基于LDP特征和贝叶斯模型的人脸识别

doi:10.11896/j.issn.1002-137X.2017.12.051

摘要/Abstract

摘要： 针对现有的局部方向模式LDP(Local Directional Pattern)方法仅利用了图像自身的LDP特征的问题,提出将LDP特征直方图与贝叶斯(Bayes)模型相结合的方法,从而有效使用人脸图像的先验信息,以提高人脸的识别率。第一步,在相互独立的训练集上,学习同类样本图像和异类样本图像的LDP直方图特征相似度的先验信息,并估计类条件概率密度函数(同类样本与异类样本分别进行计算)；第二步,利用人脸图像的LDP直方图来比较该图像是否为某一类型图像的概率数值大小；第三步,使用贝叶斯规则进行分类。仿真结果证明,在ORL库与Yale库上,与传统PCA,LBP和LDP算法相比,所提方法得到的人脸识别率均有显著提升。

关键词: 人脸识别,局部方向模式,LDP,贝叶斯模型

Abstract: For the existing Local Directional Pattern method,the LDP feature of the image itself is only proposed,and a method of combining the LDP feature histogram and the Bayesian model is proposed,which effectively improves the recognition rate by using the face image test information.The method firstly learned the prior information of similarity of LDP histogram in the same class and in different class,and evaluated the same class conditional probability density function and different class conditional probability density function.When a probe image was discriminated,the method calculated the similarity of the probe and a template image in database using their LDP histogram features,and then evalua-ted the post erior probability of the pair images coming from the same person.Finally,the probe image was classified by Bayes rule.The propose method fuses the LDP feature and prior information into face data.Experiment results on ORL and Yale databases show that it is valid and the recognition accuracy rates are improved considerably on ORL database and Yale database compared with PCA method,LBP method and LDP method.

Key words: Face recognition,Local directional pattern,LDP,Bayesian model

王燕,李鑫. 基于LDP特征和贝叶斯模型的人脸识别[J]. 计算机科学, 2017, 44(12): 283-286. https://doi.org/10.11896/j.issn.1002-137X.2017.12.051

WANG Yan and LI Xin. Face Recognition Based on LDP Feature and Bayesian Model[J]. Computer Science, 2017, 44(12): 283-286. https://doi.org/10.11896/j.issn.1002-137X.2017.12.051

参考文献

[1] ZHAO W,CHELLAPPA R.Face recognition:A Literature Survey [J].ACM Computing Surveys,2003,5(4):399-458.
[2] XIONG C Y,LI D T,DA B Y.Feature Extraction Using LBP and PCA for Face Recognition[J].Journal of South-Central University for Nationalities(Natural Science Edition),2011,30(2):75-79.(in Chinese) 熊承义,李丹婷,笪邦友.基于LBP和PCA特征提取的人脸识别 [J] 中南民族大学学报:自然科学版,2011,0(2):75-79.
[3] TURK M A,PENTLAND A P.Eigenfaces for Recognition[J].Journal of Cognitive Neuroscience,1991,3(1):71-86.
[4] ETENMAD K,CHELLAPP R.Discriminant analysis for recognition of human face images[J].Journal of the Optical Society of America,1997,4(8):1724-1733.
[5] BARLETT M S,MOVELLAN J R,SEJNOWSKI T J.FaceRecognition By Independent Component Analysis [J].IEEE Transactions on Neural Networks,2002,3(6):1450-1464.
[6] OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on feature distributions[J].Pattern Recognition,1996,9(1):51-59.
[7] AHONEN T,HADID A,PIETIKAINEN M.Face Description with Local Binary Patterns:Application to Face Recognition [J].IEEE Transactions on Pattern Analysis And Machine Intelligence,2006,8(12):2037-2041.
[8] PENEV P S,ATICK J J.Local Feature Analysis:A General Statistical Theory for Object Representation [J].Network:Comput.Neural Syst,1996,7(3):477-500.
[9] DAUGMAN J G.Uncertainty relation for resolution in space,spatial frequency,and orientation optimized by two-dimensional visual cortical filters [J].Journal of the Optical Society of America A,1985,2(7):1160-1169.
[10] JABID T,KABIR M H,CHAE O S.Local Directional Pattern(LDP) for Face Recognition [C] ∥IEEE International Confe-rence on Consumer Electronics.2010.
[11] GUO H F,LU J F,DONG Z W.Face recognition method based on improved LBP algorithm[J].Modern Electronics Technique,2015(4):98-101.(in Chinese) 郭贺飞,陆建峰,董忠汶.一种基于改进LBP特征的人脸识别[J].现代电子技术,2015(4):98-101.
[12] LUO Y,ZHANG T,ZHANG Y.Semiconductor Optoelectronics[J].An Improved LDP for Facial Expression Feature Extraction,2016(1):122-125.(in Chinese) 罗元,张天,张毅.一种改进的LDP面部表情特征提取方法[J].半导体光电.2016(1):122-125.
[13] ZHONG F J,ZHANG J S.Noise-robust face recognition algorithm based on improved local directional pattern[J].Journal of Optoelectronics·Laser,2012,3(8):1570-1575.(in Chinese) 钟福金,张家树.基于ILDP的噪声鲁棒人脸识别[J].光电子·激光,2012,3(8):1570-1575.
[14] ZHONG F J,ZHANG J S.Face recognition with enhanced local directional patterns [J].Neurocomputing,2013,9:375-384.
[15] RAMIREZ RIVERA A,ROJAS CASTILLO J,O KSAM C.Local directional number pattern for face analysis:Face and Expression recognition [J].IEEE Transaction Image Processing,2013,2(5):1740-1752.
[16] LI J,XU T R,LI H Y.Face recognition based on improved LDP[J].Computer Applications and Software,2014(5):148-150.(in Chinese) 李杰,徐汀荣,李海彦.基于改进LDP的人脸识别[J].计算机应用与软件,2014(5):148-150.
[17] WU W,JIANG Y X,ZHANG Z.The Face Recognition Algorithm Based on Improved Local Directional Pattern[J].Opto-Electronic Engineering,2014,1(12):72-77.(in Chinese) 武伟,江艳霞,张喆.基于改进的LDP人脸识别算法[J].光电工程,2014,1(12):72-77.
[18] YANG J,GAO Z S,YUAN H Z,et al.Single sample face recognition based on LBP feature and Bayes model[J].Journal of Optoelectronics.Laser,2011(5):763-765.(in Chinese) 杨军,高志升,袁红照,等.基于LBP特征和贝叶斯模型的单样本人脸识别[J].光电子·激光,2011(5):763-765.
[19] 闫常浩,丁先锋,韦鑫余.人脸识别算法[J].四川兵工学报,2011,32(4):65-67.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed