Abstract
Purchase PDF (636 K)
E-mail Article
Add to my Quick Links
Cited By in Scopus (1)
Purchase PDF (864 K)
doi:10.1016/j.imavis.2006.02.008 
Copyright © 2006 Elsevier B.V. All rights reserved.
A partition approach for the restoration of camera images of planar and curled document
Received 1 May 2005;
References and further reading may be available for this article. To view references and further reading you must purchase this article.
Abstract
As camera resolution increases, high-speed non-contact text capture through a digital camera is opening up a new channel for text capture and understanding. Unfortunately, the captured document images are normally coupled with the perspective and geometric distortions that cannot be handled by the existing optical character recognition (OCR) systems. In this paper, we propose a new technique, which is capable of removing the perspective and geometric distortions, and reconstructing the fronto-parallel view of text with a single document image. Different from reported approaches in the literature, the restoration of the distorted camera documents is carried out through the image partition, which divides the documents into multiple small image patches where text can be approximated to lie on a planar surface. The global distortion is thus corrected through the local rectification of the partitioned image patches one by one. Experimental results show that the proposed method is fast and easy for implementation.
Keywords: Document image analysis; Document image rectification; Optical character recognition; Morphological image processing; Fuzzy sets
Article Outline
- 1. Introduction
- 2. Proposed restoration technique
- 2.1. Document image partition
- 2.1.1. Document binarization
- 2.1.2. Vertical stroke boundary identification
- 2.1.3. X line and base line fitting
- 2.1.4. Document image partition
- 2.2. Target rectangle construction
- 2.3. Document restoration
- 3. Experiment results and discussion
- 4. Conclusion
- References
