一种基于同态滤波器与Radon变换的光照不变人脸识别方法

J4 ›› 2015, Vol. 37 ›› Issue (12): 2393-2398.

一种基于同态滤波器与Radon变换的光照不变人脸识别方法

齐永锋1，火元莲2

(1.西北师范大学计算机科学与工程学院，甘肃兰州 730070;
2.西北师范大学物理与电子工程学院，甘肃兰州 730070)

收稿日期:2014-10-28 修回日期:2015-05-06 出版日期:2015-12-25 发布日期:2015-12-25
基金资助:
国家自然科学基金资助项目（61262056）

An illumination invariant face recognition method based
on homomorphic filters and Radon transform

QI Yongfeng1,HUO Yuanlian2

(1.College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070；2.College of Physics and Electronic Engineering,Northwest Normal University,Lanzhou 730070,China)

Received:2014-10-28 Revised:2015-05-06 Online:2015-12-25 Published:2015-12-25

摘要/Abstract

摘要：

为了减轻光照变化对人脸识别精度的影响，提出了一种结合同态滤波器与Radon变换的人脸识别方法。首先用高斯同态滤波器对人脸图像进行处理，然后进行Radon变换，将变换得到的Radon特征用2DPCA/2DLDA进行降维。在Yale和PIE人脸数据库上的实验结果表明，提出的方法在光照变化较大时，其识别精度远高于2DPCA和2DLDA，是一种高精度的人脸识别算法。

关键词: 同态滤波器, Radon变换, 人脸识别

Abstract:

In order to reduce the effect of illumination changes on face recognition accuracy, we propose a face recognition method combining homomorphic filters with Radon transform. Firstly, we filter face images by homomorphic filters, then Radon transform is implemented and the feature dimension is reduced with 2DPCA/2DLDA.Experiment results on Yale and PIE face databases show that the recognition accuracy of the proposed method is better than the 2DPCA and 2DLDA methods under large illumination changes.Key words:

Key words: homomorphic filter;Radon transform;face recognition

齐永锋1，火元莲2. 一种基于同态滤波器与Radon变换的光照不变人脸识别方法[J]. J4, 2015, 37(12): 2393-2398.

QI Yongfeng1,HUO Yuanlian2. An illumination invariant face recognition method based
on homomorphic filters and Radon transform [J]. J4, 2015, 37(12): 2393-2398.

参考文献

［1］Yan Y,Wang Hi,Suter D,et al.Multisubregion based correlation filter bank for robust face recognition［J］.Pattern Recognition，2014，47(11):34873451.
［2］Dong Changjian,Chen Xiuhong，Chen Dayao,et al.Supervised orthogonal locality preserving projection and its application in face recognition［J］.Computer Engineering & Science，2014，36(8):15761580.(in Chinese)
［3］Deng W, Hu J, Zhou X, et al. Equidistant prototypes embedding for single sample based face recognition with generic learning and incremental learning［J］.Pattern Recognition,2014，47(12):37383749.
［4］Ou W,You X,Tao D,et al.Robust face recognition via occlusion dictionary learning［J］.Pattern Recognition，2014，47(4):15591572.
［5］Hang S .An advanced motion detection algorithm with videoquality analysis for video surveillance systems［J］.IEEE Transactions on Circuits and Systems for Video Technology,2011，21(1):114.
［6］Luan X,Fang B,Liu L,et al.Extracting sparse error of robust PCA for face recognition in the presence of varying illumination and occlusion［J］.Pattern Recognition，2014，47(2):495508.
［7］Han H,Shan S G,Chen X L,et al.A comparative study on illumination preprocessing in face recognition［J］.Pattern Recognition,2013,46(6):16911699.
［8］Cheng Xuefeng,Li Shun,Long Fei,et al.Illumination invariant face recognition based on Loggabor filtering and LBP descriptor［J］.Journal of Xiamen University(Nature Science),2014，53(3)：359363.(in Chinese)
［9］Yang W,Guo W,Peng K,et al.Research on removing shadow in workpiece image based on homomorphic filtering［J］.Procedia Engineering,2012,29:23602364.
［10］Magli E, Olmo G, Presti L, et al. Pattern recognition by means of the Radon transform and the continuous wavelet transform［J］.Signal Process,1999，73(3):277289.
［11］Ashok R,Noushath S. Subspace methods for face recognition ［J］.Computer Science Review，2010,4(1):117.
［12］Khouzani K,Zadeh H.Rotationinvariant multiresolution texture analysis using Radon and wavelet transform［J］.IEEE Transactions on Image Process,2005，14(6):783795.
［13］Jadhava D,Rotation H R.illumination invariant polynomial kernel Fisher discriminant analysis［J］.Pattern Recognition Letters，2010，31(9):10021009.
［14］Nacereddine N，Tabbonec S，Zioud D，et al.Similarity transformation parameters recovery based on Radon transform.Application in image registration and object recognition［J］.Pattern Recognition，2015，48(7):22272240.
［15］Hasegawa M,Tabbone S.Amplitudeonly log Radon transform for geometric invariant shape descriptor［J］.Pattern Recognition，2014，47(2):643658.
［16］Jadhav D,Holambe R.Feature extraction using Radon and discrete cosine transforms based features for face recognition［J］.Neurocomputing，2009，72(79):19511959.
［17］Li M,Yuan B. 2DLDA:A statistical linear discriminant analysis for image matrix［J］.Pattern Recognition Letters,2005，26(5):527532.
［18］Yang J,Zhang D,Frangi A,et al.Twodimensional PCA:A new approach to appearancebased face representation and recognition［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004，26(1):131137.
［19］Sim T,Baker S,Bsat M，et al.The CMU Pose,Illumination,and Expression(PIE) database of human faces［R］.Tech Report CMURITR0102.Pittsburgh,PA:Robotics Institute,Carnegie Mellon University,2001.
附中文参考文献：
［2］董昌剑，陈秀宏，陈达遥.有监督正交局部保留投影及其在人脸识别中的应用［J］.计算机工程与科学,2014,36(8):15761580.
［8］程雪峰，李顺，龙飞,等.基于LogGabor滤波和LBP算子的光照不变人脸识别方法［J］.厦门大学学报(自然科学版)，2014，53(3)：359363.

[1]	严春满, 张昱瑶, 张迪. 改进标签一致KSVD字典学习的人脸识别算法[J]. 计算机工程与科学, 2022, 44(02): 291-297.
[2]	孙雨浩, 陶洋, 胡昊. 基于判别低秩矩阵恢复和协同表示的遮挡人脸识别[J]. 计算机工程与科学, 2020, 42(12): 2199-2207.
[3]	钟国韵,王檬檬,汪宇玲,常艳荣,吴忠粱. 旋转均值跳动特征及其在模糊人脸识别中的应用[J]. 计算机工程与科学, 2020, 42(03): 474-482.
[4]	冯璋，裴东,王维. 基于改进灰狼算法优化支持向量机的人脸识别[J]. 计算机工程与科学, 2019, 41(06): 1057-1063.
[5]	李燕,章玥. 基于随机投影与加权稀疏表示残差的光照鲁棒人脸识别方法[J]. 计算机工程与科学, 2018, 40(11): 2015-2022.
[6]	纪明君，刘漫丹，才乐千. 基于半监督LDA特征子空间优化的人脸识别算法[J]. 计算机工程与科学, 2018, 40(10): 1851-1857.
[7]	张建明1,2，廖婷婷1,2，吴宏林1,2，刘宇凯1,2. 基于改进分数阶SVD的块协作表示的小样本人脸识别算法[J]. 计算机工程与科学, 2018, 40(07): 1237-1243.
[8]	杜弘彦，王士同，李滔. 基于非线性距离和夹角组合的最近特征空间嵌入方法[J]. 计算机工程与科学, 2018, 40(05): 888-897.
[9]	刘冀伟1，史尹嘉1，白羽1，严朝雯2. 一种脑电信息监督人脸图像的注意力分析方法[J]. 计算机工程与科学, 2018, 40(02): 298-303.
[10]	刘欢，苏士美. 基于EHMM-SVM的人脸识别算法研究[J]. 计算机工程与科学, 2017, 39(05): 925-930.
[11]	崔鹏，张雪婷. 一种基于块共同特征值的人脸识别方法[J]. 计算机工程与科学, 2017, 39(04): 777-784.
[12]	丁铭，贾维敏. 基于L1范数的分块二维局部保持投影算法[J]. 计算机工程与科学, 2017, 39(03): 519-523.
[13]	傅俊鹏，陈秀宏，葛骁倩. L2,1范数正则化的不相关判别分析及其在人脸识别中的应用[J]. 计算机工程与科学, 2017, 39(02): 343-350.
[14]	杨方方1，吴锡生1，顾标准2. 基于低秩子空间投影和Gabor特征的稀疏表示人脸识别算法[J]. 计算机工程与科学, 2017, 39(01): 131-137.
[15]	郭艳君，许道云，秦永彬. 基于QR分解重构虚拟样本的人脸识别算法[J]. 计算机工程与科学, 2016, 38(11): 2275-2281.