Degraded partial palmprint recognition for forensic investigations

Palmprint trait is emerging as a new and practical biometric solution and a few systems using full palmprints have been proposed. However, partial palmprints left at scenes of crime have not yet been exploited to recognize and find crime suspects. In this paper, a modified well known algorithm, referred to as modified phase only correlation (MPOC) is proposed to match poor quality (degraded) partial palmprints left by suspects at crime scenes against a full palmprint registered in a template database. Instead of using the conventional peak as the matching score between two palmprint images, the ratio of the conventional peak to the highest peak in the outside-lobe correlation plane is employed. Experiments were conducted on a generated database of 800 partial palmprints having an area less than 25% of that of the full palmprint images from which blurred and degraded images were created by adding an intense synthetic Gaussian noise. The results show that the proposed method yields high recognition performance thus demonstrating its ability to tackle the problem of identifying low quality partial palmprint images giving an equal error rate (EER) less than 0.4%.