Parallel texture analysis using high-order statistics and neural networks

H. Araujo; J. Dias; A. T. Almeida

doi:10.1109/SIPNN.1994.344883

Parallel texture analysis using high-order statistics and neural networks

H. Araujo, J. Dias, A. T. Almeida

Electrical Engineering

University of Coimbra, Institute of Systems and Robotics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper we present a texture analysis and classification method based on the computation of high-order statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for backpropagation networks only, but several other types of neural nets were also tested.

Original language	British English
Title of host publication	ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	401-404
Number of pages	4
ISBN (Electronic)	078031865X, 9780780318656
DOIs	https://doi.org/10.1109/SIPNN.1994.344883
State	Published - 1994
Event	1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994 - Hong Kong, Hong Kong Duration: 13 Apr 1994 → 16 Apr 1994

Publication series

Name	ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings

Conference

Conference	1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994
Country/Territory	Hong Kong
City	Hong Kong
Period	13/04/94 → 16/04/94

Access to Document

10.1109/SIPNN.1994.344883

Cite this

Araujo, H., Dias, J., & Almeida, A. T. (1994). Parallel texture analysis using high-order statistics and neural networks. In ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings (pp. 401-404). Article 344883 (ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIPNN.1994.344883

Araujo, H. ; Dias, J. ; Almeida, A. T. / Parallel texture analysis using high-order statistics and neural networks. ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings. Institute of Electrical and Electronics Engineers Inc., 1994. pp. 401-404 (ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings).

@inproceedings{60dc8524e7f249d8a10aa6a286011abe,

title = "Parallel texture analysis using high-order statistics and neural networks",

abstract = "In this paper we present a texture analysis and classification method based on the computation of high-order statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for backpropagation networks only, but several other types of neural nets were also tested.",

author = "H. Araujo and J. Dias and Almeida, {A. T.}",

note = "Publisher Copyright: {\textcopyright} 1994 IEEE.; 1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994 ; Conference date: 13-04-1994 Through 16-04-1994",

year = "1994",

doi = "10.1109/SIPNN.1994.344883",

language = "British English",

series = "ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "401--404",

booktitle = "ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings",

address = "United States",

}

Araujo, H, Dias, J & Almeida, AT 1994, Parallel texture analysis using high-order statistics and neural networks. in ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings., 344883, ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 401-404, 1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994, Hong Kong, Hong Kong, 13/04/94. https://doi.org/10.1109/SIPNN.1994.344883

Parallel texture analysis using high-order statistics and neural networks. / Araujo, H.; Dias, J.; Almeida, A. T.
ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings. Institute of Electrical and Electronics Engineers Inc., 1994. p. 401-404 344883 (ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Parallel texture analysis using high-order statistics and neural networks

AU - Araujo, H.

AU - Dias, J.

AU - Almeida, A. T.

PY - 1994

Y1 - 1994

N2 - In this paper we present a texture analysis and classification method based on the computation of high-order statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for backpropagation networks only, but several other types of neural nets were also tested.

AB - In this paper we present a texture analysis and classification method based on the computation of high-order statistics of gray-levels or selected features. The computation of these high-order statistics can be performed in parallel in non-overlapping windows that cover the full image. Classification is performed by neural networks. In this extended summary results are presented for backpropagation networks only, but several other types of neural nets were also tested.

UR - http://www.scopus.com/inward/record.url?scp=77955088065&partnerID=8YFLogxK

U2 - 10.1109/SIPNN.1994.344883

DO - 10.1109/SIPNN.1994.344883

M3 - Conference contribution

AN - SCOPUS:77955088065

T3 - ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings

SP - 401

EP - 404

BT - ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1994 International Symposium on Speech, Image Processing and Neural Networks, ISSIPNN 1994

Y2 - 13 April 1994 through 16 April 1994

ER -

Araujo H, Dias J, Almeida AT. Parallel texture analysis using high-order statistics and neural networks. In ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings. Institute of Electrical and Electronics Engineers Inc. 1994. p. 401-404. 344883. (ISSIPNN 1994 - 1994 International Symposium on Speech, Image Processing and Neural Networks, Proceedings). doi: 10.1109/SIPNN.1994.344883

Parallel texture analysis using high-order statistics and neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this