Journal Article•
Handwritten signature identification using basic concepts of graph theory
01 Oct 2011-WSEAS Transactions on Signal Processing archive (World Scientific and Engineering Academy and Society (WSEAS))-Vol. 7, Iss: 4, pp 117-129
TL;DR: Previous work in the field of signature and writer identification is presented to show the historical development of the idea and a new promising approach in handwritten signature identification based on some basic concepts of graph theory is defined.
Abstract: Handwritten signature is being used in various applications on daily basis. The problem arises when someone decides to imitate our signature and steal our identity. Therefore, there is a need for adequate protection of signatures and a need for systems that can, with a great degree of certainty, identify who is the signatory. This paper presents previous work in the field of signature and writer identification to show the historical development of the idea and defines a new promising approach in handwritten signature identification based on some basic concepts of graph theory. This principle can be implemented on both on-line handwritten signature recognition systems and off-line handwritten signature recognition systems. Using graph norm for fast classification (filtration of potential users), followed by comparison of each signature graph concepts value against values stored in database, the system reports 94.25% identification accuracy.
Citations
More filters
TL;DR: The approaches taken from other researches on preprocessing, feature extraction and classification stage specifically for recognizing individual identity for biometrics trait using finger-vein are discussed.
Abstract: Biometrics trait using finger-vein has attracted numerous attention from researchers all over the world since the last decade. Various approaches have been proposed in regard to improving the accuracy of identification result. This paper discusses on the approaches taken from other researches on preprocessing, feature extraction and classification stage specifically for recognizing individual identity. The strengths and weaknesses of these approaches are critically reviewed. The classification approach using machine learning method is highlighted to determine the future direction and to fill the research gap in this field.
53 citations
TL;DR: Offline signature verification is a challenging pattern recognition task where a writer model is inferred using only a small number of genuine signatures using a combination of complementary writer mode and reader mode.
36 citations
Cites background from "Handwritten signature identificatio..."
..., 2009), and basic concepts of graph theory (Fotak et al., 2011)....
[...]
29 Nov 2016
TL;DR: Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Patternrecognition (SSPR), and S+S SPR 2016: Structural, Syntactic, and Statistical pattern recognition.
Abstract: Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR). S+SSPR 2016: Structural, Syntactic, and Statistical Pattern Recognition pp. 553-563.
34 citations
Cites background from "Handwritten signature identificatio..."
...Recently, graphs have gained some attention in the field of handwritten document analysis [4] like for instance handwriting recognition [6], keyword spotting [7–9], or signature verification [10,11]....
[...]
17 Aug 2018
TL;DR: This work proposes to complement a recent structural approach to offline signature verification based on graph edit distance with a statistical approach based on metric learning with deep neural networks, and demonstrates that combining the structural and statistical models leads to significant improvements in performance.
Abstract: Biometric authentication by means of handwritten signatures is a challenging pattern recognition task, which aims to infer a writer model from only a handful of genuine signatures. In order to make it more difficult for a forger to attack the verification system, a promising strategy is to combine different writer models. In this work, we propose to complement a recent structural approach to offline signature verification based on graph edit distance with a statistical approach based on metric learning with deep neural networks. On the MCYT and GPDS benchmark datasets, we demonstrate that combining the structural and statistical models leads to significant improvements in performance, profiting from their complementary properties.
17 citations
01 Nov 2017
TL;DR: A novel structural approach to offline signature verification using an efficient cubic-time approximation of graph edit distance is introduced and several ways of creating, normalizing, and comparing signature graphs built from keypoints are put forward.
Abstract: Graphs provide a powerful representation formalism for handwritten signatures, capturing local properties as well as their relations. Yet, although introduced early for signature verification, only a few current systems rely on graph-based representations. A possible reason is the high computational complexity involved for matching two general graphs. In this paper, we introduce a novel structural approach to offline signature verification using an efficient cubic-time approximation of graph edit distance. We put forward several ways of creating, normalizing, and comparing signature graphs built from keypoints and investigate their performance on three benchmark datasets. The experiments demonstrate a promising performance of the proposed structural approach when compared with the state of the art.
16 citations
Cites background from "Handwritten signature identificatio..."
...The most prominent examples include [6] where signatures were represented with stroke primitives, [7] which proposed a modular graph matching approach, and [8] which leveraged some basic concepts of graph theory for signature verification....
[...]
References
More filters
03 Aug 2003
TL;DR: The distribution of the pixel gray levels within the line is considered, linked to pressure and writingspeed when text is realized, and shows the gray level distribution within the writing is characterizing the writer in a significant way.
Abstract: When identifying a writer from a handwritten text, mostoften, either some characteristic patterns or some shapeparameters are extracted. They are assumed to be specificof the writer. Here, we are to explore a differentapproach, we consider the distribution of the pixel graylevels within the line. It is linked to pressure and writingspeed when text is realized.In the line, the direction that is perpendicular to thewriting way of drawing is privileged. The curve associatedwith the gray levels in a stroke section is characterized byuse of 4 shape parameters. More over the regular sectionsare selected and are grouped in section lots. Thedistributions of the sections and of the section lots arequantified. Thus 22 parameters are extracted. Threedifferent classifiers are used with and without geneticselection of the most significant parameters for theclassifier. Then the classifiers are combined and theresults show the gray level distribution within the writingis characterizing the writer in a significant way.
18 citations
"Handwritten signature identificatio..." refers methods in this paper
...This is why we will mention some of the previous work in this field as a good idea that can be used in signature identification....
[...]
TL;DR: A novel approach to the problem of signature identification by introducing the use of the revolving active deformable model as a powerful way of capturing the unique characteristics of the overall structure of a signature.
17 citations
"Handwritten signature identificatio..." refers background in this paper
...When dealing with signature identification, we can talk about off-line and on-line handwritten signature identification....
[...]
TL;DR: A novel wavelet-based Generalized Gaussian Density (GGD) method for offline writer identification that not only achieves a better identification accuracy but also greatly reduces the elapsed time on calculation in the authors' experiments.
Abstract: Handwriting-based personal identification, which is also called handwriting-based writer identification, is an active research topic in pattern recognition. Despite continuous effort, offline handwriting-based writer identification still remains as a challenging problem because writing features can only be extracted from the handwriting image. As a result, plenty of dynamic writing information, which is very valuable for writer identification, is unavailable for offline writer identification. In this paper, we present a novel wavelet-based Generalized Gaussian Density (GGD) method for offline writer identification. Compared with the 2-D Gabor model, which is currently widely acknowledged as a good method for offline handwriting identification, GGD method not only achieves a better identification accuracy but also greatly reduces the elapsed time on calculation in our experiments.
13 citations
"Handwritten signature identificatio..." refers methods in this paper
...This is why we will mention some of the previous work in this field as a good idea that can be used in signature identification....
[...]
Proceedings Article•
23 May 2011
TL;DR: An overview of the differences between off-line and on-line mode of authentication system based on the handwritten signature as well as surveys of some properties that these features can have, supported with the latest systems to "capture" handwritten signatures are provided.
Abstract: On-line handwritten signature-based personal authentication is still a challenging research topic. Although great efforts have been achieved in developing and defining a framework that systems for on-line authentication based on the handwritten signature of a person should adhere, these frameworks are still not enough because they do not include all the features that handwritten signature as a biometric feature has. In addition, there is a range of features that current system for capturing a signature posses by which it is possible to further and better define the characteristics of signatures required to be in the process of authentication of entities, but can be used not only for authentication but also for identification. The paper provides an overview of the differences between off-line and on-line mode of authentication system based on the handwritten signature as well as surveys of some properties that these features can have, supported with the latest systems to "capture" handwritten signatures.
10 citations
"Handwritten signature identificatio..." refers background in this paper
...This is promising result for the further development of the proposed identification system....
[...]
01 Jan 2010
TL;DR: The recognition rate of Radial Basis Function (RBF) is found to be better compared to that of Back Propagation Network (BPN) and the recognition rate in the proposed system lies between 90% to 100%.
Abstract: Handwriting has continued to persist as a means of communication and recording information in day-to-day life even with the introduction of new technologies. Given its ubiquity in human transactions, machine recognition of handwriting has practical significance, as in reading handwritten notes in a personal Digital Assistant (PDA), in postal addresses on envelopes, in amounts in back checks, in handwritten fields, in forms etc . to solve the problem of writer identification with intermediate classes (writers) and objects (characters) , it is a good way to extract the features with clear physical meanings. The extracted features are in variant under translation scaling and stroke width. In this paper we tested our system using over 500 text lines from 20 writers and have in 95.45% of all cases correctly identified the writer. The off-line (which pertains to scanned images) is considered. Algorithms are preprocessing, character and word recognition, and performance with practical system are indicated. The recognition rate of Radial Basis Function (RBF) is found to be better compared to that of Back Propagation Network (BPN). The recognition rate in the proposed system lies between 90% to 100%.
10 citations
"Handwritten signature identificatio..." refers methods in this paper
...This is why we will mention some of the previous work in this field as a good idea that can be used in signature identification....
[...]