DocumentCode :
594721
Title :
A robust hybrid approach for text line segmentation in historical documents
Author :
Clausner, C. ; Antonacopoulos, A. ; Pletschacher, S.
Author_Institution :
Pattern Recognition & Image Anal. (PRImA) Res. Lab., Univ. of Salford, Salford, UK
fYear :
2012
fDate :
11-15 Nov. 2012
Firstpage :
335
Lastpage :
338
Abstract :
Large-scale digitisation of historical documents demands robust methods that cope with the presence of frequent distortions and noisy artefacts. This paper presents a hybrid text line segmentation method that uses a novel data structure and a rule base to combine the strengths of top-down and bottom-up approaches while minimising their weaknesses. The effectiveness of the proposed approach has been methodically evaluated in the context of large-scale digitisation using a standardised framework. Results on a diverse dataset show improved performance over top-down and bottom-up approaches as well as over a leading commercially available system.
Keywords :
data structures; distortion; image segmentation; knowledge based systems; text analysis; bottom-up approach; data structure; digitisation; distortion; historical document; hybrid text line segmentation method; noisy artefacts; rule base; top-down approach; Data structures; Image segmentation; Layout; Libraries; Merging; Noise; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
ISSN :
1051-4651
Print_ISBN :
978-1-4673-2216-4
Type :
conf
Filename :
6460140
Link To Document :
بازگشت