DMCA
Document Layout Structure Extraction Using Bounding Boxes of Different Entities (1996)
| Venue: | Proc. Workshop on Applications of Computer Vision |
| Citations: | 10 - 2 self |
BibTeX
@INPROCEEDINGS{Liang96documentlayout,
author = {J. Liang and J. Ha and R. M. Haralick and I. T. Phillips},
title = {Document Layout Structure Extraction Using Bounding Boxes of Different Entities},
booktitle = {Proc. Workshop on Applications of Computer Vision},
year = {1996},
pages = {278--283}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
This paper presents an efficient technique for document page layout structure extraction and classification by analyzing the spatial configuration of the bounding boxes of different entities on the given image. The algorithm segments an image into a list of homogeneous zones. The classification algorithm labels each zone as text, table, line-drawing, halftone, ruling, or noise. The text-lines and words are extracted within text zones and neighboring text-lines are merged to form text-blocks. The tabular structure is further decomposed into row and column items. Finally, the document layout hierarchy is produced from these extracted entities. 1 Introduction The goal of document understanding is to convert existing paper documents into a machine readable form. It involves estimating the rotation skew of each document page, determining the geometric page layout, labeling blocks as text, math, figure, table, halftone, etc., determining the text of text blocks through an OCR system, deter...
Keyphrases
different entity classification algorithm label document page layout structure extraction spatial configuration paper document ocr system efficient technique document understanding document page tabular structure machine readable form extracted entity homogeneous zone text zone geometric page layout column item document layout hierarchy text block rotation skew bounding box
