首页 | 本学科首页   官方微博 | 高级检索  
     

基于统计回归模型的红外人脸温度归一化
引用本文:谢志华,刘国栋,伍世虔,方志军,卢宇. 基于统计回归模型的红外人脸温度归一化[J]. 南京大学学报(自然科学版), 2011, 0(4): 426-431
作者姓名:谢志华  刘国栋  伍世虔  方志军  卢宇
作者单位:江西科技师范学院光电子与通信重点实验室;江西财经大学信息管理学院;
基金项目:国家自然科学基金(60767001); 江西省教育厅科技项目(GJJ11225)
摘    要:为了减小环境温度对红外人脸图像的影响,本文提出了一种基于统计回归模型的红外人脸温度归一化方法.为了得到环境温度与红外人脸温谱图在对应像素点灰度之间的关系,将环境温度改变值和对应人脸上的温度变化值作为研究对象,利用统计回归方法对这两个对象进行二次多项式拟合即可得到环境温度变化和对应的人脸上温度变化的函数关系.通过得到的函...

关 键 词:红外人脸识别  统计回归模型  温度归一化  信噪比

Infrared face temperature normalization using statistical regression model
Xie Zhi-Hua,,Liu Guo-Dong,Wu Shi-Qian,Fang Zhi-Jun,Lu Yu. Infrared face temperature normalization using statistical regression model[J]. Journal of Nanjing University: Nat Sci Ed, 2011, 0(4): 426-431
Authors:Xie Zhi-Hua    Liu Guo-Dong  Wu Shi-Qian  Fang Zhi-Jun  Lu Yu
Affiliation:Xie Zhi-Hua1,2,Liu Guo-Dong1,Wu Shi-Qian2,Fang Zhi-Jun2,Lu Yu2 (1.Key Laboratory of Optic-Electronic and Communication,Jiangxi Sciences and Technology Normal University,Nanchang,330013,China,2.School of information technology,Jiangxi University of Finance and Economics,Nanchang 330013,China)
Abstract:To reduce the impact of ambient temperatures on infrared face images,a normalization method of infrared images was proposed based on a statistical regression model.Firstly,we obtained the changes of both ambient temperatures and corresponding temperatures in face were obtained,which were used to establish a function through a second-order polynomial model.Then,the infrared images were normalized to reference ambient temperatures by the relevant function.Our experiments demonstrated that the images with temp...
Keywords:infrared face recognition  statistical regression model  temperature normalization  signal noise ratio  
本文献已被 CNKI 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号