摘要
由于红外温谱图会随着环境温度、生理及心理因素的变化而变化,从而导致红外人脸识别性能的急剧下降,针对此问题,提出一个血流模型,把红外温谱图转化为更为稳定的血流图,并介绍基于血流模型的实时红外人脸识别系统。对同时段及时延图像的实验表明:(1)当人体处于稳态时,血流图对环境温度更加鲁棒;(2)对时延图像,基于血流图的识别率接近同时段图像的识别率,而基于温谱图的识别率却大为降低。
It has been found that facial thermograms vary with ambient temperatures, as well as physiological and psycho logical conditions, and result in severe decline in the facial recognition rate. To cope with this problem, a blood perfusion model is proposed in this paper. The proposed model converts the facial thermograms into blood perfusion data which are more consistent in representing facial features. Then, our developed real-time infrared face recognition system (RIFARS) is introduced. The experiments conducted on both same-session and time-lapse data have demonstrated that (1) the blood per fusion data are less sensitive to ambient temperature if the human bodies are in the steady state~ (2) for time-lapse data, the performance with the blood perfusion data is nearly identical to that of the same-session data, while the recognition rate with the temperature data dramatically decreases in this case.
出处
《西安邮电学院学报》
2013年第1期11-21,共11页
Journal of Xi'an Institute of Posts and Telecommunications
基金
Supported by Agency for Science,Technology and Research,Singapore
关键词
人脸识别
红外图像
血流模型
归一化
时延图像
生物识别技术
face recognition, infrared facial images, blood perfusion, normalization, time lapse images, biometrics.