Title :
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
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;
Conference_Titel :
Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on
Conference_Location :
Tours
Print_ISBN :
978-1-4799-3243-6
DOI :
10.1109/DAS.2014.39
