A Typed and Handwritten Text Block Segmentation System for Heterogeneous and Complex Documents

Author

Barlas, Panagiotis ; Adam, S. ; Chatelain, C. ; Paquet, T.

Author_Institution

Lab. LITIS, Univ. de Rouen, Rouen, France

fYear

2014

fDate

7-10 April 2014

Firstpage

46

Lastpage

50

Abstract

This paper presents a Document Image Analysis (DIA) system able to extract homogeneous typed and handwritten text regions from complex layout documents of various types. The method is based on two connected component classification stages that successively discriminate text/non text and typed/handwritten shapes, followed by an original block segmentation method based on white rectangles detection. We present the results obtained by the system during the first competition round of the MAURDOR campaign.

Keywords

document image processing; feature extraction; image classification; image segmentation; object detection; text detection; DIA system; MAURDOR campaign; block segmentation method; complex documents; complex layout documents; component classification; document image analysis; handwritten shapes; handwritten text block segmentation system; handwritten text regions extraction; heterogeneous documents; homogeneous typed regions extraction; typed shapes; white rectangle detection; Context; Feature extraction; Image segmentation; Measurement; Shape; Text analysis; Text recognition; Document Image Analysis; MAURDOR campaign; text block segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on

Conference_Location

Tours

Print_ISBN

978-1-4799-3243-6

Type

conf

DOI

10.1109/DAS.2014.39

Filename

6830967