Person identification is an essential task in defense and forensic applications such as surveillance and criminal investigation activities. Studies conducted in the past included different types of regular biometric traits, namely fingerprint, face, iris, and voice have a limitation of falsification, and they do not fit guarantee of liveness of the subject. In this context, Electrocardiogram based Biometric recognition is an alternative solution, where the security of the information is very high level. This research aims to provide with a complete systematic approach to ECG based Biometric recognition, which contains primarily the processing of raw signal through noise elimination filters and a time domain analysis is carried for all ECG characteristic waves detection. Subsequently, an effective feature extraction method for ECG is developed, which extracts six best P-QRS-T fragments based on priority and their positions are normalized. Also, 72-time domain features are calculated. These features are formed into feature vector corresponding to each signal separately for both train and test data sets. To analyze the performance of the system, the feature vectors are trained with various Machine learning classification algorithms like Artificial Neural Network (ANN), Support Vector Machine (SVM) and K-Nearest Neighbor (KNN). Finally, the proposed system is tested with a challenging, public available MIT-BIH ECG-ID Database. A comparative analysis using performance parameters is made with different classifiers, and the obtained results show that SVM classifier provides 93.709% overall classification accuracy when compared to previous literature.