改进的双目立体视觉正面脸合成

doi:10.3969/j.issn.0255-8297.2014.01.012

应用科学学报 ›› 2014, Vol. 32 ›› Issue (1): 74-78.doi: 10.3969/j.issn.0255-8297.2014.01.012

改进的双目立体视觉正面脸合成

王晶1,2，苏光大1

1. 清华大学电子工程系，北京100084
2. 国家计算机网络应急技术处理协调中心，北京100029

收稿日期:2012-09-14 修回日期:2013-03-31 出版日期:2014-01-31 发布日期:2013-03-31
作者简介:王晶，博士生，研究方向：人脸识别、双目立体视觉，E-mail: wangjing8641@126.com；苏光大，教授，研究方向：人脸识别、图像处理，E-mail: susu@tsinghua.edu.cn
基金资助:
国家“十一·五”科技支撑计划基金（No.2006BAK08B07）资助

Frontal Face Synthesis Based on Improved Binocular Stereo Vision

WANG Jing1,2, SU Guang-da1

1. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
2. The National Computer Network Emergency Response Technical Team Coordination Center of China, Beijing 100029, China

Received:2012-09-14 Revised:2013-03-31 Online:2014-01-31 Published:2013-03-31

摘要/Abstract

摘要： 为了解决人脸在不同姿态下难以识别的问题，提出了一种基于改进的双目立体视觉的正面人脸合成算法. 针对人脸图像纹理平滑性对特征匹配带来的困难，设计了一套新的匹配算法，获得了更准确的人脸视差图. 根据视差图求出人脸的三维坐标，参照人眼特征点定位结果求出人脸偏转角度，并将人脸合成为正面图像. 实验结果表明，该方法比其他方法具有更高的真实性和准确性，同时具有较快的处理速度.

关键词: 双目立体视觉, 人脸识别, 区域增长法, 视差图

Abstract: To improve the face recognition performance under different poses, we propose an improved frontal face synthesis method based on binocular stereo vision, which can effectively and quickly synthesize a frontal face. A modified matching algorithm is designed to deal with smoothness of faces. Then 3-D coordinates are generated according to the disparity image, and the pose angle of the face calculated according to the location of eyes. A frontal face is generated according to the pose angle using the method of binocular stereo vision.Experimental results show that the method is precise, practical, and fast.

Key words: binocular stereo vision, face recognition, region growing, disparity map

中图分类号:

TP391

王晶1,2，苏光大1. 改进的双目立体视觉正面脸合成[J]. 应用科学学报, 2014, 32(1): 74-78.

WANG Jing1,2, SU Guang-da1. Frontal Face Synthesis Based on Improved Binocular Stereo Vision[J]. Journal of Applied Sciences, 2014, 32(1): 74-78.

参考文献

[1] TURK M, PENTLAND A. Eigenfaces for recognition [J]. Journal of Cognitive Neuroscience, 1991, 3(1): 71-86.

[2] YANG J, ZHANG D. Two-dimensional PCA: a new approach to appearance-based face representation and recognition [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 2004, 26(1): 131-137.

[3] BELHUMEUR P N, HESPANHA J P, KRIEGMAN D J. Eigenfaces vs. fisherfaces: recognition using class specific linear projection [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 1997, 19(7): 711-720.

[4] BARTLETT M S, MOVELLAN J R, SEJNOWSKI T J. Face recognition by independent component analysis [J]. IEEE Transactions Neural Networks, 2002, 13(6): 1450-1464.

[5] TAKACS B. Comparing face images using the modified Hausdorff distance [J]. Pattern Recognition, 1998, 31(12): 1873-1881.

[6] WISKOTT L, FELLOUS J M, KRUGER N, Von Der M C. Face recognition by elastic bunch graph matching [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 1997, 19(7): 775-779.

[7] DENIZ O, CASTRILLON M, HERNANDEZ M. Face recognition using independent component analysis and support vector machines [J]. Pattern Recognition Letters, 2003, 24(13): 2153-2157.

[8] TSALAKANIDOU F, TZOVARAS D, STRINTZIS M G. Use of depth and color eigenfaces for face recognition [J]. Pattern recognition Letter, 2003, 24(9/10): 1427-1435.

[9] 王跃明，潘纲，吴朝晖. 三维人脸识别研究综述 [J]. 计算机辅助设计与图形学报，2008, 20(7): 819-829.

WANG Yueming, PAN Gang, WU Zhaohui. A survey of 3D face recognition [J]. Journal of Computer-Aided Design & Computer Graphics, 2009, 20(7): 819-829. （in Chinese）

[10] BUSTARD J, NIXON M. 3D morphable model construction for robust ear and face recognition [C]. Computer Vision and Pattern Recognition, 2010: 2582-2589.

[11] ZHAO W, CHELLAPPA R. Robust face recognition using symmetric shape-from-shading [R]. Center for Automation Research, 1999.

[12] WU J, SMITH W, HANCOCK E. Facial gender classification using shape-from-shading [J]. Image and Vision Computing, 2010, 28(6): 1039-1048.

[13] JACEK K, PRZEMYSLAW R. Pose invariant face recognition method using stereo vision [J]. Computer Recognition Systems 4, 2011: 13-22.

[14] HIRSCHMULLER H. Stereo processing by semiglobal matching and mutual information [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 2008, 30(2): 328-341.

[15] GEIGER A, ROSER M, URTASUN R. Efficient large-scale stereo matching [C]// Asian Conference on Computer Vision, 2011: 25-38.

[16] 邓亚峰，苏光大，傅博。一种基于AdaBoost的快速动态人脸检测算法 [J]. 计算机工程，2006, 32(11): 222-224.

DENG Yafeng, Guagnda SU, FU Bo. An algorithm of fast face detection in video based on Adaboost [J]. Computer Engineering, 2006, 32(11): 222-224. （in Chinese）

[17] 顾华，苏光大，杜成. 人脸关键特征点的自动定位 [J]. 光电子激光，2004, 15(8): 975-979.

GU Hua, SU Guangda, DU Cheng. Automatic localization of the vital feature points on human faces [J]. Journal of Optoelectronics Laser, 2004, 15(8): 975-979. （in Chinese）

[18] HIRSCHMULLER H. Stereo processing by semiglobal matching and mutual information [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 2008, 30(2): 328-341.

[19] DING J J. Time-frequency analysis and wavelet transform [D]. Taipei: National Taiwan University, 2007.

改进的双目立体视觉正面脸合成

Frontal Face Synthesis Based on Improved Binocular Stereo Vision

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	吕婧淑, 操晓春, 杨培. 基于区块链和人脸识别的双因子身份认证模型[J]. 应用科学学报, 2019, 37(2): 164-178.
[2]	熊邦书, 罗院华, 黄建萍, 李新民. 基于立体视觉的直升机桨叶扭转角模拟测量方法[J]. 应用科学学报, 2018, 36(6): 950-957.
[3]	孟一飞1，袁雪1，魏学业1，秦飞舟2，覃庆努1. 基于样本扩展和线性子空间特征提取的单样本人脸识别[J]. 应用科学学报, 2013, 31(5): 488-494.
[4]	张二虎，牟永强，陈万军. 边缘保持滤波与视觉最优准则的人脸图像光照归一化[J]. 应用科学学报, 2013, 31(5): 519-525.
[5]	郎利影，夏飞佳. 人脸识别中的零范数稀疏编码[J]. 应用科学学报, 2012, 30(3): 281-286.
[6]	胡晓俞王新姚菁. 利用二元结构特征的人脸识别[J]. 应用科学学报, 2010, 28(3): 271-276.
[7]	冀贞海, 邹采荣, 赵力. 一种改进的对齐算法及其在面部特征定位中的应用[J]. 应用科学学报, 2006, 24(6): 555-559.
[8]	贺云辉, 赵力, 邹采荣. 核最近特征分类器及人脸识别应用[J]. 应用科学学报, 2006, 24(3): 227-231.
[9]	贺云辉, 赵力, 邹采荣. 基于KPCA及最佳鉴别独立分量的人脸识别方法[J]. 应用科学学报, 2005, 23(6): 551-556.
[10]	陈蕾, 张道强, 周鹏, 陈松灿. 基于SWA的核自联想记忆模型及其人脸识别应用[J]. 应用科学学报, 2005, 23(5): 497-501.
[11]	贺云辉, 赵力, 邹采荣. 基于奇异值分解的分类器及在人脸识别中的应用[J]. 应用科学学报, 2005, 23(4): 345-349.
[12]	孙大瑞, 吴乐南. 基于特征的弹性图匹配人脸识别算法[J]. 应用科学学报, 2002, 20(4): 377-381.