基于Edge Boxes和深度学习的非限制条件下人脸检测Face detection based on Edge Boxes and deep learning under unconstrained condition
刘英剑,张起贵
摘要(Abstract)：
针对光线、旋转、遮挡、平移等因素对人脸检测结果产生的干扰,提出一种基于Edge Boxes和深度学习相结合的人脸检测算法。首先采用Edge Boxes算法提取出可能存在人脸的边界框,提取边界框中的图像并调整至合适的大小,作为卷积神经网络的输入,然后利用卷积神经网络对提取出的图像进行特征提取和分类,最后利用非极大抑制算法排除多余人脸检测框,得到人脸的准确位置。该算法应用于LFW和Yale B人脸数据库的检测率分别达到98.7%和98.5%,识别单张人脸的时间均小于0.5 s。实验结果表明,该算法在检测率和检测速率方面较传统算法都有了很大的提高,对于遮挡、光照、旋转等干扰具有更强的鲁棒性。
关键词(KeyWords)： 人脸检测;特征提取;深度学习;Edge Boxes;卷积神经网络;非极大抑制算法
基金项目(Foundation): 山西省基础研究项目自然科学基金(2013011017-3)~~
作者(Author): 刘英剑,张起贵
DOI: 10.16652/j.issn.1004-373x.2018.13.007
参考文献(References)：
- [1]GUNASEKAR S,GHOSH J,BOVIK A C.Face detection on distorted images augmented by perceptual quality-aware features[J].IEEE transactions on information forensics&security,2014,9(12):2119-2131.
- [2]WOLF L,HASSNER T,TAIGMAN Y.Effective unconstrained face recognition by combining multiple descriptors and learned background statistics[J].IEEE transactions on pattern analysis&machine intelligence,2011,33(10):1978-1990.
- [3]WANG X,HAN T X,YAN S.An HOG-LBP human detector with partial occlusion handling[C]//Proceedings of 2009 IEEE International Conference on Computer Vision.Kyoto:IEEE,2009:32-39.
- [4]MOON H,PHILLIPS P J.Computational and performance aspects of PCA-based face-recognition algorithms[J].Perception,2001,30(3):303-321.
- [5]HARIPRASAD E N,JAYASREE M.Face detection using SURF descriptor and SVM[J].International journal of computer applications,2015,129(4):41-46.
- [6]GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifier neural networks[J].Journal of machine learning research,2012,15:315-323.
- [7]SYAFEEZA A R,KHALIL-HANI M,LIEW S S,et al.Convolutional neural network for face recognition with pose and illumination variation[J].International journal of engineering&technology,2014,6(1):498-519.
- [8]ZENG R,WU J,SHAO Z,et al.Quaternion softmax classifier[J].Electronics letters,2014,50(25):1929-1931.
- [9]SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al.Dropout:a simple way to prevent neural networks from overfitting[J].Journal of machine learning research,2014,15(1):1929-1958.
- [10]ROTHE R,GUILLAUMIN M,GOOL L V.Non-maximum suppression for object detection by passing messages between windows[C]//2015 Asian Conference on Computer Vision.[S.l.]:IEEE,2015:290-306.
- [11]LI Lijuan.Face detection algorithm based on general sample Adaboost[J].Microcomputer information,2010,35(1):187-191.
- [12]JAIN V,LEARNED-MILLER E.FDDB:a benchmark for face detection in unconstrained settings[R/OL].[2010-12-07].https://people.cs.umass.edu/~elm/papers/fddb.pdf.