Graph Based Offline Signature Recognition System by using Euclidian Distance

Authors

  • Ravikumar B. Chawhan Department of computer science and engineering, Samskruti College of Engineering & Technology –Hyderabad

Keywords:

Pre-processing; Binarization; Normalization; Euclidean Distance; Graph theory; Graph based features

Abstract

Signature recognition is an important requirement of automatic document recognition system. Many
approaches for signature recognition are found in literature. A novel approach for Graph based offline signature
recognition system is presented in this paper, which is based on powerful Graph based features. The proposed system
functions in three stages. Pre-processing stage; which consists of six steps: gray scale conversion, noise removal,
normalization, binarization, resize, thinning to make signatures ready for feature extraction, Feature extraction stage;
where totally 22 features are extracted which are used to distinguish the different signatures. Finally in classification
stage; a simple Euclidean distance measure is used as decision tool. The average recognition accuracy obtained using
this model ranges from 94% to 95% with the training set of 50 persons.

Downloads

Published

2016-07-25

How to Cite

Ravikumar B. Chawhan. (2016). Graph Based Offline Signature Recognition System by using Euclidian Distance. International Journal of Advance Research in Engineering, Science & Technology, 3(7), 245–250. Retrieved from https://ijarest.org/index.php/ijarest/article/view/940

Issue

Vol. 3 No. 7 (2016): Volume: 03, Issue: 07 - July, 2016.

Section

Articles