A set of geometrical features for writer identification

Authors:
Abdelâali Hassaïne;Somaya Al-Maadeed;Ahmed Bouridane
Affiliations:
Computer Science and Engineering Department, College of Engineering, Qatar University, Doha, Qatar;Computer Science and Engineering Department, College of Engineering, Qatar University, Doha, Qatar;CEIS, Northumbria University, Newcastle upon Tyne, UK
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part V
Year:
2012

Citing 11
Cited 0

A fast parallel algorithm for thinning digital patterns

Communications of the ACM
Random Forests

Machine Learning
Estimation of Curvature and Tangent Direction by Median Filtered Differencing

ICIAP '95 Proceedings of the 8th International Conference on Image Analysis and Processing
Defining Writer's Invariants to Adapt the Recognition Task

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Ink Texture Analysis for Writer Identification

IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
Individuality of Handwriting: A Validation Study

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Writer Identification Using Text Line Based Features

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Text-Independent Writer Identification and Verification Using Textural and Allographic Features

IEEE Transactions on Pattern Analysis and Machine Intelligence
Writer identification using edge-based directional probability distribution features for arabic words

AICCSA '08 Proceedings of the 2008 IEEE/ACS International Conference on Computer Systems and Applications
Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features

Pattern Recognition
The ICDAR2011 Arabic Writer Identification Contest

ICDAR '11 Proceedings of the 2011 International Conference on Document Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Writer identification is an important field in the forensic document examination. We propose in this paper a set of geometrical features that makes it possible to characterize writers. They include directions, curvatures and tortuosities. We show how these features can be combined with edge based directional features as well as chain code based features. Evaluation of the method is performed on the IAM handwriting database.