Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion
This paper presents a user-optimized multiple classifiers approach for an offline signature verification system. Local features are extracted from a sliding window that slides across the signature images. Multiple HMM-based classifiers are used for the soft decisions, where each classifier is train...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Scottish Group
2013
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/28817/ http://psasir.upm.edu.my/id/eprint/28817/1/Personalized%20offline%20signature%20verification%20using%20multiple%20HMM.pdf |
| _version_ | 1848846221205045248 |
|---|---|
| author | Syed Ahmad Abdul Rahman, Sharifah Mumtazah Ahmad, Abdul Rahim Shakil, Asma Muhamed Balbed, Mustafa Agil Wan Adnan, Wan Azizun |
| author_facet | Syed Ahmad Abdul Rahman, Sharifah Mumtazah Ahmad, Abdul Rahim Shakil, Asma Muhamed Balbed, Mustafa Agil Wan Adnan, Wan Azizun |
| author_sort | Syed Ahmad Abdul Rahman, Sharifah Mumtazah |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | This paper presents a user-optimized multiple classifiers approach for an offline signature verification system. Local features are extracted from a sliding window that
slides across the signature images. Multiple HMM-based classifiers are used for the soft decisions, where each classifier is trained on a particular feature. In this
work, we select the two best features to represent each user via ANOVA statistical analysis. A fuzzy decision fusion system that is tuned using SOM based clustering technique is used to combine the soft decisions from the selected HMM classifiers in producing the final verification output. The system has been tested on SIGMA signature database which is a collection of over 6000 genuine and 2000 forged signatures. Results show that our
personalized multiple classifiers approach out performs common single classifier systems. |
| first_indexed | 2025-11-15T08:59:16Z |
| format | Article |
| id | upm-28817 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T08:59:16Z |
| publishDate | 2013 |
| publisher | Scottish Group |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-288172016-02-02T01:21:24Z http://psasir.upm.edu.my/id/eprint/28817/ Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion Syed Ahmad Abdul Rahman, Sharifah Mumtazah Ahmad, Abdul Rahim Shakil, Asma Muhamed Balbed, Mustafa Agil Wan Adnan, Wan Azizun This paper presents a user-optimized multiple classifiers approach for an offline signature verification system. Local features are extracted from a sliding window that slides across the signature images. Multiple HMM-based classifiers are used for the soft decisions, where each classifier is trained on a particular feature. In this work, we select the two best features to represent each user via ANOVA statistical analysis. A fuzzy decision fusion system that is tuned using SOM based clustering technique is used to combine the soft decisions from the selected HMM classifiers in producing the final verification output. The system has been tested on SIGMA signature database which is a collection of over 6000 genuine and 2000 forged signatures. Results show that our personalized multiple classifiers approach out performs common single classifier systems. Scottish Group 2013-02 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/28817/1/Personalized%20offline%20signature%20verification%20using%20multiple%20HMM.pdf Syed Ahmad Abdul Rahman, Sharifah Mumtazah and Ahmad, Abdul Rahim and Shakil, Asma and Muhamed Balbed, Mustafa Agil and Wan Adnan, Wan Azizun (2013) Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion. Scottish Journal of Arts, Social Sciences and Scientific Studies, 9 (1). pp. 148-165. ISSN 2047-1278 http://scottishjournal.co.uk/paper/SJASS_Vol.9_No.1.pdf |
| spellingShingle | Syed Ahmad Abdul Rahman, Sharifah Mumtazah Ahmad, Abdul Rahim Shakil, Asma Muhamed Balbed, Mustafa Agil Wan Adnan, Wan Azizun Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title | Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title_full | Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title_fullStr | Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title_full_unstemmed | Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title_short | Personalized offline signature verification using multiple HMM-classifiers and SOM-fuzzy decision fusion |
| title_sort | personalized offline signature verification using multiple hmm-classifiers and som-fuzzy decision fusion |
| url | http://psasir.upm.edu.my/id/eprint/28817/ http://psasir.upm.edu.my/id/eprint/28817/ http://psasir.upm.edu.my/id/eprint/28817/1/Personalized%20offline%20signature%20verification%20using%20multiple%20HMM.pdf |