Title :
Pennes Equation based blood perfusion model and its application in face recognition
Author :
Xie Zhihua ; Liu Guodong ; Wu Shiqian ; Fang Zhijun ; Gan Yun
Author_Institution :
Key Lab. of Opt.-Electron. & Commun., Jiangxi Sci. & Technol. Normal Univ., Nanchang, China
Abstract :
To get stable biological features from the time-elapse infrared face, a new construction method of blood perfusion is proposed based on bio-heat transfer, which can be applied to face recognition. Firstly, according to the classic bio-heat transfer equation (the Pennes Equation), the blood perfusion rate in different positions can be computed based on the new blood perfusion model (PBPM). Then, due to the low-resolution of the infrared images, the feature extraction method (Liner Discriminative Analysis in DCT domain) is chosen to get the principle features in the blood perfusion image, which is suitable for real-time application. The experiment results demonstrate that compared traditional methods, the blood perfusion model proposed in this paper is more stable, the infrared face recognition method proposed is robust to both same-session data and time-elapse data.
Keywords :
discrete cosine transforms; face recognition; feature extraction; heat transfer; image resolution; infrared imaging; DCT domain; Pennes equation; bio-heat transfer equation; blood perfusion model; discrete cosine transform; face recognition; feature extraction method; infrared image; linear discriminative analysis; low image resolution; stable biological feature; time-elapse infrared face; Biological system modeling; Biology computing; Blood; Differential equations; Discrete cosine transforms; Face recognition; Feature extraction; Image analysis; Infrared imaging; Robustness; Pennes equation; bio-heat transfer; blood perfusion image; face recognition;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512277