计算机科学 ›› 2016, Vol. 43 ›› Issue (5): 294-297.doi: 10.11896/j.issn.1002-137X.2016.05.056

• 图形图像与模式识别 • 上一篇    下一篇

基于曲波变换和余弦测度的人脸识别方法

李艳萍,姜颖,胡金明,李卫平   

  1. 河北工业大学廊坊分校 廊坊065000,河北工业大学廊坊分校 廊坊065000,河北工业大学廊坊分校 廊坊065000,武汉理工大学信息工程学院 武汉430070
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受河北省科学技术研究与发展计划项目(14K50123D),国家自然科学基金项目(6140060035)资助

Face Recognition Method Based on Curvelet Transform and Cosine Rules

LI Yan-ping, JIANG Ying, HU Jin-ming and LI Wei-ping   

  • Online:2018-12-01 Published:2018-12-01

摘要: 人脸识别是一种常用的生物特征识别技术,广泛应用于门禁考勤、公安司法等领域。光照、人脸表情与姿态、遮挡等采集条件的变化对 现有人脸识别方法 影响较大,限制了其应用。提出了一种基于曲波变换和余弦测度的人脸识别方法,以提高人脸识别对采集条件的鲁棒性。首先,对待识别人脸图像进行曲波变换,依据曲波系数检测人脸区域的关键点;然后,提取各关键点在不同尺度和方向上的曲波特征,构建人脸特征描述子;最后,依据余弦测度、累加和运算和极值运算求取人脸的最优匹配结果。仿真实验表明,所提方法对光照、姿态、表情和遮挡等变化的鲁棒性强,且识别性能好。

关键词: 人脸识别,曲波变换,余弦测度,尺度调整

Abstract: Face recognition is common biometric identification,widely used in access control,public security and justice,and so on.Existing face recognition methods are greatly influenced by the change of acquisition conditions on illumination,facial expression,pose and occlusion,limiting the application of face recognition technology.This paper proposed a face recognition method based on curvelet transform and cosine rules,to improve the robustness on acquisition conditions.First,we executed curvelet transform on face image,and detected key points according to curvelet coefficients.Then,we extracted curvelet features from key points with different scales and directions,and obtained a face descriptor.Finally,the optimal matching result was computed through cosine rules,cumulative and extreme operation.Experiments show that the proposed method is robust to changes of illumination,facial expression,pose and occlusion,and has good recognition performance.

Key words: Face recognition,Curvelet transform,Cosine rules,Scales adjustment

[1] Nikan S,Ahmadi M.Local gradient-based illumination invariant face recognition using local phase quantisation and multi-resolution local binary pattern fusion[J].IET Image Processing,2015,9(1):12-21
[2] Su G,Zhang C,Ding R,et al.MMP-PCA face recognition me-thod[J].Electronics Letters,2002,38(25):1654-1656
[3] Xiang X,Yang J,Chen Q.Color face recognition by PCA-like ap-proach[J].Neurocomputing,2015,152:231-235
[4] Lai J H,Yuen P C,Feng G C.Face recognition using holisticFourier invariant features[J].Pattern Recognition,2001,34(1):95-109
[5] Hsieh C C,Chen W H.A Face Recognition System Based on ASM Facial Components[J].Applied Mechanics & Materials,2011,8-60:2314-2319
[6] Pei D.Research of automatic face recognition based on ICA[J/OL].http://en.cnki.com.cn/Article_cn/CJFDTOTAL-HWYH200105009.html
[7] Z Sun X,Zhang Q,Wang Z.Face Recognition Based on NMF and SVM[C]∥International Symposium on Electronic Commerce and Security.2009:616-619
[8] Zhang Jian,He Hua,Zhan Xiao-si,et al.Pose-invariant Face Re-cognition Via SIFT Vocabulary Tree[J].Journal of Computer-Aided Design & Computer Graphics,2013,25(11):1694-1700(in Chinese) 张剑,何骅,詹小四,等.用SIFT词汇树实现的姿态无关的人脸识别[J].计算机辅助设计与图形学学报,2013,25(11):1694-1700
[9] Li Gen,Li Wen-hui.Face occlusion recognition based onMEBML[J].Journal of Jilin University(Engineering and Technology Edition),2014,44(5):1410-1416(in Chinese) 李根,李文辉.基于思维进化的机器学习的遮挡人脸识别[J].吉林大学学报(工学版),2014,44(5):1410-1416
[10] Ding Rong,Su Guang-da,Lin Xing-gang.Using Key Points to Improve Elastic Matching in Face Recognition[J].Acta Electronica Sinica,2002,30(9):1292-1294(in Chinese) 丁嵘,苏光大,林行刚.使用关键点信息改进弹性匹配人脸识别算法[J].电子学报,2002,30(9):1292-1294
[11] Donoho D L,Duncan M R,Duncan M R.Digital curvelet transform:strategy,implementation,and experiments[J].Wavelet Applications VII,2000,4056:12-29
[12] Candès E,Demanet L,Donoho D,et al.Fast Discrete Curvelet Transforms[J].Multiscale Modeling & Simulation,2010,5(3):861-899
[13] Nemati R J,Javed M Y.Fingerprint verification using filter-bank of Gabor and Log Gabor filters[C]∥International Conference on Systems,Signals and Image Processing.IEEE,2008:363-366
[14] Geng C,Jiang X.Face recognition based on the multi-scale local image structures[J].Pattern Recognition,2011,40(10-11):2565-2575
[15] Andrés A M,Padovani S.Face recognition on partially occluded images using compressed sensing[J].Pattern Recognition Letters,2014,36(1):235-242
[16] Jia Q,Fang C,Wen D,et al.Generating face images under multiple illuminations based on a single front-lighted sample without 3D models[C]∥International Conference on Biometrics,2013:1-6

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!