Rectifying perspective distortion into affine distortion using variants and invariants

Masakazu Iwamura, Ryo Niwa, Koichi Kise, Seiichi Uchida, Shinichiro Omachi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

For user convenience, document image processing captured with a digital camera instead of a scanner has been researched. However, existing methods of document image processing are not usable for a perspective document image captured by a digital camera because most of them are designed for the one captured by a scanner. Thus, we have to rectify the perspective of the document image and obtain the frontal image as if it was captured by a scanner. In this paper, for eliminating perspective distortion from a planar paper without any prior knowledge, we propose a new rectification method of a document image introducing variants which change according to the gradient of the paper and invariants which do not change against it. Since the proposed method does not use strong assumptions, it is widely applicable to many document images unlike other methods. We confirmed the proposed method rectifies a document image suffering from perspective distortion and acquires the one with affine distortion.

Original languageEnglish
Title of host publicationProceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007
Pages138-145
Number of pages8
Publication statusPublished - 2007
Event2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007 - Curitiba, Brazil
Duration: Sep 22 2007Sep 22 2007

Other

Other2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007
CountryBrazil
CityCuritiba
Period9/22/079/22/07

Fingerprint

Digital cameras
Image processing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Human-Computer Interaction
  • Software

Cite this

Iwamura, M., Niwa, R., Kise, K., Uchida, S., & Omachi, S. (2007). Rectifying perspective distortion into affine distortion using variants and invariants. In Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007 (pp. 138-145)

Rectifying perspective distortion into affine distortion using variants and invariants. / Iwamura, Masakazu; Niwa, Ryo; Kise, Koichi; Uchida, Seiichi; Omachi, Shinichiro.

Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007. 2007. p. 138-145.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Iwamura, M, Niwa, R, Kise, K, Uchida, S & Omachi, S 2007, Rectifying perspective distortion into affine distortion using variants and invariants. in Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007. pp. 138-145, 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007, Curitiba, Brazil, 9/22/07.
Iwamura M, Niwa R, Kise K, Uchida S, Omachi S. Rectifying perspective distortion into affine distortion using variants and invariants. In Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007. 2007. p. 138-145
Iwamura, Masakazu ; Niwa, Ryo ; Kise, Koichi ; Uchida, Seiichi ; Omachi, Shinichiro. / Rectifying perspective distortion into affine distortion using variants and invariants. Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007. 2007. pp. 138-145
@inproceedings{975a1e19148d44ba92327ed8bb68023d,
title = "Rectifying perspective distortion into affine distortion using variants and invariants",
abstract = "For user convenience, document image processing captured with a digital camera instead of a scanner has been researched. However, existing methods of document image processing are not usable for a perspective document image captured by a digital camera because most of them are designed for the one captured by a scanner. Thus, we have to rectify the perspective of the document image and obtain the frontal image as if it was captured by a scanner. In this paper, for eliminating perspective distortion from a planar paper without any prior knowledge, we propose a new rectification method of a document image introducing variants which change according to the gradient of the paper and invariants which do not change against it. Since the proposed method does not use strong assumptions, it is widely applicable to many document images unlike other methods. We confirmed the proposed method rectifies a document image suffering from perspective distortion and acquires the one with affine distortion.",
author = "Masakazu Iwamura and Ryo Niwa and Koichi Kise and Seiichi Uchida and Shinichiro Omachi",
year = "2007",
language = "English",
pages = "138--145",
booktitle = "Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007",

}

TY - GEN

T1 - Rectifying perspective distortion into affine distortion using variants and invariants

AU - Iwamura, Masakazu

AU - Niwa, Ryo

AU - Kise, Koichi

AU - Uchida, Seiichi

AU - Omachi, Shinichiro

PY - 2007

Y1 - 2007

N2 - For user convenience, document image processing captured with a digital camera instead of a scanner has been researched. However, existing methods of document image processing are not usable for a perspective document image captured by a digital camera because most of them are designed for the one captured by a scanner. Thus, we have to rectify the perspective of the document image and obtain the frontal image as if it was captured by a scanner. In this paper, for eliminating perspective distortion from a planar paper without any prior knowledge, we propose a new rectification method of a document image introducing variants which change according to the gradient of the paper and invariants which do not change against it. Since the proposed method does not use strong assumptions, it is widely applicable to many document images unlike other methods. We confirmed the proposed method rectifies a document image suffering from perspective distortion and acquires the one with affine distortion.

AB - For user convenience, document image processing captured with a digital camera instead of a scanner has been researched. However, existing methods of document image processing are not usable for a perspective document image captured by a digital camera because most of them are designed for the one captured by a scanner. Thus, we have to rectify the perspective of the document image and obtain the frontal image as if it was captured by a scanner. In this paper, for eliminating perspective distortion from a planar paper without any prior knowledge, we propose a new rectification method of a document image introducing variants which change according to the gradient of the paper and invariants which do not change against it. Since the proposed method does not use strong assumptions, it is widely applicable to many document images unlike other methods. We confirmed the proposed method rectifies a document image suffering from perspective distortion and acquires the one with affine distortion.

UR - http://www.scopus.com/inward/record.url?scp=62249133981&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=62249133981&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:62249133981

SP - 138

EP - 145

BT - Proceedings of the 2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007

ER -