loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Rabiaa Zitouni 1 ; Hala Bezine 2 and Najet Arous 1

Affiliations: 1 Laboratory LR-SITI ENIT, University Tunis El Manar, B.P.37, 1002 Tunis, Tunisia ; 2 Laboratory REGIM ENIS, University Sfax, B.P.1173, 3038 Sfax, Tunisia

Keyword(s): Fuzzy Attributed Relational Graph, Graph Matching, Structural Pattern Recognition, Handwritten Graphs, Tree Search Method.

Abstract: In this research, we attempt to propose a novel graph-based approach for online handwritten character recognition. Unlike the most well-known online handwritten recognition methods, which are based on statistical representations, we set forward a new approach based on structural representation to overcome the inherent deformations of handwritten characters. An Attributed Relational Graph (ARG) is dedicated to allowing the direct labeling of nodes (strokes) and edges (relationships) of a graph to model the input character. Each node is characterized by a set of fuzzy membership degrees describing their properties (type, size). Fuzzy description is invested in order to guarantee more robustness against uncertainty, ambiguity and vagueness. ARGs edges stand for spatial relationships between different strokes. At a subsequent stage, a tree-search based optimal matching algorithm is explored, which allows the search for character structures i.e the minimum cost of nodes. Experiments perfo rmed on ADAB and IRONOFF datasets, reveal promising results. In particular, the comparison with the state of the art demonstrates the significance of the proposed system. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.12.154.133

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Zitouni, R.; Bezine, H. and Arous, N. (2020). Graph based Method for Online Handwritten Character Recognition. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - GRAPP; ISBN 978-989-758-402-2; ISSN 2184-4321, SciTePress, pages 263-270. DOI: 10.5220/0008956602630270

@conference{grapp20,
author={Rabiaa Zitouni. and Hala Bezine. and Najet Arous.},
title={Graph based Method for Online Handwritten Character Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - GRAPP},
year={2020},
pages={263-270},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008956602630270},
isbn={978-989-758-402-2},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - GRAPP
TI - Graph based Method for Online Handwritten Character Recognition
SN - 978-989-758-402-2
IS - 2184-4321
AU - Zitouni, R.
AU - Bezine, H.
AU - Arous, N.
PY - 2020
SP - 263
EP - 270
DO - 10.5220/0008956602630270
PB - SciTePress