International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 53 - Issue 2 |
Published: September 2012 |
Authors: Yogendra Kumar Jain, Rupal S. Patil |
![]() |
Yogendra Kumar Jain, Rupal S. Patil . Offline Signature Verification using FMCN with GA based Optimization of Features. International Journal of Computer Applications. 53, 2 (September 2012), 33-39. DOI=10.5120/8396-2025
@article{ 10.5120/8396-2025, author = { Yogendra Kumar Jain,Rupal S. Patil }, title = { Offline Signature Verification using FMCN with GA based Optimization of Features }, journal = { International Journal of Computer Applications }, year = { 2012 }, volume = { 53 }, number = { 2 }, pages = { 33-39 }, doi = { 10.5120/8396-2025 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2012 %A Yogendra Kumar Jain %A Rupal S. Patil %T Offline Signature Verification using FMCN with GA based Optimization of Features%T %J International Journal of Computer Applications %V 53 %N 2 %P 33-39 %R 10.5120/8396-2025 %I Foundation of Computer Science (FCS), NY, USA
In recent years, along with extraordinary diffusion of internet and growing need of personal identification in many applications, signature verification is considered with interest. This paper proposed an offline signature verification method based on Genetic Algorithm and Fuzzy Min Max Neural Network Classifier with Compensatory Neuron. The proposed method is basically consists of two steps. At first step optimizing the features using genetic algorithm, and at second step signature recognition is done using Fuzzy Min Max Neural Network Classifier with Compensatory Neurons. The sample of signatures is used to represent a particular person. The sample signature is first preprocessed, and then features of the processed signature are extracted by using Krawtchouk moment. After feature extraction, these features are optimized by using genetic algorithm and finally optimized features are given to the classification phase for recognition. With this proposed method, we get the 98% accuracy in recognition and less time is required for classification with optimized features as compared to time required for classification without optimizing feature.