Can Handwriting Style Help Strengthen the Person Identity?

Abstract

Recently, user identification is an essential founda- tion for protecting information in several applications. However, the need for heightened this identification has expanded the research to focus on the biometric traits of the users. Obviously, one of the biometrics based behavioral characteristics advantage is their simplicity of use as well as their acceptability by the users. For that, among several behavioral characteristics, person handwriting has been systematically used to make identification for last years. Handwriting identification aims to determine which person or writer has written a given text sample. In this paper, we aim to design a Latin script identification system based on Local Phase Quantization (LPQ) and then the obtained results are used to constrict a biometric based person identification system. The proposed method is validated for their efficacy on the available CVL-Database of 310 writers. Our experimental results show the effectiveness and reliability of the proposed method, which brings both high recognition and accuracy rate.