基于Mask R-CNN的人脸检测与分割方法

doi:10.19678/j.issn.1000-3428.0054566

摘要/Abstract

摘要： 针对现有主流的人脸检测算法不具备像素级分割，从而存在人脸特征具有噪声及检测精度不理想的问题，提出了一种基于Mask R-CNN的人脸检测及分割方法。通过ResNet-101结合RPN网络生成候选区域，再利用RoIAlign算法实现像素级的特征点定位，旨在提高定位精度。根据全卷积网络生成相应的人脸二值掩码，实现图像中人脸信息与背景的分割。此外，构建了一个具有分割标注信息的人脸数据集用于训练相应模型。在通用人脸检测数据集的实验结果表明，该方法具有较好的人脸检测效果，并能在准确检测的同时实现像素级的人脸信息分割。

关键词: 人脸检测, Mask R-CNN算法, 实例分割, RoIAlign 算法, 全卷积网络

Abstract: Face detection is an important research direction in computer vision and information security,which has been widely studied over the past few decades.In the traditional face detection method,there is no pixel-level segmentation process,which leads to the problem of face features with noise and unsatisfactory detection accuracy.In order to overcome this shortcoming,a face detection and segmentation method based on Mask R-CNN is proposed in this paper.In this method,ResNet-101 and RPN is used to generate RoIs,and RoIAlign faithfully retains the exact spatial locations to generate binary mask through Fully Convolution Network.In order to train the model,this paper constructs a face dataset with segmentation annotation information.The experimental results of well-known face detection dataset show that the proposed method has better face detection effect and can achieve pixel-level face information segmentation at the same time.

Key words: face detection, Mask R-CNN algorithm, instance segmentation, RoIAlign algorithm, Full Convolutional Network(FCN)

中图分类号:

TP391

林凯瀚, 赵慧民, 吕巨建, 詹瑾, 刘晓勇, 陈荣军. 基于Mask R-CNN的人脸检测与分割方法[J]. 计算机工程, 2020, 46(6): 274-280.

LIN Kaihan, ZHAO Huimin, Lü Jujian, ZHAN Jin, LIU Xiaoyong, CHEN Rongjun. Face Detection and Segmentation Method Based on Mask R-CNN[J]. Computer Engineering, 2020, 46(6): 274-280.

http://www.ecice06.com/CN/Y2020/V46/I6/274

图/表 9

20200617091548

20200617091552

20200617091555

20200617091558

20200617091601

20200617091604

20200617091607

20200617091611

20200617091614

参考文献

[1] VIOLA P,JONES M J.Robust real-time face detection[J].International Journal of Computer Vision,2004,57(2):137-154.
[2] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:886-893.
[3] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[4] BAY H,ESS A,TUYTELAARS T,et al.Speeded-up rbust features[J].Computer Vision and Image Understaning,2008,110(3):346-359.
[5] AHONEN T,HADID A,PIETIRAINEN M.Face description with local binary patterns:application to face recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(12):2037-2041.
[6] FELZENSZWALB P F,GIRSHICK R B,MCAllESTER D,et al.Oject detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Mchine Intelligence,2010,32(9):1627-1645.
[7] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Proceedings of IEEE NIPS'12.Washington D.C.,USA:IEEE Press,2012:1097-1105.
[8] ZHAN Shu,TAO Qinqin,LI Xiaohong.Face detection using representation learning[J].Neurocomputing,2016,187:19-26.
[9] RANJAN R,PATEL V M,CHELLAPPA R.A deep pyramid deformable part model for face detection[C]//Proceedings of the 7th IEEE International Conference on Biometrics Theory,Applications and Systems.Washington D.C.,USA:IEEE Press,2015:1-8.
[10] JIANG H,LEARNED-MILLER E.Face detection with the faster R-CNN[C]//Proceedings of the 12th IEEE International Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,2017:650-657.
[11] WU Wenqi,YIN Yingjie,WANG Xingang,et al.Face detection with different scales based on faster R-CNN[J].IEEE Transactions on Cybernetics,2018,49(11):4017-4028.
[12] SUN X,WU P,HOI S C H.Face detection using deep learning:an improved faster rcnn approach[J].Neurocomputing,2018,299:42-50.
[13] GUO Xiaobo,ZHOU Zhaoyong,LI Songyang.Nasal tip detection and posture correction of 3D face based on effective energy[J].Computer Engineering,2018,44(9):236-242.(in Chinese)郭小波,周兆永,李松阳.基于有效能量的3D人脸鼻尖点检测与姿态矫正[J].计算机工程,2018,44(9):236-242.
[14] ZOU Guofeng,FU Guxia,GAO Mingliang,et al.Pose varied face recognition based on self learning deep convolutional neural network[J].Journal of Chinese Computer Systems,2018,39(6):1156-1162.(in Chinese)邹国锋,傅桂霞,高明亮,等.基于自学习深度卷积神经网络的姿态变化人脸识别[J].小型微型计算机系统,2018,39(6):1156-1162.
[15] QIU Yiming,LIAO Haibin,CHEN Qinghu.Occluded face pose recognition based on dictionary learning with discrimination performance[J].Geomatics and Information Science of Wuhan University,2018,43(2):275-281,288.(in Chinese)邱益鸣,廖海斌,陈庆虎.基于鉴别字典学习的遮挡人脸姿态识别[J].武汉大学学报(信息科学版),2018,43(2):275-281,288.
[16] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2961-2969.
[17] JAIN V,LEARNED-MILLER E.Fddb:a benchmark for face detection in unconstrained settings[EB/OL].[2019-03-04].https://www.researchgate.net/publication/.
[18] WONG Y,CHEN S,MAU S,et al.Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2011:74-81.
[19] HE Kaiming,ZHANG Xiangyu,REN Shaoqing,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.
[20] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:580-587.
[21] GIRSHICK R.Fast R-CNN[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:1440-1448.
[22] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[C]//Proceedings of IEEE NIPS'15.Washington D.C.,USA:IEEE Press,2015:91-99.
[23] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Oomputer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[24] LIN T Y,MAIRE M,BELONGUE S,et al.Microsoft coco:common objects in context[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2014:740-755.
[25] MARKUS N,FRLJAK M,PANDZIC I S,et al.A method for object detection based on pixel intensity comparisons organized in decision trees[EB/OL].[2019-03-10].https://www.researchgate.net/publication/.
[26] JENSEN O H.Implementing the Viola-Jones face detection algorithm[D].Lyngby,Denmark:Technical University of Denmark,2008.
[27] KOESTINGER M,WOHLHART P,ROTH P M,et al.Robust face detection by simple means[C]//Proceedings of IEEE DAGM'12.Washington D.C.,USA:IEEE Press,2012:125-137.
[28] RAMANAN D,ZHU X.Face detection,pose estimation,and landmark localization in the wild[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:2879-2886.
[29] MATHIAS M,BENENSON R,PEDERSOLI M,et al.Face detection without bells and whistles[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2014:720-735.
[30] FINK M,FERGUS R,ANGELOVA A.Caltech 10000 Web faces[EB/OL].[2019-03-10].http://www.vision.caltech.edu/Image_Datasets/Caltech_10K_WebFaces.
[31] YANG S,LUO P,LOY C C,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.

选择文件类型/文献管理软件名称

选择包含的内容