Marginal noise removal of document images

Kuo Chin Fan, Yuan Kai Wang, Tsann Ran Lay

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

Marginal noise is a common phenomenon in document analysis which results from the scanning of thick documents or skew documents. It usually appears in the front of a large and dark region around the margin of document images. Marginal noise might cover meaningful document objects. The overlapping of marginal noise with meaningful objects makes it difficult to perform the task of segmentation and recognition of document objects. This paper proposes a novel approach to remove marginal noise. The proposed approach consists of two steps which are marginal noise detection and marginal noise deletion. Marginal noise detection will reduce an original document image into a smaller image, and then find marginal noise regions according to the shape, length, and location of the splitted blocks. After the detection of marginal noise regions, removal is performed. Experimenting with a wide variety' of test samples reveals the feasibility and effectiveness of our proposed approach in removing marginal noises.

Original languageEnglish
Title of host publicationProceedings - 6th International Conference on Document Analysis and Recognition, ICDAR 2001
PublisherIEEE Computer Society
Pages317-321
Number of pages5
ISBN (Electronic)0769512631, 0769512631, 0769512631
DOIs
StatePublished - 2001
Event6th International Conference on Document Analysis and Recognition, ICDAR 2001 - Seattle, United States
Duration: 10 Sep 200113 Sep 2001

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume2001-January
ISSN (Print)1520-5363

Conference

Conference6th International Conference on Document Analysis and Recognition, ICDAR 2001
Country/TerritoryUnited States
CitySeattle
Period10/09/0113/09/01

Fingerprint

Dive into the research topics of 'Marginal noise removal of document images'. Together they form a unique fingerprint.

Cite this