Online Signature Verification

2014 ◽  
Vol 24 ◽  
pp. 5-19 ◽  
Author(s):  
Marianela Parodi ◽  
Juan C. Gomez ◽  
Linda Alewijnse ◽  
Marcus Liwicki
Keyword(s):  
Information Fusion ◽  
Wavelet Decomposition ◽  
State Of The Art ◽  
Error Rates ◽  
Signature Verification ◽  
Signature Analysis ◽  
Discriminative Power ◽  
Feature Sets ◽  
Online Signature ◽  
Online Signature Verification

In this paper, the discriminative power of a set of features which seems to be relevant to signature analysis by Forensic Handwriting Experts (FHEs) is analyzed and particularly compared to the discriminative power of automatically selected feature sets. This analysis could help FHEs to further understand the signatures and the writer behaviour. In addition, two information fusion schemes are proposed to combine the discriminative capability of the two types of features being considered. The coefficients in the wavelet decomposition of the different time functions associated with the signing process are used as features to model them. Two different signature styles are considered, namely, Western and Chinese, of one of the most recent publicly available Online Signature Databases. The experimental results are promising, especially for the features that seem to be relevant to FHEs, since the obtained verification error rates are comparable to the ones reported in the state-of-the-art over the same datasets. Further, the results also show that it is possible to combine both types of features to improve the verification performance. Purchase Article for $10 

OPTIMAL PROTOTYPE FUNCTIONS OF FEATURES FOR ONLINE SIGNATURE VERIFICATION

2004 ◽  
Vol 18 (07) ◽  
pp. 1189-1206 ◽  
Author(s):  
JULIO CESAR MARTÍNEZ ROMO ◽  
ROGELIO ALCÁNTARA SILVA
Keyword(s):  
Error Rates ◽  
Signature Verification ◽  
Static Characteristics ◽  
Continuous Space ◽  
Verification Algorithm ◽  
Verification Problem ◽  
Online Signature ◽  
Online Signature Verification ◽  
The One ◽  
Rejection Rates

It is well known that the approach of functions of time to represent the dynamic and static characteristics of signatures usually outperforms the approaches based on parameters; in addition to this result, we propose here that the model or prototype function of the discriminant features of the signatures should be created considering the signature verification problem as a bi-objective optimization problem in which the false acceptance and false rejection rates are minimized simultaneously; to accomplish these goals, a discrete space of solutions is searched by a genetic algorithm, and a continuous space of solutions is searched by a modified gradient method, both spaces containing candidate prototype functions and the one that best meets some optimization criteria is first chosen as the optimal prototype function and then improved. Given that creating the prototype functions of features is just one of the earlier steps of a signature verification system, we also propose here a scheme of signature verification algorithm with intelligent classification. Our approach was tested in the context of random and highly skilled forgeries, with error rates below 0.1% over 7,300 verifications. Our database consisted of 1,762 exemplars, containing genuine signatures and skilled forgeries from 36 persons. Comparison to other methods of making prototype functions of features is shown.

scholarly journals Online Handwritten Signature Verification Using Neural Network Classifier Based on Principal Component Analysis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Vahab Iranmanesh ◽  
Sharifah Mumtazah Syed Ahmad ◽  
Wan Azizun Wan Adnan ◽  
Salman Yussof ◽  
Olasimbo Ayodeji Arigbabu ◽  
...  
Keyword(s):  
Principal Component Analysis ◽  
Principal Component ◽  
Rejection Rate ◽  
Component Analysis ◽  
Error Rates ◽  
Signature Verification ◽  
Feature Selection Technique ◽  
Online Signature ◽  
Online Signature Verification ◽  
Handwritten Signature

One of the main difficulties in designing online signature verification (OSV) system is to find the most distinctive features with high discriminating capabilities for the verification, particularly, with regard to the high variability which is inherent in genuine handwritten signatures, coupled with the possibility of skilled forgeries having close resemblance to the original counterparts. In this paper, we proposed a systematic approach to online signature verification through the use of multilayer perceptron (MLP) on a subset of principal component analysis (PCA) features. The proposed approach illustrates a feature selection technique on the usually discarded information from PCA computation, which can be significant in attaining reduced error rates. The experiment is performed using 4000 signature samples from SIGMA database, which yielded a false acceptance rate (FAR) of 7.4% and a false rejection rate (FRR) of 6.4%.

scholarly journals Online Signature Verification: To What Extent Should a Classifier be Trusted in?

2017 ◽  
Vol 20 (2) ◽  
Author(s):  
Marianela Parodi ◽  
Juan C. Gómez
Keyword(s):  
Signature Verification ◽  
Support Vector ◽  
Main Concern ◽  
Score Level Fusion ◽  
Feature Sets ◽  
Belief Function Theory ◽  
Online Signature ◽  
Online Signature Verification ◽  
Level Fusion ◽  
Fusion Approach

To select the best features to model the signatures is one of the major challenges in the field of online signature verification. To combine different feature sets, selected by different criteria, is a useful technique to address this problem. In this line, the analysis of different features and their discriminative power has been researchers’ main concern, paying less attention to the way in which the different kind of features are combined. Moreover, the fact that conflicting results may appear when several classifiers are being used, has rarely been taken into account. In this paper, a score level fusion scheme is proposed to combine three different and meaningful feature sets, viz., an automatically selected feature set, a feature set relevant to Forensic Handwriting Experts (FHEs), and a global feature set. The score level fusion is performed within the framework of the Belief Function Theory (BFT), in order to address the problem of the conflicting results appearing when multiple classifiers are being used. Two different models, namely, the Denoeux and the Appriou models, are used to embed the problem within this framework, where the fusion is performed resorting to two well-known combination rules, namely, the Dempster-Shafer (DS) and the Proportional Conflict Redistribution (PCR5) one. In order to analyze the robustness of the proposed score level fusion approach, the combination is performed for the same verification system using two different classification techniques, namely, Ramdon Forests (RF) and Support Vector Machines (SVM). Experimental results, on a publicly available database, show that the proposed score level fusion approach allows the system to have a very good trade-off between verification results and reliability.

scholarly journals Online Signature Verification: State of the art

2005 ◽  
Vol 4 (2) ◽  
pp. 664-678 ◽  
Author(s):  
Ibrahim El-Henawy ◽  
Magdy Rashad ◽  
Omima Nomir ◽  
Kareem Ahmed
Keyword(s):  
State Of The Art ◽  
User Authentication ◽  
Cost Effective ◽  
The State ◽  
Signature Verification ◽  
Stroke Length ◽  
Online Signature ◽  
Online Signature Verification ◽  
Dynamic Signature ◽  
The Relationship

online or Dynamic signature verification (DSV) is one of the most acceptable, intuitive, fast and cost effective tool for user authentication. DSV uses some dynamics like speed, pressure, directions, stroke length and pen-ups/pen-downs to verify the signer's identity. The state of the art in DSV is presented in this paper. several approaches for DSV are compared and the most influential techniques in this field are highlighted. We concentrate on the relationship between the verification approach used (the nature of the classifier) and the type of features that are used to represent the signature.

Chaotic Liquid State Machine

2015 ◽  
Vol 9 (4) ◽  
pp. 1-20
Author(s):  
Mario Antoine Aoun ◽  
Mounir Boukadoum
Keyword(s):  
Liquid State ◽  
State Machine ◽  
Spiking Neurons ◽  
Signature Verification ◽  
Time Varying ◽  
Plasticity Mechanism ◽  
Online Signature ◽  
Online Signature Verification ◽  
One Class Classifier ◽  
Classification Capability

The authors implement a Liquid State Machine composed from a pool of chaotic spiking neurons. Furthermore, a synaptic plasticity mechanism operates on the connection weights between the neurons inside the pool. A special feature of the system's classification capability is that it can learn the class of a set of time varying inputs when trained from positive examples only, thus, it is a one class classifier. To demonstrate the applicability of this novel neurocomputing architecture, the authors apply it for Online Signature Verification.

scholarly journals Online signature verification using neural network and pearson correlation features

2013 ◽  
Author(s):  
Vahab Iranmanesh ◽  
Sharifah Mumtazah Syed Ahmad ◽  
Wan Azizun Wan Adnan ◽  
Fahad Layth Malallah ◽  
Salman Yussof
Keyword(s):  
Neural Network ◽  
Pearson Correlation ◽  
Signature Verification ◽  
Online Signature ◽  
Online Signature Verification
Sign in / Sign up

Export Citation Format

Share Document