[1]洪 杨,于凤芹.基于改进的快速鲁棒特征算法的人脸检测研究[J].南京理工大学学报(自然科学版),2017,41(06):714.[doi:1005-9830(2017)06-0714-06]
 Hong Yang,Yu Fengqin.Face detection based on improved speeded uprobust features algorithm[J].Journal of Nanjing University of Science and Technology,2017,41(06):714.[doi:1005-9830(2017)06-0714-06]
点击复制

基于改进的快速鲁棒特征算法的人脸检测研究()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年06期
页码:
714
栏目:
出版日期:
2017-12-31

文章信息/Info

Title:
Face detection based on improved speeded uprobust features algorithm
文章编号:
10.14177/j.cnki.32-1397n.2017.41.06.008
作者:
洪 杨于凤芹
江南大学 物联网工程学院,江苏 无锡 214122
Author(s):
Hong YangYu Fengqin
School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China
关键词:
快速鲁棒特征 人脸检测 图像熵 非极大值抑制 哈尔小波响应 费舍尔矢量核
Keywords:
speeded up robust features face detection image entropy non-maximum suppression Haar wavelet response Fisher vector kernel
分类号:
TP391
DOI:
1005-9830(2017)06-0714-06
摘要:
针对快速鲁棒特征(SURF)算法冗余信息多且计算速度慢的缺点,该文对SURF算法进行改进,用于人脸检测。计算特征点邻域的图像熵,并使用非极大值抑制提取图像熵高的特征点,通过减少区域描述减少冗余信息。使用扇形窗口遍历各特征点邻域,通过计算窗口内哈尔小波响应构建该点的特征描述子,从而加快计算速度。使用费舍尔矢量核将各特征描述子映射到高维空间进行人脸检测。仿真实验表明,在应用于人脸检测数据集和基准(FDDB)数据集时,与SURF算法相比,该文算法检测率提高了7.9%,特征计算时间减少了53.1%,特征点数减少了59.7%。
Abstract:
An improved speeded up robust features(SURF)algorithm is used in face detection aming at the shortcomings of many redundant information and low computing speed of the SURF algorithm.The image entropy of neighborhood of each feature point is calculated,and the feature points with high image entropy are selected by non-maximum suppression to decrease description area and redundant information.A fan window is used to traverse the neighborhood of each feature point,and Haar wavelet response in the fan window is calculated to form the descriptor of each feature point,and the computing speed is faster.Each descriptor is mapped into a high dimensional space by Fisher vector kernel for face detection.The simulation results in face detection data set and benchmark(FDDB)show that,compared with that of SURF algorithm,the detection rate of the improved SURF algorithm increases by 7.9%,the feature calculation time decreases by 53.1%,and the feature points decreases by 59.7%.

参考文献/References:

[1] 郭志波,严云洋,杨静宇,等.基于沃尔什特征和增强型Cascade算法的人脸检测[J].南京理工大学学报,2008,32(1):60-64.
Guo Zhibo,Yan Yunyang,Yang Jingyu,et al.Fast face detection based on Walsh feature and enhanced cascade algorithm[J].Journal of Nanjing University of Science and Technology,2008,32(1):60-64.
[2]朱文佳,戚飞虎.快速人脸检测与特征定位[J].中国图象图形学报,2006,10(11):1454-1457.
Zhu Wenjia,Qi Feihu.Fast face detection and facial features localization[J].Journal of Image and Graphics,2006,10(11):1454-1457.
[3]Baumann F,Ehlers A,Vogt K,et al.Cascaded random forest for fast object detection[M].Heidelberg,Berlin,Germany:Springer,2013.
[4]范燕,於东军,宋晓宁,等.镜像基函数下过渡投影子空间人脸特征抽取算法[J].南京理工大学学报,2012,36(6):915-918.
Fan Yan,Yu Dongjun,Song Xiaoning,et al.Face feature extraction approach of projective transition sub-space based on basic function of mirror symmetry[J].Journal of Nanjing University of Science and Technology,2012,36(6):915-918.
[5]王小玉,张亚洲,陈德运.基于多块局部二值模式特征和人眼定位的人脸检测[J].仪器仪表学报,2014,35(12):2739-2745.
Wang Xiaoyu,Zhang Yazhou,Chen Deyun.Face detection based on MB-LBP and eye tracking[J].Chinese Journal of Scientific Instrument,2014,35(12):2739-2745.
[6]Liao Shengcai,Jain A K,Li S Z.A fast and accurate unconstrained face detector[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):211-223.
[7]Ramanan D,Zhu Xiangxin.Face detection,pose estimation and landmark localization in the wild[C]//Computer Vision and Pattern Recognition.Providence,RI,USA:IEEE,2012:2879-2886.
[8]Nilsson M,Nordberg J,Claesson I.Face detection using local SMQT features and split up snow classifier[C]//Acoustics,Speech and Signal Processing.Honolulu,HI,USA:IEEE,2007:II-589-592.
[9]Bay H,Ess A,Tuytelaars T,et al.Speeded-up robust features(SURF)[J].Computer Vision and Image Understanding,2008,110(3):346-359.
[10]Kim D,Dahyot R.Face components detection using SURF descriptors and SVMs[C]//Machine Vision and Image Processing Conference.Portrush,Ireland,UK:IEEE,2008:51-56.
[11]李红波,赵永耀,吴渝,等.一种基于距离约束的改进SURF算法[J].系统仿真学报,2014,26(12):2944-2949.
Li Hongbo,Zhao Yongyao,Wu Yu,et al.Improved SURF algorithm based on distance constraint[J].Journal of System Simulation,2014,26(12):2944-2949.
[12]Li Jianguo,Wang Tao,Zhang Yimin.Face detection using surf cascade[C]//Computer Vision Workshops(ICCV Workshops).Barcelona,Spain:IEEE,2011:2183-2190.
[13]Fergus R,Perona P,Zisserman A.Weakly supervised scale-invariant learning of models for visual recognition[J].International Journal of Computer Vision,2007,71(3):273-303.
[14]Leibe B,Leonardis A,Schiele B.Robust object detection with interleaved categorization and segmentation[J].International Journal of Computer Vision,2008,77(1-3):259-289.
[15]Sánchez J,Perronnin F,Mensink T,et al.Image classification with the Fisher vector:Theory and practice[J].International Journal of Computer Vision,2013,105(3):222-245.
[16]Jain V,Learned-Miller E.FDDB:A benchmark for face detection in unconstrained settings[EB/OL].http://vis-www.cs.umass.edu/fddb/index.html#download,2017-10-18.

相似文献/References:

[1]王玉亮,廖文和,沈建新,等.基于快速鲁棒特征的眼底图像自动配准与拼接[J].南京理工大学学报(自然科学版),2012,36(01):79.
 WANG Yu-liang,LIAO Wen-he,SHEN Jian-xin.Automatic Fundus Images Registration and Mosaic Based on Speeded up Robust Features[J].Journal of Nanjing University of Science and Technology,2012,36(06):79.
[2]郭志波,严云洋,杨静宇,等.基于沃尔什特征和增强型Cascade算法的人脸检测[J].南京理工大学学报(自然科学版),2008,(01):60.
 GUO Zhi-bo,YAN Yun-yang,YANG Jing-yu.Fast Face Detection Based on Walsh Feature and Enhanced Cascade Algorithm[J].Journal of Nanjing University of Science and Technology,2008,(06):60.

备注/Memo

备注/Memo:
收稿日期:2016-09-28 修回日期:2017-02-20
作者简介:洪杨(1992-),男,硕士生,主要研究方向:图像信号与信息处理,E-mail:15961709701@163.com; 通讯作者:于凤芹(1962-),女,博士,教授,主要研究方向:语音信号分析与处理、图像信号与信息处理等,E-mail:986094253@qq.com。
引文格式:洪杨,于凤芹.基于改进的快速鲁棒特征算法的人脸检测研究[J].南京理工大学学报,2017,41(6):714-719.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-12-31