Lip print recognition based on DTW algorithm

Abstract

This paper presents a method of lip print recognition using the Dynamic Time Warping algorithm (DTW). The presented method consists of two stages. In the first stage lip print image is subjected to pre-processing which aims to distinct the lip pattern. In the second stage features extraction is performed by generation of the lip pattern image projections: horizontal, vertical and oblique (angle of 45° and 135°). The resulting projections are then compared with each other using the DTW algorithm. Tests were conducted for lip print images acquired from 30 individuals. The results are satisfactory and suggest the possibility of using the method in forensic identification systems.