[1]胡春华,马旭东,戴先中,等.一种基于标准混合高斯模型的快速人脸检测方法[J].东南大学学报(自然科学版),2007,37(3):389-394.[doi:10.3969/j.issn.1001-0505.2007.03.007]
 Hu Chunhua,Ma Xudong,Dai Xianzhong,et al.Method for fast face-detection based on normalization Gaussian mixture model[J].Journal of Southeast University (Natural Science Edition),2007,37(3):389-394.[doi:10.3969/j.issn.1001-0505.2007.03.007]
点击复制

一种基于标准混合高斯模型的快速人脸检测方法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
37
期数:
2007年第3期
页码:
389-394
栏目:
自动化
出版日期:
2007-05-20

文章信息/Info

Title:
Method for fast face-detection based on normalization Gaussian mixture model
作者:
胡春华 马旭东 戴先中 钱堃
东南大学自动化学院, 南京 210096
Author(s):
Hu Chunhua Ma Xudong Dai Xianzhong Qian Kun
School of Automation, Southeast University, Nanjing 210096, China
关键词:
人脸检测 混合高斯模型 Gabor变换 人眼特征 移动机器人
Keywords:
face detection mixture-Gaussian model Gabor transform eyes features mobile robot
分类号:
TP24
DOI:
10.3969/j.issn.1001-0505.2007.03.007
摘要:
针对室内移动机器人运动过程提出一种快速而稳定的人脸检测方法.由于室内存在多种物体,背景不断变化,且光照条件可能不断变化, 提出采用人脸肤色的标准混合高斯模型与人眼特征相结合的人脸检测法,无需对原始图像进行尺度变换.检测过程首先将经过补光处理及光线增强的人脸库转换到YCbCr空间,求其非线性变换空间YCbC’r,求出左右脸标准正态密度函数及混合高斯分布; 然后根据人眼颜色特征,分别对人脸肤色候选区域进行人眼候选区域提取,利用人眼Gabor模板的不变Hu矩与人眼候选区域的相关性,找出人眼拟合矩形区域,再综合利用人眼与人脸的特征关系以及人脸候选区域的投影关系检测出人脸区域.大量实验表明,新方法速度快,适应性较好,并可扩展检测到侧面人脸.
Abstract:
An effective and fast method of face detection for a service robot is proposed, which combines a mixture of Gaussian distribution model of skin tone color with eyes features. Candidate skin-color regions over the entire image are extracted based on normal Gaussian distributions models of left and right faces in a nonlinearly transformed YCbCr color space, following the light compensation and enhancement procedures. Eyes candidates are located in the candidate skin regions by using different contrasts in color between the eyes and face skins, and Gabor filtered Hu-moments of those are produced as statistical features for further identification of the eyes. Combining the projection histogram of skin-color regions and detected eyes features, the faces regions are accurately located. Experimental results demonstrate that the proposed method is effective and fast to detect both frontal and profile faces with robustness of lighting fluctuations and background clutters.

参考文献/References:

[1] Jain Anil K,Hsu Rein-Lien.Face detection in color image [M].Michigan:Michigan State University,2002:5-8.
[2] 艾海舟,梁路宏,徐光祐,等.基于肤色和模板的人脸检测[J].软件学报,2001,12(12):1784-1792.
  Ai Haizhou,Liang Luhong,Xu Guangyou,et al.Face detection based on skin color and template[J].Journal of Software,2001,12(12):1784-1792.(in Chinese)
[3] Taigun L,Sung-Kee P,Mignon P.An effective method for detecting facial features and face in human-robot interaction [J]. Information Sciences,2006,176(21):3166-3189.
[4] Chiang Cheng-Chin,Tai Wen-Kai,Yang Mau-Tsuen,et al.A novel method for detecting lips,eyes,and faces in real times [J].Real-Time Imaging,2003,9(4):277-287.
[5] Solina Franc,Peer Peter,Batagelj Borut,et al.Color-based face detection in the “15 seconds of fame” art installation[C] //Conference on Computer Vision/Computer Graphics Collaboration for Model-based Imaging,Rendering,Image Analysis and Graphical Special Effects.Mirage,France:Wilfried Philips,Rocquencourt,INRIA,2003:38-47.
[6] Pham The Bao,Jin Young Kim,Seung You Na.Fast multi-face detection in color images using fuzzy logic [C] //Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems.Hong Kong,2005:777-780.
[7] Karungaru Stephen,Fukumi Minoru,Akamatsu Norio.Detection of human faces in visual scenes [C] //Intelligent Information Systems Conference.Perth,Australia,2001:165-170.
[8] Liu Chengjun.A Bayesian discriminating features method for face detection [J].IEEE Trans Pattern Analysis and Machine Intelligence,2003,25(6):725-740.
[9] Eickeler S.Face database retrieval using pseudo 2D hidden Markov models [C] //Proceeding of Conference on Automatic Face and Gesture Recognition.Washington D C,USA,2002:65-70.
[10] Jin Hongliang,Liu Qingshan,Lu Hanqing,et al.Face detection using one-class SVM in color images[C] // International Conference on Signal Processing.Beijing,China,2004:1431-1434.
[11] Li Stan Z,Zhen Qiu.Floatboost learning and statistical face detection [J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2004,26(9):1-12.
[12] Huang L L,Shimizu A,Kobatake H.Classification-based face detection using Gabor filter features [C] //The 6th IEEE International Conference on Automatic Face and Gesture Recognition.Seoul,Korea,2004:397-402.
[13] 盛骤,谢式千,潘承毅.概率论与数理统计[M].北京:高等教育出版社,1996:170-173.

相似文献/References:

[1]王原,汤勇明,王保平.基于混合高斯模型的非固定握持姿势手势识别[J].东南大学学报(自然科学版),2014,44(2):239.[doi:10.3969/j.issn.1001-0505.2014.02.003]
 Wang Yuan,Tang Yongming,Wang Baoping.Gesture recognition with unfixed holding position based on Gaussian mixture model[J].Journal of Southeast University (Natural Science Edition),2014,44(3):239.[doi:10.3969/j.issn.1001-0505.2014.02.003]

备注/Memo

备注/Memo:
基金项目: 国家重点基础研究发展计划(973计划)资助项目(2002CB312200)、国家高技术研究发展计划(863计划)资助项目(2004AA420110).
作者简介: 胡春华(1977—),女,博士生; 马旭东(联系人),男,教授,xdma@seu.edu.cn.
更新日期/Last Update: 2007-05-20