Context based multiscale classification of images

Jia Li, Robert M. Gray

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

This paper presents an algorithm to segment images into four classes: background, photograph, text and graph. There are two important aspects about the algorithm. The first is that the algorithm takes a multiscale approach, which adaptively classifies an image at different resolutions. The multiscale structure enables accurate classification at class boundaries as well as fast classification overall. The second is that the context information, which is accumulated in the process of classification, is used to improve the classification accuracy.

Original languageEnglish (US)
Pages566-570
Number of pages5
StatePublished - Dec 1 1998
EventProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) - Chicago, IL, USA
Duration: Oct 4 1998Oct 7 1998

Other

OtherProceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3)
CityChicago, IL, USA
Period10/4/9810/7/98

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Li, J., & Gray, R. M. (1998). Context based multiscale classification of images. 566-570. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .
Li, Jia ; Gray, Robert M. / Context based multiscale classification of images. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .5 p.
@conference{79e8fcf5f163443d93bd73948f32ab67,
title = "Context based multiscale classification of images",
abstract = "This paper presents an algorithm to segment images into four classes: background, photograph, text and graph. There are two important aspects about the algorithm. The first is that the algorithm takes a multiscale approach, which adaptively classifies an image at different resolutions. The multiscale structure enables accurate classification at class boundaries as well as fast classification overall. The second is that the context information, which is accumulated in the process of classification, is used to improve the classification accuracy.",
author = "Jia Li and Gray, {Robert M.}",
year = "1998",
month = "12",
day = "1",
language = "English (US)",
pages = "566--570",
note = "Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3) ; Conference date: 04-10-1998 Through 07-10-1998",

}

Li, J & Gray, RM 1998, 'Context based multiscale classification of images', Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, 10/4/98 - 10/7/98 pp. 566-570.

Context based multiscale classification of images. / Li, Jia; Gray, Robert M.

1998. 566-570 Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Context based multiscale classification of images

AU - Li, Jia

AU - Gray, Robert M.

PY - 1998/12/1

Y1 - 1998/12/1

N2 - This paper presents an algorithm to segment images into four classes: background, photograph, text and graph. There are two important aspects about the algorithm. The first is that the algorithm takes a multiscale approach, which adaptively classifies an image at different resolutions. The multiscale structure enables accurate classification at class boundaries as well as fast classification overall. The second is that the context information, which is accumulated in the process of classification, is used to improve the classification accuracy.

AB - This paper presents an algorithm to segment images into four classes: background, photograph, text and graph. There are two important aspects about the algorithm. The first is that the algorithm takes a multiscale approach, which adaptively classifies an image at different resolutions. The multiscale structure enables accurate classification at class boundaries as well as fast classification overall. The second is that the context information, which is accumulated in the process of classification, is used to improve the classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=0032307245&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032307245&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0032307245

SP - 566

EP - 570

ER -

Li J, Gray RM. Context based multiscale classification of images. 1998. Paper presented at Proceedings of the 1998 International Conference on Image Processing, ICIP. Part 2 (of 3), Chicago, IL, USA, .