Rectifying perspective distortion into affine distortion using variants and invariants

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

Research output: Contribution to conferencePaperpeer-review

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
Pages138-145
Number of pages8
Publication statusPublished - 2007
Externally publishedYes
Event2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007 - Curitiba, Brazil
Duration: 2007 Sep 222007 Sep 22

Other

Other2nd International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2007
CountryBrazil
CityCuritiba
Period07/9/2207/9/22

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Rectifying perspective distortion into affine distortion using variants and invariants'. Together they form a unique fingerprint.

Cite this