Video-analysis inference automated ECG (VID-ECG): improving video-based heart rate detection and exposing security risks of ECG-based biometric authentication

security;biometric;video processing;Video-analysis Inference Electrocardiogram (VID-ECG);image processing;signal processing;Eulerian

Adhikari, Anku ; Hu ; Yih-Chun

关键词: security;    biometric;    video processing;    Video-analysis Inference Electrocardiogram (VID-ECG);    image processing;    signal processing;    Eulerian;   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/89206/ADHIKARI-THESIS-2015.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Many recent biometric authentication methods using heart signals in theform of ECG and its components have been proposed to be used as a uniquesecurity key for body area networks (BANs) to authenticate individuals andprotect privacy and network security. In this thesis we show how compo-nents of information on cardiac activity, heart rate and beat-to-beat heartpulse information can be extracted easily using our video-based non-contactmethod and expose the vulnerability of such biometric security protocols.We propose a novel method called Video-analysis Inference AutomatedECG (VID-ECG) for pulse extraction by facial video processing. Our al-gorithm combines facial region tracking, motion stabilization, filtering andheart beat information extraction methods to allow automated extraction ofeach pulse from subject facial videos. VID-ECG results show a high level ofaccuracy and, unlike related methods in this area, VID-ECG does automaticextraction without knowledge of any frequency range. It is also able to han-dle natural motion in subjects. We applied VID-ECG on a wide range ofsubjects with varied skin tones, and found accuracy to be high, with morethan 0.9 cross-correlation with ground truth and error less than 0.085% ofaverage heart rate for each sample. Results have also been compared witha previously proposed video based method for heart rate extraction, and ac-curacy and beat-to-beat correspondence have been shown to be significantlyimproved, mainly due to the more realistic filtering used and improved mo-tion handling features of VID-ECG.As we are able to obtain many components of cardiac activity such asaverage heart rate information and close to real-time beat-to-beat informa-tion, we discuss the implication of our results and how VID-ECG exposesthe vulnerability of ECG/cardiac data based biometric authentication meth-ods to remote attack using easily obtainable video data from omnipresentcommodity cameras around us today in public and private spaces.