Automatic Verification for Handwritten Based on GLCM Properties and Seven Moments

Abstract

In recent years, the need for community verification of personality has increased dramatically, and biometrics are becoming very important in many daily applications. Biometrics work to verify individuals based on measurable data for their descriptions and characteristics. Biometric systems have thus been able to verify or identify a person.
 The fact that the use of handwritten signatures are recognized in all societies, and because they are biometric, has made signature verification an important biometric process. In this paper, a number of models are collected from hand signatures for a person to study the characteristics of the parity matrix for each of these signatures for the purpose of finding common factors between the characteristics of the matrix of these models. The practical aspect summarizes the removal of all empty spaces outside the frame of the signature image to be followed by the process of unifying the dimensions, and then drawing four characteristics of the matrix of the dialogues. The process is conducted on a sample of 100 samples to sign the person to draw the qualities of his signature and then find the common characteristics among those four attributes of the signatures group.
 The tests conducted on 10 people proved that the adoption of the plastic qualities offers a clear distinction between people's manual signatures. More than 80% of the signatures of people who were approved for the test were found. Thus supporting the possibility of being adopted as a biometric standard for personal verification, Matlab has been adopted for the implementation of the software.