Multi-phase Offline Signature Verification System Using Deep Convolutional Generative Adversarial Networks

2016 ◽  
Author(s):  
Zehua Zhang ◽  
Xiangqian Liu ◽  
Yan Cui
Keyword(s):  
Signature Verification ◽  
Generative Adversarial Networks ◽  
Adversarial Networks ◽  
Verification System ◽  
Offline Signature Verification ◽  
Multi Phase

FREEMAN CHAIN CODE AS REPRESENTATION IN OFFLINE SIGNATURE VERIFICATION SYSTEM

2016 ◽  
Vol 78 (8-2) ◽  
Author(s):  
Aini Najwa Azmi ◽  
Dewi Nasien ◽  
Azurah Abu Samah
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Rejection Rate ◽  
Data Representation ◽  
Signature Verification ◽  
Global Features ◽  
Chain Code ◽  
Verification System ◽  
Offline Signature Verification ◽  
Handwritten Signature

Over recent years, there has been an explosive growth of interest in the pattern recognition. For example, handwritten signature is one of human biometric that can be used in many areas in terms of access control and security. However, handwritten signature is not a uniform characteristic such as fingerprint, iris or vein. It may change to several factors; mood, environment and age. Signature Verification System (SVS) is a part of pattern recognition that can be a solution for such situation. The system can be decomposed into three stages: data acquisition and preprocessing, feature extraction and verification. This paper presents techniques for SVS that uses Freeman chain code (FCC) as data representation. In the first part of feature extraction stage, the FCC was extracted by using boundary-based style on the largest contiguous part of the signature images. The extracted FCC was divided into four, eight or sixteen equal parts. In the second part of feature extraction, six global features were calculated. Finally, verification utilized k-Nearest Neighbour (k-NN) to test the performance. MCYT bimodal database was used in every stage in the system. Based on our systems, the best result achieved was False Rejection Rate (FRR) 14.67%, False Acceptance Rate (FAR) 15.83% and Equal Error Rate (EER) 0.43% with shortest computation, 7.53 seconds and 47 numbers of features.

scholarly journals Signature Extraction and Recognition from Bank Cheque ImageSignature Extraction and Recognition from Bank Cheque Image

2019 ◽  
Vol 9 (2) ◽  
pp. 2211-2214
Keyword(s):  
Research Problem ◽  
Gaussian Mixture ◽  
Signature Verification ◽  
Classification Algorithms ◽  
Signature Extraction ◽  
Performance Accuracy ◽  
Verification System ◽  
Offline Signature Verification ◽  
Matching Models ◽  
Verification Model

Automatic signature extraction and recognition from document images is an open research problem. Signature verification is of two types; static and dynamic, and has two approaches; writer dependent and writer independent. Signature verification system in case of bank cheque image should essentially be an error prone system to elude the fraudulent transactions. In this work, a three layer signature verification system is proposed, which is writer independent and offline signature verification system. Graphometrical and FAST features are extracted from the signature images and are given as inputs to the classification algorithms. The proposed signature verification model is a combination of three classification algorithms; artificial neural network, Gaussian mixture model and image matching models, to circumvent the fraudulent transactions. The overall performance accuracy of proposed process is 99%.

Sign in / Sign up

Export Citation Format

Share Document