An automated Multispectral pixel and image classification system using texture analysis and neural networks

Yi Zheng, David A. Foley, Thomas M. Kinter, James F Greenleaf

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

An automated pixel and image classification system has been developed to identify texture patterns within images after training with representative texture patterns. Multispectral analysis is applied to ultrasound images to form hyperspaces in which texture patterns are clustered. The clusters in the space are produced using run-length and Markovian texture statistics. Several neural network models can be selected to classify patterns. The system has been implemented in C on a Sun workstation in a window environment. It is highly automated and has potential for clinical applications. Texture patterns found in a series of cardiac ultrasound images of a tumor were used to train the system. The tumor was correcdy identified throughout a series of consecutive, closely-space tomographic images.

Original languageEnglish (US)
Title of host publication1992 Ultrasonics Symposium Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1093-1096
Number of pages4
ISBN (Electronic)0780305620
DOIs
StatePublished - Jan 1 1992
Externally publishedYes
Event1992 Ultrasonics Symposium - Tucson, United States
Duration: Oct 20 1992Oct 23 1992

Publication series

NameProceedings - IEEE Ultrasonics Symposium
Volume1992-October
ISSN (Print)1051-0117

Conference

Conference1992 Ultrasonics Symposium
CountryUnited States
CityTucson
Period10/20/9210/23/92

Fingerprint

image classification
textures
pixels
tumors
hyperspaces
workstations
sun
education
statistics

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

Zheng, Y., Foley, D. A., Kinter, T. M., & Greenleaf, J. F. (1992). An automated Multispectral pixel and image classification system using texture analysis and neural networks. In 1992 Ultrasonics Symposium Proceedings (pp. 1093-1096). [276007] (Proceedings - IEEE Ultrasonics Symposium; Vol. 1992-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ULTSYM.1992.276007

An automated Multispectral pixel and image classification system using texture analysis and neural networks. / Zheng, Yi; Foley, David A.; Kinter, Thomas M.; Greenleaf, James F.

1992 Ultrasonics Symposium Proceedings. Institute of Electrical and Electronics Engineers Inc., 1992. p. 1093-1096 276007 (Proceedings - IEEE Ultrasonics Symposium; Vol. 1992-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zheng, Y, Foley, DA, Kinter, TM & Greenleaf, JF 1992, An automated Multispectral pixel and image classification system using texture analysis and neural networks. in 1992 Ultrasonics Symposium Proceedings., 276007, Proceedings - IEEE Ultrasonics Symposium, vol. 1992-October, Institute of Electrical and Electronics Engineers Inc., pp. 1093-1096, 1992 Ultrasonics Symposium, Tucson, United States, 10/20/92. https://doi.org/10.1109/ULTSYM.1992.276007
Zheng Y, Foley DA, Kinter TM, Greenleaf JF. An automated Multispectral pixel and image classification system using texture analysis and neural networks. In 1992 Ultrasonics Symposium Proceedings. Institute of Electrical and Electronics Engineers Inc. 1992. p. 1093-1096. 276007. (Proceedings - IEEE Ultrasonics Symposium). https://doi.org/10.1109/ULTSYM.1992.276007
Zheng, Yi ; Foley, David A. ; Kinter, Thomas M. ; Greenleaf, James F. / An automated Multispectral pixel and image classification system using texture analysis and neural networks. 1992 Ultrasonics Symposium Proceedings. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 1093-1096 (Proceedings - IEEE Ultrasonics Symposium).
@inproceedings{ba6e711143844030b414f59f2b2200b6,
title = "An automated Multispectral pixel and image classification system using texture analysis and neural networks",
abstract = "An automated pixel and image classification system has been developed to identify texture patterns within images after training with representative texture patterns. Multispectral analysis is applied to ultrasound images to form hyperspaces in which texture patterns are clustered. The clusters in the space are produced using run-length and Markovian texture statistics. Several neural network models can be selected to classify patterns. The system has been implemented in C on a Sun workstation in a window environment. It is highly automated and has potential for clinical applications. Texture patterns found in a series of cardiac ultrasound images of a tumor were used to train the system. The tumor was correcdy identified throughout a series of consecutive, closely-space tomographic images.",
author = "Yi Zheng and Foley, {David A.} and Kinter, {Thomas M.} and Greenleaf, {James F}",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/ULTSYM.1992.276007",
language = "English (US)",
series = "Proceedings - IEEE Ultrasonics Symposium",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1093--1096",
booktitle = "1992 Ultrasonics Symposium Proceedings",

}

TY - GEN

T1 - An automated Multispectral pixel and image classification system using texture analysis and neural networks

AU - Zheng, Yi

AU - Foley, David A.

AU - Kinter, Thomas M.

AU - Greenleaf, James F

PY - 1992/1/1

Y1 - 1992/1/1

N2 - An automated pixel and image classification system has been developed to identify texture patterns within images after training with representative texture patterns. Multispectral analysis is applied to ultrasound images to form hyperspaces in which texture patterns are clustered. The clusters in the space are produced using run-length and Markovian texture statistics. Several neural network models can be selected to classify patterns. The system has been implemented in C on a Sun workstation in a window environment. It is highly automated and has potential for clinical applications. Texture patterns found in a series of cardiac ultrasound images of a tumor were used to train the system. The tumor was correcdy identified throughout a series of consecutive, closely-space tomographic images.

AB - An automated pixel and image classification system has been developed to identify texture patterns within images after training with representative texture patterns. Multispectral analysis is applied to ultrasound images to form hyperspaces in which texture patterns are clustered. The clusters in the space are produced using run-length and Markovian texture statistics. Several neural network models can be selected to classify patterns. The system has been implemented in C on a Sun workstation in a window environment. It is highly automated and has potential for clinical applications. Texture patterns found in a series of cardiac ultrasound images of a tumor were used to train the system. The tumor was correcdy identified throughout a series of consecutive, closely-space tomographic images.

UR - http://www.scopus.com/inward/record.url?scp=0013634816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0013634816&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.1992.276007

DO - 10.1109/ULTSYM.1992.276007

M3 - Conference contribution

T3 - Proceedings - IEEE Ultrasonics Symposium

SP - 1093

EP - 1096

BT - 1992 Ultrasonics Symposium Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -