Human Authentication Based on ECG Waves Using Radon Transform

Automated security is one of the major concerns of modern times. Secure and reliable authentication systems are in great demand. A biometric trait like electrocardiogram (ECG) of a person is unique and secure. In this paper, we propose a human authentication system based on ECG waves considering a plotted ECG wave signal as an image. The Radon Transform is applied on the preprocessed ECG image to get a radon image consisting of projections for theta varying from 0 degrees to 180 degrees. The pairwise distance between the columns of Radon image is computed to get a feature vector. Correlation Coefficient between feature vector stored in the database and that of input image is computed to check the authenticity of a person. Then the confusion matrix is generated to find False Acceptance Ratio (FAR) and False Rejection Ratio (FRR). This methodology of authentication is tested on ECG wave data set of 105 individuals taken from Physionet QT Database. The proposed authentication system is found to have FAR of about 3.19% and FRR of about 0.128%. The overall accuracy of the system is found to be 99.85%.