基于Gabor小波变换多特征向量的人脸识别鲁棒性研究

计算机科学 ›› 2014, Vol. 41 ›› Issue (2): 308-311.

基于Gabor小波变换多特征向量的人脸识别鲁棒性研究

彭辉

浙江大学计算机学院杭州310018

出版日期:2018-11-14 发布日期:2018-11-14
基金资助:
本文受浙江省高等教育课堂教学改革项目:《图形与图像处理》延伸型教学管理模式和多阶段考核方式的探索资助

Research on Gabor Wavelet Transform Feature Recognition Robustness Based on Vector of Face

PENG Hui

Online:2018-11-14 Published:2018-11-14

摘要/Abstract

摘要： 传统的Gabor小波变换人脸识别技术在曲线奇异性的表达上存在着不足,难以识别包含表情的人脸信息,针对该问题,提出了结合Gabor小波变换和多特征向量的人脸识别算法。算法首先利用Gabor小波变换的频率及方向选择性来提取出人脸的多尺度、多方向上的Gabor特征,并组成联合稀疏模型,通过计算可以得到各个方向和尺度上Gabor特征的共同特征和表情特征,利用这两个特征向量可以精确重构测试图像的特征向量。仿真实验结果表明,所提出的方法能够有效提高带表情人脸图像的正确匹配率,改善识别效果。

关键词: 人脸识别,表情识别,Gabor小波变换,多特征向量中图法分类号TP391文献标识码A

Abstract: There is insufficiency in expressing curve singularity for traditional Gabor wavelet transformation in face re-cognition technology that causes facial expression information hard to identify．This paper proposed a face recognition algorithm combining Gabor wavelet transform and multiple feature vectors．The algorithm firstly utilizes frequency and direction selectivity of Gabor wavelet transformation to extract the Gabor features of face multi-scale and direction and forms a joint sparse model in which the common features and expression characteristics of Gabor can be characterized in all directions and scales via calculation,at the same time,the test image feature vector can be accurately reconstructed using the two feature vector．Finally,the simulation results show that this method can effectively enhance the correct matching ratio of facial expression image and improve the recognition effect.

Key words: Face recognition,Facial expression recognition,Gabor wavelet transformation,Feature vector

彭辉. 基于Gabor小波变换多特征向量的人脸识别鲁棒性研究[J]. 计算机科学, 2014, 41(2): 308-311. https://doi.org/

PENG Hui. Research on Gabor Wavelet Transform Feature Recognition Robustness Based on Vector of Face[J]. Computer Science, 2014, 41(2): 308-311. https://doi.org/

参考文献

[1] Yacoob Y,Lam H,Davis L S．Recognizing faces showing expressions[A]∥International Workshop on Automatic Face-and Gesture-Recognition[C]．Zurich,1995:278-283
[2] Yu Bing,Jin Lian-fu,Chen Ping．Expression—invariant FaceRecognition Based on Eigenmotion[J]．Journal of Image and Graphics,2002,7(A):1140-1143
[3] Hu Ping,Cao Wei-guo,Li Hua．A Novel Isometric Invariant and its Applications in 3D Face Recognition[J]．Journal of Compu-ter-Aided Design & Computer Graphics,2010,22(12):2090-2094
[4] 杜杏菁.基于Candide-3模型的姿态表情人脸识别研究[J].计算机工程与设计,2012,33(3):1018-1020
[5] Peng Hui．A method based on wavelet transform and SVM of ECG human idenfication[J]．Microelectrionics&Computer,2012,3:152-155
[6] Hu D,Feng G,Zhou Z．Two-dimensional locality preserving projection with its application to palmprint recognition[J]．Pattern Recognition,2007,40(1):339-342
[7] Bartlett M S,Movellan J R,Sejnowski T J．Face recognition by independent component analysis[J]．IEEE Transactions on Neural Networks,2002,13(6):1450-1464
[8] 赵宏伟．基于PCA针对表情变化的人脸识别研究[D]．西安:西安电子科技大学,2009:37-40
[9] Shen L L,Bai L．Gabor wavelets and general discriminant analysis or face identification and verification[J]．Image and Vision Computing,2007,25(5):553-563
[10] He C,Dong J Y,Yuan F．Object tracking using the Gabor wave-let transform and the golden section algorithm[J]．IEEE Tran-sactions on Multimedia,2002,4(4):528-538
[11] Candes E J,Donoho D L．New tight frames of curvelets and optimal representations of objects with C2singularities[J]．Communications on Pure and Applied Mathematics,2004,57(2):219-266
[12] 吕翊,林贺宇,赵辉．基于sym8小波和部分hadmard矩阵的深空图像压缩编码[J].重庆邮电大学学报:自然科学版,2012,4(5):646-651

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed