Human recognition with heartbeat signal is useful for different applications such as information security, user identification and remote patient monitoring. In this paper, we propose a model-based method for the alignment of heartbeat morphology to enhance the recognition capability. The scale change of different heartbeats of the same individual due to heart rate variability is estimated and inversed to yield better alignment. Recognition capabilities of different alignment methods are analyzed and measured by intra-individual and inter-individual distances of aligned heartbeats. A framework for heartbeat recognition incorporating the model-based alignment method is also presented. We tested the recognition capability of heartbeat morphology by using two different databases. It was found that model-based alignment method was useful to boost the recognition capability of heartbeat morphology. A statistical t-test revealed that the improvement was significant with respect to recognition capabilities of other existing alignment methods. We also used the aligned morphology as a feature, tested the recognition accuracy on both databases and compared the recognition performance to those of four other state-of-the-art features. A large increase in recognition accuracy was obtained especially for a multisession database of heartbeat signals captured from fingers using a handheld ECG device.