On the Recovery of Oriented Documents from Single Images

P Clark; M Mirmehdi

On the Recovery of Oriented Documents from Single Images

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

A method is presented for the fronto-parallel recovery of text documents in images of real scenes. Initially an extension of the standard 2D projection profile, commonly used in document recognition, is introduced to locate the horizontal vanishing point of the text plane. This allows us to segment the lines of text, which are then analysed to reveal the style of justification of the paragraphs. The change in line spacings exhibited due to perspective is then used to recover the vertical vanishing point of the document. We do not assume any knowledge of the focal length of the camera. Finally, a fronto-parallel view is recovered, suitable for OCR or other high-level recognition. We provide results demonstrating the algorithm's performance on documents over a wide range of orientations.

Translated title of the contribution	On the Recovery of Oriented Documents from Single Images
Original language	English
Title of host publication	Unknown
Editors	W. Philips
Publisher	Ghent University
Pages	190 - 197
Number of pages	7
Publication status	Published - Sep 2002

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the 4th IEEE Advanced Concepts for Intelligent Vision Systems

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000664

Fingerprint Dive into the research topics of 'On the Recovery of Oriented Documents from Single Images'. Together they form a unique fingerprint.

Cite this

@inproceedings{2e32e60c9cbe484aa970eb2400c8f906,

title = "On the Recovery of Oriented Documents from Single Images",

abstract = "A method is presented for the fronto-parallel recovery of text documents in images of real scenes. Initially an extension of the standard 2D projection profile, commonly used in document recognition, is introduced to locate the horizontal vanishing point of the text plane. This allows us to segment the lines of text, which are then analysed to reveal the style of justification of the paragraphs. The change in line spacings exhibited due to perspective is then used to recover the vertical vanishing point of the document. We do not assume any knowledge of the focal length of the camera. Finally, a fronto-parallel view is recovered, suitable for OCR or other high-level recognition. We provide results demonstrating the algorithm's performance on documents over a wide range of orientations. ",

author = "P Clark and M Mirmehdi",

note = "Conference Proceedings/Title of Journal: Proceedings of the 4th IEEE Advanced Concepts for Intelligent Vision Systems ",

year = "2002",

month = sep,

language = "English",

pages = "190 -- 197",

editor = "W. Philips",

booktitle = "Unknown",

publisher = "Ghent University",

}

TY - GEN

T1 - On the Recovery of Oriented Documents from Single Images

AU - Clark, P

AU - Mirmehdi, M

N1 - Conference Proceedings/Title of Journal: Proceedings of the 4th IEEE Advanced Concepts for Intelligent Vision Systems

PY - 2002/9

Y1 - 2002/9

N2 - A method is presented for the fronto-parallel recovery of text documents in images of real scenes. Initially an extension of the standard 2D projection profile, commonly used in document recognition, is introduced to locate the horizontal vanishing point of the text plane. This allows us to segment the lines of text, which are then analysed to reveal the style of justification of the paragraphs. The change in line spacings exhibited due to perspective is then used to recover the vertical vanishing point of the document. We do not assume any knowledge of the focal length of the camera. Finally, a fronto-parallel view is recovered, suitable for OCR or other high-level recognition. We provide results demonstrating the algorithm's performance on documents over a wide range of orientations.

AB - A method is presented for the fronto-parallel recovery of text documents in images of real scenes. Initially an extension of the standard 2D projection profile, commonly used in document recognition, is introduced to locate the horizontal vanishing point of the text plane. This allows us to segment the lines of text, which are then analysed to reveal the style of justification of the paragraphs. The change in line spacings exhibited due to perspective is then used to recover the vertical vanishing point of the document. We do not assume any knowledge of the focal length of the camera. Finally, a fronto-parallel view is recovered, suitable for OCR or other high-level recognition. We provide results demonstrating the algorithm's performance on documents over a wide range of orientations.

M3 - Conference Contribution (Conference Proceeding)

SP - 190

EP - 197

BT - Unknown

A2 - Philips, W.

PB - Ghent University

ER -