This project evaluates an efficient approach for Offline Signature Verification using Machine Learning techniques. The proposed algorithm able to identify the original signature and forgery signatures in a skilled way. First going through the preprocessing phase the signature is made noise free and the region of interest portion of the signature is get selected. After preprocessing some useful features such as global features, region based geometrical features and robust features are used to extract for this algorithm. The training and testing phase is done using those extracted feature description vectors of the signatures with the help of machine learning techniques. A comparative study is performed between two well known supervised learning techniques, Support Vector Machine and Single Layer Perceptron in the verification phase of the proposed algorithm. This proposed algorithm yields percentage accuracy of 97.3% on average for Single layer perceptron and percentage accuracy of 76.16% on average for Support vector machine algorithm. Where Single Layer Perceptron provides an efficient result for this proposed approach.
This project evaluates an efficient approach for Offline Signature Verification using Machine Learning techniques. The proposed algorithm able to identify the original signature and forgery signatures in a skilled way. First going through the preprocessing phase the signature is made noise free and the region of interest portion of the signature…
damayant/Offline-Signature-Verification-Using-Machine-Learning-
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
This project evaluates an efficient approach for Offline Signature Verification using Machine Learning techniques. The proposed algorithm able to identify the original signature and forgery signatures in a skilled way. First going through the preprocessing phase the signature is made noise free and the region of interest portion of the signature…
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published