Presentation 2013-03-11
Removing of curve and perspective distortion from document images captured by cameras
Kouu YOU, Tetsuya MATSUMOTO, Yoshinori TAKEUCHI, Hiroaki KUDO, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method that can get character information from document images by removing curve and perspective distortions. In the proposed method, we extract character candidates and divide them by text-lines using the hoiiz)ntal overlap of neighboring characters and ^proximate the curve of text-lines by using 4^ order polynomial. Then, we estimate the vertical lines based on invariant cross-ratio and vanishing point which extracted from the left and right edges. The estimated vertical lines and text-lines divide the image into grids. Finally, for each grid we calculate the perspective transform matrix and remove the distortions. Experimental results for 50 images of document images (30 Eiglish document images and 20 Japanes e/Chines e document images) show the effectiveness ofthe proposed method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Document images / OCR / Perspective dis tortion / Cross-ratio / Dewaiping
Paper # IMQ2012-61,IE2012-165,MVE2012-122,WIT2012-71
Date of Issue

Conference Information
Committee MVE
Conference Date 2013/3/4(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Removing of curve and perspective distortion from document images captured by cameras
Sub Title (in English)
Keyword(1) Document images
Keyword(2) OCR
Keyword(3) Perspective dis tortion
Keyword(4) Cross-ratio
Keyword(5) Dewaiping
1st Author's Name Kouu YOU
1st Author's Affiliation Graduate school of Information Science, Nagoya University()
2nd Author's Name Tetsuya MATSUMOTO
2nd Author's Affiliation Graduate school of Information Science, Nagoya University
3rd Author's Name Yoshinori TAKEUCHI
3rd Author's Affiliation School of Informatics, Daido University
4th Author's Name Hiroaki KUDO
4th Author's Affiliation Graduate school of Information Science, Nagoya University
5th Author's Name Noboru OHNISHI
5th Author's Affiliation Graduate school of Information Science, Nagoya University
Date 2013-03-11
Paper # IMQ2012-61,IE2012-165,MVE2012-122,WIT2012-71
Volume (vol) vol.112
Number (no) 474
Page pp.pp.-
#Pages 6
Date of Issue