Detection of curved text path based on the fuzzy curve-tracing (FCT) algorithm

Artistic documents often contain text along curved paths. Commonly used computer algorithms for text extraction, which only deal with text along straight lines, cannot be employed to analyze these artistic documents. In this paper, we solve this problem using the fuzzy curve-tracing algorithm. In ou...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:6th Document Analysis and Recognition: Proceedings of the International Conference 2001: Seattle, WA S. 266 - 270
1. Verfasser: Hong Yan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 2001
Schlagworte:
Algorithm design and analysis
Character recognition
Clustering algorithms
Data mining
Graphics
Histograms
Image analysis
Iterative algorithms
Optical character recognition software
Text analysis
ISBN:9780769512631, 0769512631
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Artistic documents often contain text along curved paths. Commonly used computer algorithms for text extraction, which only deal with text along straight lines, cannot be employed to analyze these artistic documents. In this paper, we solve this problem using the fuzzy curve-tracing algorithm. In our method, the character pixels are grouped based on the fuzzy c-means algorithm to reduce the amount of data. Then the cluster centers are connected to form the initial curve representing the text path. Finally the character pixels are clustered again under the constraint that the path must be smooth. Results from several experiments are presented to show the effectiveness of our method.
ISBN:9780769512631
0769512631
DOI:10.1109/ICDAR.2001.953796