(3):605-610. LI T T,HU Y L,WEI F L.Improved facial expression recognition algorithm based on GAN and application[J]. Journal of Jilin University(Science Edition),2020,58(3):605-610.(in Chinese)
[8] HE K,ZHANG X,REN S,et al.Deep residual learning for image recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:770-778.
[9] JIE H,LI S,GANG S.Squeeze and excitation networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:7132-7141.
[10] WANG H,GONG D,LI Z,et al.Decorrelated adversarial learning for age-invariant face recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:3527-3536.
[11] DENG J,GUO J,XUE N,et al.Arcface:additive angular margin loss for deep face recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:4690-4699.
[12] WANG Y,GONG D,ZHOU Z,et al.Orthogonal deep features decomposition for age-invariant face recognition[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2018:738-753.
[13] WANG H,WANG Y,ZHOU Z,et al.Cosface:large margin cosine loss for deep face recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:5265-5274.
[14] TANG X,DU D K,HE Z,et al.PyramidBox:a context-assisted single shot face detector[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2018:797-813.
[15] ZHANG S,WEN L,SHI H,et al.Single-shot scale-aware network for real-time face detection[J].International Journal of Computer Vision,2019,127(6/7):537-559.
[16] OH H J,LEE K M,LEE S U.Occlusion invariant face recognition using selective local non-negative matrix factorization basis images[J].Image and Vision Computing,2008,26(11):1515-1523.
[17] PARK S,LEE H,YOO J H,et al.Partially occluded facial image retrieval based on a similarity measurement[J].Mathematical Problems in Engineering,2015(1):1-11.
[18] WRIGHT J,YANG A Y,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[19] ZHAO F,FENG J,ZHAO J,et al.Robust LSTM-autoencoders for face de-occlusion in the wild[J].IEEE Transactions on Image Processing,2018,27(2):778-790.
[20] TRIGUEROS D S,MENG L,HARTNETT M.Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss[J].Image and Vision Computing,2018,79:99-108.
[21] WAN W,CHEN J.Occlusion robust face recognition based on mask learning[C]//Proceedings of IEEE International Conference on Image Processing.Washington D.C.,USA:IEEE Press,2017:3795-3799.
[22] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[23] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2012:2564-2571.
[24] BIAN J,LIN W Y,MATSUSHITA Y,et al.GMS:grid-based motion statistics for fast,ultra-robust feature correspondence[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2828-2837.
[25] YANG S,LUO P,CHEN C L,et al.WIDER FACE:a face detection benchmark[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:5525-5533.
[27] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[28] ALEIX M,BENAVENTE R.The AR face database[J].CVC Technical Report,1998,24:1-8.
[29] GE S,LI J,YE Q,et al.Detecting masked faces in the wild with LLE-CNNs[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2682-2690.

选择文件类型/文献管理软件名称

选择包含的内容