Texture feature column scheme for single‐ and multi‐script writer identification
Abstract Identification of writers from images of handwriting is an interesting research problem in the handwriting recognition community. Application of image analysis and machine learning techniques to this problem allows development of computerised solutions which can facilitate forensic experts...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-03-01
|
| Series: | IET Biometrics |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/bme2.12010 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832558651121860608 |
|---|---|
| author | Faycel Abbas Abdeljalil Gattal Chawki Djeddi Imran Siddiqi Ameur Bensefia Kamel Saoudi |
| author_facet | Faycel Abbas Abdeljalil Gattal Chawki Djeddi Imran Siddiqi Ameur Bensefia Kamel Saoudi |
| author_sort | Faycel Abbas |
| collection | DOAJ |
| description | Abstract Identification of writers from images of handwriting is an interesting research problem in the handwriting recognition community. Application of image analysis and machine learning techniques to this problem allows development of computerised solutions which can facilitate forensic experts in reducing the search space against a questioned document. This article investigates the effectiveness of textural measures in characterising the writer of a handwritten document. A novel descriptor by crossing the local binary patterns (LBP) with different configurations that allows capturing the local textural information in handwriting using a column histogram is introduced. The representation is enriched with the oriented Basic Image Features (oBIFs) column histogram. Support vector machine (SVM) is employed as the classifier, and the experimental study is carried out on five different datasets in single as well as multi‐script evaluation scenarios. Multi‐script evaluations allow evaluating the hypothesis that writers share common characteristics across multiple scripts and the reported results validate the effectiveness of textural measures in capturing this script‐independent, writer‐specific information. |
| format | Article |
| id | doaj-art-4e7fb8a98a9140d3b68c33f2d835ec21 |
| institution | Kabale University |
| issn | 2047-4938 2047-4946 |
| language | English |
| publishDate | 2021-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Biometrics |
| spelling | doaj-art-4e7fb8a98a9140d3b68c33f2d835ec212025-02-03T01:31:55ZengWileyIET Biometrics2047-49382047-49462021-03-0110217919310.1049/bme2.12010Texture feature column scheme for single‐ and multi‐script writer identificationFaycel Abbas0Abdeljalil Gattal1Chawki Djeddi2Imran Siddiqi3Ameur Bensefia4Kamel Saoudi5LIMPAF Laboratory Akli Mohand Oulhadj University Bouira AlgeriaDepartment of Mathematics and Computer Science Larbi Tebessi University Tebessa AlgeriaDepartment of Mathematics and Computer Science Larbi Tebessi University Tebessa AlgeriaVision & Learning Lab Bahria University Islamabad PakistanHigher Colleges of Technology CIS Division Abu Dhabi UAEDepartment of Electrical Engineering Akli Mohand Oulhadj University Bouira AlgeriaAbstract Identification of writers from images of handwriting is an interesting research problem in the handwriting recognition community. Application of image analysis and machine learning techniques to this problem allows development of computerised solutions which can facilitate forensic experts in reducing the search space against a questioned document. This article investigates the effectiveness of textural measures in characterising the writer of a handwritten document. A novel descriptor by crossing the local binary patterns (LBP) with different configurations that allows capturing the local textural information in handwriting using a column histogram is introduced. The representation is enriched with the oriented Basic Image Features (oBIFs) column histogram. Support vector machine (SVM) is employed as the classifier, and the experimental study is carried out on five different datasets in single as well as multi‐script evaluation scenarios. Multi‐script evaluations allow evaluating the hypothesis that writers share common characteristics across multiple scripts and the reported results validate the effectiveness of textural measures in capturing this script‐independent, writer‐specific information.https://doi.org/10.1049/bme2.12010feature extractionhandwriting recognitionhandwritten character recognitionimage texturelearning (artificial intelligence)support vector machines |
| spellingShingle | Faycel Abbas Abdeljalil Gattal Chawki Djeddi Imran Siddiqi Ameur Bensefia Kamel Saoudi Texture feature column scheme for single‐ and multi‐script writer identification IET Biometrics feature extraction handwriting recognition handwritten character recognition image texture learning (artificial intelligence) support vector machines |
| title | Texture feature column scheme for single‐ and multi‐script writer identification |
| title_full | Texture feature column scheme for single‐ and multi‐script writer identification |
| title_fullStr | Texture feature column scheme for single‐ and multi‐script writer identification |
| title_full_unstemmed | Texture feature column scheme for single‐ and multi‐script writer identification |
| title_short | Texture feature column scheme for single‐ and multi‐script writer identification |
| title_sort | texture feature column scheme for single and multi script writer identification |
| topic | feature extraction handwriting recognition handwritten character recognition image texture learning (artificial intelligence) support vector machines |
| url | https://doi.org/10.1049/bme2.12010 |
| work_keys_str_mv | AT faycelabbas texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification AT abdeljalilgattal texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification AT chawkidjeddi texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification AT imransiddiqi texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification AT ameurbensefia texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification AT kamelsaoudi texturefeaturecolumnschemeforsingleandmultiscriptwriteridentification |