针对实际应用中要对不同尺度的人脸图像进行匹配和识别的需求,提出一种基于变尺度DCT(离散余弦变换)结合PCA(主成分分析法)的人脸识别方法.首先将不同尺度的人脸图像进行DCT变换,然后提取出相同的DCT系数,再将提出的DCT系数进行PCA降维,最后进行匹配识别.通过对ORL人脸库及实验采集的多尺度人脸图像进行实验,证明了所提方法对不同尺度图像的匹配识别有效,并测算了DCT变换后的修剪尺度及PCA特征维数对该方法识别准确率的影响.
A variable scale face images recognition method is proposed, based on the DCT binding the PCA. First, different scale face images are transformed by DCT. Then, the same DCT coefficients are extracted;and the dimension of the DCT coefficients is reduced by PCA. Finally, matching and recognition of images is done. By the ORL and collected face images, it is proved that the method of recognition variable scale images is efficient. Effective values of DCT transformed coefficients and PCA feature dimension are measured.
[1] CHAIT Y,RIZON M, WOO S S,et al.Facial features for template matching based face recognition[J].American Journal of Applied Sciences.2009,6(11):1897-1901.
[2] LU J,ZHAO J W,CAO F L.Extended feed forward neural networks with random weights for face recognition[J].Neurocomputing,2014(136):96-102.DOI:dx.doi.org/10.1016/j.neucom.20141.01.022.
[3] 李康顺,李凯,张文盛.一种基于改进BP神经网络的PCA人脸识别算法[J].计算机应用与软件,2014,3(11):158-161.DOI:10.3969 /j.issn.1000-386x.2014.01.041. LI Kangshun,LI Kai,ZAHNG Wensheng.PCA face recognition algorithm based on improved BP neural network[J].Computer Applications and Software,2014,3(11):158-161.DOI:10.3969 /j.issn.1000-386x.2014.01.041.
[4] ANSUMAN M,TUSAR K M,PANKAJ,et al.Human recognition system for outdoor videos using Hidden Markov model[J].International Journal of Electronics and Communications,2013,08(011):227-236.DOI:dx.doi.org/10.1016/j.aeue.2013.08.011.
[5] 李忠建,杨宜民,梅平.基于改进的隐马尔科夫模型的人脸识别方法[J].工业控制计算机,2014,27(11):29-31. LI Zhongjian,YANG Yimin,MEI Ping.Approach of face recognition based on improved Hidden Markov model[J].Industrial control computer,2014,27(11):29-31.
[6] SRINIVASAN A.A Framework for face recognition using adaptive binning and adaboost techniques[J].International Journal of Multimedia & Its Applications,2014,3(1):76-88.DOI:10.5121/ijma.2011.3107.
[7] 徐永红,申鸿魁,赵艳茹,等.四元数目小波和Adaboost在人脸识别中的应用[J].计算机工程与应用,2011,47(29):196-199.DOI:10.3778/j.issn.1002-8331.2011.29.055. XU Yonghong,SHEN Hongkui,ZHAO Yanru,et al.Application of quaternion wavelet and Adaboost in face recognition[J].Computer Engineering and Application,2011,47(29):196-199.DOI:10.3778/j.issn.1002-8331.2011.29.055.
[8] 王宏漫,欧宗瑛.人面部的代数特征与几何特征的提取及识别[D].大连:大连理工大学,2003. WANG Hongman,OU Zongying.Human facial algebraic and geometrical feature extraction and recognition[D].Dalian:Dalian University of Technology,2003.
[9] 张淑军,王高峰,石峰.基于AAM提取几何特征的人脸识别算法[J].系统仿真学报,2013,25(10):2374-2380.DOI:10.16182/j.cnki.joss.2013.10.029. ZHANG Shujun,WANG Gaofeng,SHI Feng.Face recognition algorithm based on Geometric characteristics extracted by AAM [J].System Simulation,2013,25(10):2374-2380.DOI:10.16182/j.cnki.joss.2013.10.029.
[10] 郑宇杰,杨静宇,吴小俊.基于独立成分分析和模糊支持向量机的人脸识别方法[J].系统仿真学报,2005,17(7):1768 -1770.DOI:10.16182/j.cnki.joss.2005.07.063. ZHENG Yujie,YANG Jingyu,WU Xiaojun.Face recognition by independent component analysis and fuzzy support vector machine[J].System Simulation,2005,17(7):1768 -1770.DOI:10.16182/j.cnki.joss.2005.07.063.
