|Table of Contents|

Page Segmentation Research Based on Connective Region(PDF)

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2003年01期
Page:
16-19
Research Field:
Publishing date:

Info

Title:
Page Segmentation Research Based on Connective Region
Author(s):
GuoLi HuangYuanyuan YangJingyu
Department of Computer Science and Technology,NUST,Nanjing 210094
Keywords:
connect ive region dynamic clustering method page segmentat ion
PACS:
TP391.41
DOI:
-
Abstract:
Pag e segmentat ion is an important part of opt ical character recognit ion ( OCR) system, it is a necessary step in the process of transforming printed document s to elect ronic version. T his paper proposed a page segmentation based on connective reg ion. First, a dynamic clustering method w as used to get the smearing value, then the image w as smeared to get large connect ive regions, and the region posit ion information w as used to get the segmentation result . Experiment s show the method can be eff icient ly used in both simple rectang le layout and other complex layout such as non-Manhat tan layout .

References:

1 Bair d H S. Background structure in document images[ J] . I nternat ional Journal of Pattern Recogn-i tion and Ar tificial Intelligence, 1994, 8: 1 013~ 1 030.
2 王海琴. 基于投影和递归的版面理解算法[ J] . 模式识别与人工智能, 1997, 10( 2) : 118~ 126.
3 Jain A K, Bin Y. Document representatio n and its application to page decomposition[ J] . Patter n Recognition and Machine I ntelligence, 1998, 20( 3) : 294~ 308.
4 Adnan A, Ricky S. Page segmentation and classification utilizing bottom- up approach[ J] . International Journal of Image and Graphics, 2001, 1( 2) : 345~ 361.
5 Pavlidis T , Zhou J. Page segmentation and classification[ J] . Graphical Models and Imag e Processing , 1992, 54: 484~ 496.

Memo

Memo:
-
Last Update: 2013-03-17