Recognition-based segmentation of Nom characters from body text regions of stele images using area Voronoi diagram - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2009

Recognition-based segmentation of Nom characters from body text regions of stele images using area Voronoi diagram

Abstract

Segmentation of Nom characters from body text regions of stele images is a challenging problem due to the confusing spatial distribution of the connected components composing these characters. In this paper, for each vertical text line, area Voronoi diagram is employed to represent the neighborhood of the connected components and Voronoi edges are used as nonlinear segmentation hypotheses. Characters are then segmented by selecting appropriate adjacent Voronoi regions. For this purpose, we utilize the information about the horizontal overlap of connected components and the recognition distances of candidate characters provided by an OCR engine. Experimental results show that the proposed method is highly accurate and robust to various types of stele.
Fichier principal
Vignette du fichier
CAIP2009.pdf (567.07 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00430806 , version 1 (10-11-2009)

Identifiers

Cite

Thai V. Hoang, Salvatore Tabbone, Ngoc-Yen Pham. Recognition-based segmentation of Nom characters from body text regions of stele images using area Voronoi diagram. International Conference on Computer Analysis of Images and Patterns - CAIP'2009, Sep 2009, Munster, Germany. pp.205-212, ⟨10.1007/978-3-642-03767-2⟩. ⟨inria-00430806⟩
497 View
366 Download

Altmetric

Share

Gmail Facebook X LinkedIn More