S-transform based approach for texture analysis of medical images

Pyari Mohan Pradhan, Chun Hing Cheng, Joseph Ross Mitchell

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

2 Citations (Scopus)

Abstract

Image texture is often characterized using gray level co-occurrence matrices (GLCM). The GLCM statistics reflect only the highest power and spatial frequencies. To address this, researchers have employed discrete wavelet transform (DWT) along with GLCM. However, this method involves a computationally complex convolution operation in the spatial domain, and also inherits the sampling limitations of the DWT. Extending texture analysis to the space-frequency (SF) domain will uncover patterns not visible through the GLCM-based approaches while still capitalizing on the effectiveness of the traditional co-occurrence matrix. The discrete S-transform (DST) provides the SF representation at a pixel by localizing with a Gaussian modulated sinusoidal window. The DST based texture analysis is proposed to improve upon the GLCM while providing advantages over wavelets. This paper presents the promising preliminary results achieved using the proposed method.

Original languageEnglish (US)
Title of host publication2014 International Conference on High Performance Computing and Applications, ICHPCA 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479959587
DOIs
StatePublished - Feb 18 2015
Event2014 International Conference on High Performance Computing and Applications, ICHPCA 2014 - Bhubaneswar, India
Duration: Dec 22 2014Dec 24 2014

Other

Other2014 International Conference on High Performance Computing and Applications, ICHPCA 2014
CountryIndia
CityBhubaneswar
Period12/22/1412/24/14

Fingerprint

Textures
Mathematical transformations
Discrete wavelet transforms
Image texture
Convolution
Pixels
Statistics
Sampling

Keywords

  • Grey level co-occurrence matrix
  • S-transform
  • texture analysis

ASJC Scopus subject areas

  • Software

Cite this

Pradhan, P. M., Cheng, C. H., & Mitchell, J. R. (2015). S-transform based approach for texture analysis of medical images. In 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014 [7045374] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHPCA.2014.7045374

S-transform based approach for texture analysis of medical images. / Pradhan, Pyari Mohan; Cheng, Chun Hing; Mitchell, Joseph Ross.

2014 International Conference on High Performance Computing and Applications, ICHPCA 2014. Institute of Electrical and Electronics Engineers Inc., 2015. 7045374.

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

Pradhan, PM, Cheng, CH & Mitchell, JR 2015, S-transform based approach for texture analysis of medical images. in 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014., 7045374, Institute of Electrical and Electronics Engineers Inc., 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014, Bhubaneswar, India, 12/22/14. https://doi.org/10.1109/ICHPCA.2014.7045374
Pradhan PM, Cheng CH, Mitchell JR. S-transform based approach for texture analysis of medical images. In 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014. Institute of Electrical and Electronics Engineers Inc. 2015. 7045374 https://doi.org/10.1109/ICHPCA.2014.7045374
Pradhan, Pyari Mohan ; Cheng, Chun Hing ; Mitchell, Joseph Ross. / S-transform based approach for texture analysis of medical images. 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{d3639aa2989748059293be83c6e734bf,
title = "S-transform based approach for texture analysis of medical images",
abstract = "Image texture is often characterized using gray level co-occurrence matrices (GLCM). The GLCM statistics reflect only the highest power and spatial frequencies. To address this, researchers have employed discrete wavelet transform (DWT) along with GLCM. However, this method involves a computationally complex convolution operation in the spatial domain, and also inherits the sampling limitations of the DWT. Extending texture analysis to the space-frequency (SF) domain will uncover patterns not visible through the GLCM-based approaches while still capitalizing on the effectiveness of the traditional co-occurrence matrix. The discrete S-transform (DST) provides the SF representation at a pixel by localizing with a Gaussian modulated sinusoidal window. The DST based texture analysis is proposed to improve upon the GLCM while providing advantages over wavelets. This paper presents the promising preliminary results achieved using the proposed method.",
keywords = "Grey level co-occurrence matrix, S-transform, texture analysis",
author = "Pradhan, {Pyari Mohan} and Cheng, {Chun Hing} and Mitchell, {Joseph Ross}",
year = "2015",
month = "2",
day = "18",
doi = "10.1109/ICHPCA.2014.7045374",
language = "English (US)",
isbn = "9781479959587",
booktitle = "2014 International Conference on High Performance Computing and Applications, ICHPCA 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - S-transform based approach for texture analysis of medical images

AU - Pradhan, Pyari Mohan

AU - Cheng, Chun Hing

AU - Mitchell, Joseph Ross

PY - 2015/2/18

Y1 - 2015/2/18

N2 - Image texture is often characterized using gray level co-occurrence matrices (GLCM). The GLCM statistics reflect only the highest power and spatial frequencies. To address this, researchers have employed discrete wavelet transform (DWT) along with GLCM. However, this method involves a computationally complex convolution operation in the spatial domain, and also inherits the sampling limitations of the DWT. Extending texture analysis to the space-frequency (SF) domain will uncover patterns not visible through the GLCM-based approaches while still capitalizing on the effectiveness of the traditional co-occurrence matrix. The discrete S-transform (DST) provides the SF representation at a pixel by localizing with a Gaussian modulated sinusoidal window. The DST based texture analysis is proposed to improve upon the GLCM while providing advantages over wavelets. This paper presents the promising preliminary results achieved using the proposed method.

AB - Image texture is often characterized using gray level co-occurrence matrices (GLCM). The GLCM statistics reflect only the highest power and spatial frequencies. To address this, researchers have employed discrete wavelet transform (DWT) along with GLCM. However, this method involves a computationally complex convolution operation in the spatial domain, and also inherits the sampling limitations of the DWT. Extending texture analysis to the space-frequency (SF) domain will uncover patterns not visible through the GLCM-based approaches while still capitalizing on the effectiveness of the traditional co-occurrence matrix. The discrete S-transform (DST) provides the SF representation at a pixel by localizing with a Gaussian modulated sinusoidal window. The DST based texture analysis is proposed to improve upon the GLCM while providing advantages over wavelets. This paper presents the promising preliminary results achieved using the proposed method.

KW - Grey level co-occurrence matrix

KW - S-transform

KW - texture analysis

UR - http://www.scopus.com/inward/record.url?scp=84925428214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84925428214&partnerID=8YFLogxK

U2 - 10.1109/ICHPCA.2014.7045374

DO - 10.1109/ICHPCA.2014.7045374

M3 - Conference contribution

SN - 9781479959587

BT - 2014 International Conference on High Performance Computing and Applications, ICHPCA 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -