Shifted 1D-LBP Based ECG Recognition System

ECG analysis has been investigated as promising biometric in many fields especially in medical science and cardiovascular disease for last decades in order to exploit the discriminative capability provided by these liveness measures developing a robust ECG based recognition system. In this paper, an ECG biometric recognition system was proposed based on shifted 1D-LBP. Shifted 1D-LBP was applied to extract the representative non-fiducial features from preprocessed and segmented ECG heartbeats. For matching step, K Nearest Neighbors (KNN) was adopted. Two benchmark databases namely MIT-BIH/Normal Sinus Rhythm and ECG-ID database were used to validate the proposed approach. A Correct Recognition Rate (CRR) of 100% and 97% was achieved with MIT-BIH/Normal Sinus Rhythm and ECG-ID databases, respectively.