Arabic Handwritten Signature Identification
This paper proposes a new intelligent off-line Arabic handwritten signature identification and verification system based on texture analysis. The system uses the texture as feature and back propagation neural network as classifier. The signature image is preprocessed by several operations (Noise rem...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
Mosul University
2013-09-01
|
| Series: | Al-Rafidain Journal of Computer Sciences and Mathematics |
| Subjects: | |
| Online Access: | https://csmj.mosuljournals.com/article_163525_3bfd7b9bab5c5dc4cd43e0636f502352.pdf |
| _version_ | 1818208491283677184 |
|---|---|
| author | Alaa Taqa Hanaa Mahmood |
| author_facet | Alaa Taqa Hanaa Mahmood |
| author_sort | Alaa Taqa |
| collection | DOAJ |
| description | This paper proposes a new intelligent off-line Arabic handwritten signature identification and verification system based on texture analysis. The system uses the texture as feature and back propagation neural network as classifier. The signature image is preprocessed by several operations (Noise removal, Conversion of the signature image to binary image, Finding outer rectangle, Thinning and Size normalization) then the fractal number and co-occurrence matrix are computed to estimate texture features. In this work, two off-line Arabic handwritten signature identification systems are constructed. The first one uses the nearest Euclidean distance, while the other uses back propagation neural network. The paper analyzes and compares the results obtained from the two proposed systems to show the robustness level of the proposed intelligence system. Furthermore, the proposed system was tested by using<strong> Genuine</strong> signatures and has achieved a CCR (Correct Classification Rate) of 100% in best cases, while it was tested by using <strong>Forged</strong> signatures it has achieved a CRR approximated to 96.3% in best cases. The experimental results showed that the proposed system is efficient and competent with other state-of-the-art texture-based off-line signature identification systems. |
| first_indexed | 2024-12-12T04:45:39Z |
| format | Article |
| id | doaj.art-71e5279c42504930acaf4f9e98e9c932 |
| institution | Directory Open Access Journal |
| issn | 1815-4816 2311-7990 |
| language | Arabic |
| last_indexed | 2024-12-12T04:45:39Z |
| publishDate | 2013-09-01 |
| publisher | Mosul University |
| record_format | Article |
| series | Al-Rafidain Journal of Computer Sciences and Mathematics |
| spelling | doaj.art-71e5279c42504930acaf4f9e98e9c9322022-12-22T00:37:38ZaraMosul UniversityAl-Rafidain Journal of Computer Sciences and Mathematics1815-48162311-79902013-09-01103375410.33899/csmj.2013.163525163525Arabic Handwritten Signature IdentificationAlaa Taqa0Hanaa Mahmood1College of Education University of Mosul, Mosul, IraqCollege of Education University of Mosul, Mosul, IraqThis paper proposes a new intelligent off-line Arabic handwritten signature identification and verification system based on texture analysis. The system uses the texture as feature and back propagation neural network as classifier. The signature image is preprocessed by several operations (Noise removal, Conversion of the signature image to binary image, Finding outer rectangle, Thinning and Size normalization) then the fractal number and co-occurrence matrix are computed to estimate texture features. In this work, two off-line Arabic handwritten signature identification systems are constructed. The first one uses the nearest Euclidean distance, while the other uses back propagation neural network. The paper analyzes and compares the results obtained from the two proposed systems to show the robustness level of the proposed intelligence system. Furthermore, the proposed system was tested by using<strong> Genuine</strong> signatures and has achieved a CCR (Correct Classification Rate) of 100% in best cases, while it was tested by using <strong>Forged</strong> signatures it has achieved a CRR approximated to 96.3% in best cases. The experimental results showed that the proposed system is efficient and competent with other state-of-the-art texture-based off-line signature identification systems.https://csmj.mosuljournals.com/article_163525_3bfd7b9bab5c5dc4cd43e0636f502352.pdftexture analysisback propagation artificial neural networkoffline signature identification and verification |
| spellingShingle | Alaa Taqa Hanaa Mahmood Arabic Handwritten Signature Identification Al-Rafidain Journal of Computer Sciences and Mathematics texture analysis back propagation artificial neural network offline signature identification and verification |
| title | Arabic Handwritten Signature Identification |
| title_full | Arabic Handwritten Signature Identification |
| title_fullStr | Arabic Handwritten Signature Identification |
| title_full_unstemmed | Arabic Handwritten Signature Identification |
| title_short | Arabic Handwritten Signature Identification |
| title_sort | arabic handwritten signature identification |
| topic | texture analysis back propagation artificial neural network offline signature identification and verification |
| url | https://csmj.mosuljournals.com/article_163525_3bfd7b9bab5c5dc4cd43e0636f502352.pdf |
| work_keys_str_mv | AT alaataqa arabichandwrittensignatureidentification AT hanaamahmood arabichandwrittensignatureidentification |