罗丽红,刘春晓,柯灵

• 1:重庆邮电大学移通学院
• 2:重庆电讯职业学院计算机与传媒系

摘要(Abstract)：

为提高异质人脸识别模型精度,提出一种基于二进制多层Gabor极限学习机(GELM)的异质人脸识别模型方法。首先,提出一种新的基于像素加权的随机加权Gabor特征提取方案,将局部几何输入图像子块传播到隐藏节点,并将提取的Gabor特征嵌入隐藏层中,利用一组Gabor核随机加权求和,实现对传播像素的非线性激活函数的卷积运算;然后,利用类似于极限学习机方式对输出层采用线性加权方法进行估计。最后,利用BERC VIS-TIR数据库和CASIA NIR-VIS 2.0数据库对所提算法的异质人脸识别方法性能进行验证,实验结果显示该算法识别精度高、CPU计算时间短。

关键词(KeyWords)： 异质人脸识别;Gabor特征提取;性能验证;极限学习机;识别模型;Gabor滤波

Abstract:

Keywords:

基金项目(Foundation): 基于云平台的智慧教育教学模式改革探讨实践~~

作者(Author): 罗丽红,刘春晓,柯灵

DOI: 10.16652/j.issn.1004-373x.2018.23.009

参考文献(References)：

• [1]谌湘倩,刘坷,马飞.基于协作表示和正则化最小二乘法的多姿态人脸识别方法[J].现代电子技术,2017,40(5):49-53.CHEN Xiangqian,LIU Ke,MA Fei.Multi pose face recognition method based on cooperative representation and regularized least square method[J].Modern electronics technique,2017,40(5):49-53.
• [2]贾海鹏,张云泉,袁良,等.基于OpenCL的Viola-Jones人脸检测算法性能优化研究[J].计算机学报,2016,39(9):1775-1789.JIA Haipeng,ZHANG Yunquan,YUAN Liang,et al.Research on the performance optimization of Viola-Jones face detection algorithm based on OpenCL[J].Chinese journal of computer,2016,39(9):1775-1789.
• [3]李月龙,孟丽,封举富,等.基于光照补偿空间的鲁棒人脸识别[J].中国科学:信息科学,2013,43(11):1398-1409.LI Yuelong,MENG Li,FENG Jufu,et al.Robust face recognition based on illumination compensation space[J].Chinese science:information science,2013,43(11):1398-1409.
• [4]伍凯,朱恒亮,郝阳阳,等.级联回归的多姿态人脸配准[J].中国图象图形学报,2017,22(2):257-264.WU Kai,ZHU Hengliang,HAO Yangyang,et al.Cascaded regression of multi pose face registration[J].Chinese journal of image and graphics,2017,22(2):257-264.
• [5]SHAIKH M K,LAWGALY A,TAHIR M A,et al.Modality identification for heterogeneous face recognition[J].Multimedia tools and applications,2017,76(3):4635-4650.
• [6]LüXiong,JIANG Shuqiang,HERRANZ Luis,et al.RGB-Dhand-held object recognition based on heterogeneous feature fusion[J].Journal of computer science and technology,2015,30(2):340-352.
• [7]ROY Hiranmoy,BHATTACHARJEE Debotosh.Face sketchphoto recognition using local gradient checksum:LGCS[J].International journal of machine learning and cybernetics,2017,8(5):1457-1469.
• [8]KAR Arindam,SARKAR Sanchayan,BHATTACHARJEE Debotosh.Local centre of mass face for face recognition under varying illumination[J].Multimedia tools and applications,2017,76(18):19211-19240.
• [9]HO H T,GOPALAN R.Model-driven domain adaptation on product manifolds for unconstrained face recognition[J].International journal of computer vision,2014,109(1/2):110-125.
• [10]RAHMAN R A,SOMMER W.Knowledge scale effects in face recognition:an electrophysiological investigation[J].Cognitive,affective&behavioral neuroscience,2012,12(1):161-174.
• [11]TORRE M D L,GRANGER E,SABOURIN R,et al.An adaptive ensemble-based system for face recognition in person re-identification[J].Machine vision and applications,2015,26(6):741-773.
• [12]ZHANG Yuanyuan,ZHAO Dong,SUN Jiande,et al.Adaptive convolutional neural network and its application in face recognition[J].Neural processing letters,2016,43(2):389-399.
• [13]TIAN Lei,FAN Chunxiao,MING Yue.Learning spherical hashing based binary codes for face recognition[J].Multimedia tools and applications,2017,76(11):13271-13299.
• [14]JIN Yi,LU Jiwen,RUAN Qiuqi.Coupled discriminative feature learning for heterogeneous face recognition[J].IEEEtransactions on information forensics and security,2015,10(3):640-652.
• [15]GONG Dihong,LI Zhifeng,HUANG Weilin,et al.Heterogeneous face recognition:a common encoding feature discriminant approach[J].IEEE transactions on image processing,2017,26(5):2079-2089.