基于统计回归模型的红外人脸温度归一化*

南京大学学报(自然科学版) ›› 2011, Vol. 47 ›› Issue (4): 426–431.

基于统计回归模型的红外人脸温度归一化*

谢志华¹²**，刘国栋¹，伍世虔²，方志军²，卢宇²

出版日期:2015-04-15 发布日期:2015-04-15
作者简介: (1.江西科技师范学院光电子与通信重点实验室，南昌，330013
2.江西财经大学信息管理学院，南昌，330013)
基金资助:
国家自然科学基金(60767001)，江西省教育厅科技项日(GJJ 11225)

Infrared face temperature normalization using statistical regression model

Xie Zhi一Hua¹² ,Liu Guo Dong ¹ ,Wu Shi一Qian² ,Fanh Zhi一Jun²,Lu Yu²

Online:2015-04-15 Published:2015-04-15
About author: (1 .Kcy Laboratory of Optic-Electronic and Communication, Jiangxi Sciencesand Technology Normal University, Nanchang, 330013，China

摘要/Abstract

摘要： 为了减小环境温度对红外人脸图像的影响，木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.通过得到的函数关系，建立归一化模型对红外
图像进行温度归一化处理，减小环境温度对红外人脸识别的影响.实验结果表明:相对于归一化前的图像，温度归一化后的红外人脸图像与参考图像之间的信噪比有了明显改善，木文提出的归一化方法提高了红外人脸识别识别率.

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 temperature normalization have higher signal noise ratio than those without normalization, and that our method can significantly
improve the infrared face-recognition performance.

谢志华¹²**，刘国栋¹，伍世虔²，方志军²，卢宇²
. 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, 47(4): 426–431.

Xie Zhi一Hua¹² ,Liu Guo Dong ¹ ,Wu Shi一Qian² ,Fanh Zhi一Jun²,Lu Yu². Infrared face temperature normalization using statistical regression model[J]. Journal of Nanjing University(Natural Sciences), 2011, 47(4): 426–431.

参考文献

[1]Wu S Q, Wei L. Z, Fang Z J. infrared face rer ognition technology; A survey. Journal of lm- age and Graphics, 2008，13(12):2260一2269. (伍世虔，韦礼珍，方志军.红外人脸识别技术.中国图像图形学报，2008, 13(12); 2260}- 2269).
[2]Socolinsky D A，Sclingcr A.Thcrmal face recognition in an operational scenario.Computer vision and pattern recognition. Proceedings of IEEE international Conference on Computer Vi sion and Pattern Recognition 2004，2，2004:1012~1019
[3]Wu S Q, Fang Z J，Xie Z H，et al. Rcccnt ad- vance in face recognition. Australia; ln-Tech Press, 2008:184一206.
[4]Wu S Q, Jiang L J，Chcng L，et al. R7FARS: A real-time infrared face recognition system. Proceedings of Asian Biomctric Workshop, Sin gapore，2003:1一6.
[5]Kakuta N，Yokoyama S, Mahuchi K. Human thermal models for evaluating infrared images. IEEE Medicine and Biology Society, 2002，21: 65一72.
[6]Wu S Q, Jiang L J，Xic S L, et al, infrared face recognition by using blood perfusion data. Proceedings of Audio-and Video-based Biometric Person Authentication, 2005，320一328.
[7]Xic X,Lam K M. Face recognition under var ying illumination based on a 2D face shape mod el. Pattern Recognition,2005，38(2);221一230
[8]Jiang Q Y，He Q, Uao L. Mathematics Experincnts.Beijing; Higher Education Press, 2004(姜启源，何晴，高立.数学实验.高等教育出版社，2004).
[9]Xic X H，Lai J H，Zhcng W S. illumination normalization of human face based on the scr ond-order polynomial model. Acta Electronic Sinica, 2010, 38(8): 1791一1797.(谢晓华，赖剑煌，郑伟诗.基于二次多项式模型的人脸归一化研究.电子学报，2010, 38(8): 1791一1797).

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed