Page segmentation and identification for intelligent signal processing

Kuo Chin Fan, Liang Shen Wang, Yuan Kai Wang

Research output: Contribution to journalArticlepeer-review

12 Scopus citations

Abstract

Document analysis plays an important role in office automation, especially in intelligent signal processing. In this paper, we propose an intelligent document analysis system to achieve the document segmentation and identification goal. The proposed system consists of two modules: block segmentation and block identification. In our approach, we first segment a document into several non-overlapping blocks by utilizing a novel recursive segmentation technique, then extract the features embedded in each segmented block. Two kinds of features, connectivity histogram and multiresolution features, are extracted. The features are verified to be effective in characterizing document blocks. Last, a two-layer perceptron is adopted in the identification module to determine the identity of the considered block. Experiments with a wide varity of documents verify the feasibility of our approach.

Original languageEnglish
Pages (from-to)329-346
Number of pages18
JournalSignal Processing
Volume45
Issue number3
DOIs
StatePublished - Sep 1995

Keywords

  • Alternative tree representation
  • Connectivity histogram
  • Document analysis
  • Multi-resolution features

Fingerprint

Dive into the research topics of 'Page segmentation and identification for intelligent signal processing'. Together they form a unique fingerprint.

Cite this