Improvement of authorship invarianceness for individuality representation in writer identification
Writer Identification (WI) is one of the areas in pattern recognition that have created a center of attention for many researchers to work in. Recently, its main focus is in forensics and biometric application, e.g. writing style can be used as biometric features for authenticating individuality uni...
Main Authors: | , , |
---|---|
Format: | Article |
Published: |
Institute of Information and Computer Technology ASCR; Faculty of Transport, Czech Polytechnic University, Prague
2010
|
Subjects: |
_version_ | 1796856162556051456 |
---|---|
author | Shamsuddin, Siti Mariyam Muda, Azah Kamilah Abraham, Ajith |
author_facet | Shamsuddin, Siti Mariyam Muda, Azah Kamilah Abraham, Ajith |
author_sort | Shamsuddin, Siti Mariyam |
collection | ePrints |
description | Writer Identification (WI) is one of the areas in pattern recognition that have created a center of attention for many researchers to work in. Recently, its main focus is in forensics and biometric application, e.g. writing style can be used as biometric features for authenticating individuality uniqueness. Existing works in WI concentrate on feature extraction and classi?cation task in order to identify the handwritten authorship. However, additional steps need to be per- formed in order to have a better representation of input prior to the classi?cation task. Features extracted from the feature extraction task for a writer are in vari- ous representations, which degrades the classi?cation performance. This paper will discuss this additional process that can transform the various representations into a better representation of individual features for Individuality of Handwriting, in order to improve the performance of identification in WI. |
first_indexed | 2024-03-05T18:39:22Z |
format | Article |
id | utm.eprints-26212 |
institution | Universiti Teknologi Malaysia - ePrints |
last_indexed | 2024-03-05T18:39:22Z |
publishDate | 2010 |
publisher | Institute of Information and Computer Technology ASCR; Faculty of Transport, Czech Polytechnic University, Prague |
record_format | dspace |
spelling | utm.eprints-262122018-11-30T06:23:09Z http://eprints.utm.my/26212/ Improvement of authorship invarianceness for individuality representation in writer identification Shamsuddin, Siti Mariyam Muda, Azah Kamilah Abraham, Ajith QA75 Electronic computers. Computer science Writer Identification (WI) is one of the areas in pattern recognition that have created a center of attention for many researchers to work in. Recently, its main focus is in forensics and biometric application, e.g. writing style can be used as biometric features for authenticating individuality uniqueness. Existing works in WI concentrate on feature extraction and classi?cation task in order to identify the handwritten authorship. However, additional steps need to be per- formed in order to have a better representation of input prior to the classi?cation task. Features extracted from the feature extraction task for a writer are in vari- ous representations, which degrades the classi?cation performance. This paper will discuss this additional process that can transform the various representations into a better representation of individual features for Individuality of Handwriting, in order to improve the performance of identification in WI. Institute of Information and Computer Technology ASCR; Faculty of Transport, Czech Polytechnic University, Prague 2010 Article PeerReviewed Shamsuddin, Siti Mariyam and Muda, Azah Kamilah and Abraham, Ajith (2010) Improvement of authorship invarianceness for individuality representation in writer identification. Neural Network World, 20 (3). 371 - 387. ISSN 1210-0552 http://www.softcomputing.net/nnw2010_3.pdf |
spellingShingle | QA75 Electronic computers. Computer science Shamsuddin, Siti Mariyam Muda, Azah Kamilah Abraham, Ajith Improvement of authorship invarianceness for individuality representation in writer identification |
title | Improvement of authorship invarianceness for individuality representation in writer identification |
title_full | Improvement of authorship invarianceness for individuality representation in writer identification |
title_fullStr | Improvement of authorship invarianceness for individuality representation in writer identification |
title_full_unstemmed | Improvement of authorship invarianceness for individuality representation in writer identification |
title_short | Improvement of authorship invarianceness for individuality representation in writer identification |
title_sort | improvement of authorship invarianceness for individuality representation in writer identification |
topic | QA75 Electronic computers. Computer science |
work_keys_str_mv | AT shamsuddinsitimariyam improvementofauthorshipinvariancenessforindividualityrepresentationinwriteridentification AT mudaazahkamilah improvementofauthorshipinvariancenessforindividualityrepresentationinwriteridentification AT abrahamajith improvementofauthorshipinvariancenessforindividualityrepresentationinwriteridentification |