Human identification using main loop of the VCG contour

In this paper the possibility of using the VCG "Vectorcardiograph" main loop for Biometrics identification is investigated. A test set of 550 VCG contours recorded from 22 healthy individuals measured at different times are used to validate the system. The proposed system uses only the main loop of the VCG contour for identification. Two different algorithms are used. In the first one selected Fourier Descriptor coefficients of the main loop of the VCG are used as biometric data. In the second method coefficients from specially developed descriptor are used for identification. In both methods Feed Forward Neural Networks are used as classifiers giving an identification rate ranging from 95% to 99.45%.