Translator Disclaimer
19 January 2009 Camera-based document image mosaicing using LLAH
Author Affiliations +
Abstract
In this paper we propose a mosaicing method of camera-captured document images. Since document images captured using digital cameras suffer from perspective distortion, their alignment is a diffcult task for previous methods. In the proposed method, correspondences of feature points are calculated using an image retrieval method LLAH. Document images are aligned using a perspective transformation parameter estimated from the correspondences. Since LLAH is invariant to perspective distortion, feature points can be matched without compensation of perspective distortion. Experimental results show that document images captured by a digital camera can be stitched using the proposed method.
© (2009) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tomohiro Nakai, Koichi Kise, and Masakazu Iwamura "Camera-based document image mosaicing using LLAH", Proc. SPIE 7247, Document Recognition and Retrieval XVI, 72470O (19 January 2009); https://doi.org/10.1117/12.805949
PROCEEDINGS
10 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Copy-move forgery detection from printed images
Proceedings of SPIE (February 18 2014)
Applications of image processing technologies to fine arts
Proceedings of SPIE (October 08 2003)
Image retrieval algorithm using fractal dimensions
Proceedings of SPIE (July 30 2002)
Camera identification from printed images
Proceedings of SPIE (March 17 2008)

Back to Top