Unwarping images of curved documents using global shape optimization

Jian Liang; Daniel Dementhon; David Doermann

Unwarping images of curved documents using global shape optimization

Jian Liang
, Daniel Dementhon
, David Doermann

Department of Computer Science and Engineering

University of Maryland, College Park

Research output: Contribution to conference › Paper › peer-review

8 Scopus citations

Abstract

The unwarping of curved document images is a crucial problem for camera-based document analysis since most of current OCR techniques can not handle distortion due to perspective and warping. In previous work we have shown how to recover the page shape from a single image using an iterative procedure without camera calibration, and using the shape information to restore a frontal view of a flat document. In this paper we report our recent progress using a global optimization method to do shape estimation. Experimental results show a clear improvement over our previous method.

Original language	English
Pages	25-29
Number of pages	5
State	Published - 2005
Event	1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005 - Seoul, Korea, Republic of Duration: Aug 29 2005 → Aug 29 2005

Conference

Conference	1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005
Country/Territory	Korea, Republic of
City	Seoul
Period	08/29/05 → 08/29/05

Cite this

@conference{8bcf60026c0a4576b32f3ca53259dd74,

title = "Unwarping images of curved documents using global shape optimization",

abstract = "The unwarping of curved document images is a crucial problem for camera-based document analysis since most of current OCR techniques can not handle distortion due to perspective and warping. In previous work we have shown how to recover the page shape from a single image using an iterative procedure without camera calibration, and using the shape information to restore a frontal view of a flat document. In this paper we report our recent progress using a global optimization method to do shape estimation. Experimental results show a clear improvement over our previous method.",

author = "Jian Liang and Daniel Dementhon and David Doermann",

year = "2005",

language = "English",

pages = "25--29",

note = "1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005 ; Conference date: 29-08-2005 Through 29-08-2005",

}

TY - CONF

T1 - Unwarping images of curved documents using global shape optimization

AU - Liang, Jian

AU - Dementhon, Daniel

AU - Doermann, David

PY - 2005

Y1 - 2005

N2 - The unwarping of curved document images is a crucial problem for camera-based document analysis since most of current OCR techniques can not handle distortion due to perspective and warping. In previous work we have shown how to recover the page shape from a single image using an iterative procedure without camera calibration, and using the shape information to restore a frontal view of a flat document. In this paper we report our recent progress using a global optimization method to do shape estimation. Experimental results show a clear improvement over our previous method.

AB - The unwarping of curved document images is a crucial problem for camera-based document analysis since most of current OCR techniques can not handle distortion due to perspective and warping. In previous work we have shown how to recover the page shape from a single image using an iterative procedure without camera calibration, and using the shape information to restore a frontal view of a flat document. In this paper we report our recent progress using a global optimization method to do shape estimation. Experimental results show a clear improvement over our previous method.

UR - https://www.scopus.com/pages/publications/34548235390

M3 - Paper

AN - SCOPUS:34548235390

SP - 25

EP - 29

T2 - 1st International Workshop on Camera-Based Document Analysis and Recognition, CBDAR 2005

Y2 - 29 August 2005 through 29 August 2005

ER -

Unwarping images of curved documents using global shape optimization

Abstract

Conference

Other files and links

Fingerprint

Cite this