Clutter Noise Removal in Binary Document Images

Author

Agrawal, Mudit ; Doermann, David

Author_Institution

Inst. of Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA

fYear

2009

Firstpage

556

Lastpage

560

Abstract

The paper presents a clutter detection and removal algorithm for complex document images. The distance transform based approach is independent of clutter´s position, size, shape and connectivity with text. Features are based on a residual image obtained by analysis of the distance transform and clutter elements, if present, are identified with an SVM classifier. Removal is restrictive, so text attached to the clutter is not deleted in the process. The method was tested on a collection of degraded and noisy, machine-printed and handwritten Arabic and English text documents. Results show pixel-level accuracies of 97.5% and 95% for clutter detection and removal respectively. This approach was also extended with a noise detection and removal model for documents having a mix of clutter and salt-n-pepper noise.

Keywords

document image processing; image classification; image denoising; support vector machines; text analysis; SVM classifier; binary document image; clutter noise removal; distance transform; noise detection; text analysis; Algorithm design and analysis; Background noise; Educational institutions; Image analysis; Image recognition; Ink; Multi-stage noise shaping; Noise shaping; Shape; Text analysis; clutter; ink blobs; marginal noise; noise removal;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on

Conference_Location

Barcelona

ISSN

1520-5363

Print_ISBN

978-1-4244-4500-4

Electronic_ISBN

1520-5363

Type

conf

DOI

10.1109/ICDAR.2009.277

Filename

5277594