Texture feature extraction and classification using radial basis function for diagnosis of brain tumour

Kumar Vaibhav, Sanyog Rawat, Ashwani Kumar Yadav, Sudhanshu Singh, Sangeeta Shekhawat

Research output: Contribution to journalArticle

Abstract

Texture features are playing major role now-a-days for the analysis of medical images. With the help of texture features extraction and classification, we can differentiate between pathological and healthy issues in various organs. In this paper, we have formed gray level cooccurrence matrix (GLCM) for MR brain images. Then, we have extracted Haralick texture features and then used support vector machine (SVM) using Gaussian radical basis function for classification between malignant and healthy brain. The performance of various texture features are compared in terms of percentage accuracy for the correct classification of images.

Original languageEnglish (US)
Pages (from-to)161-168
Number of pages8
JournalFar East Journal of Electronics and Communications
VolumeSpecialVolume3
DOIs
StatePublished - Jan 1 2016
Externally publishedYes

Fingerprint

Feature extraction
Tumors
Brain
Textures
Support vector machines

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

Texture feature extraction and classification using radial basis function for diagnosis of brain tumour. / Vaibhav, Kumar; Rawat, Sanyog; Yadav, Ashwani Kumar; Singh, Sudhanshu; Shekhawat, Sangeeta.

In: Far East Journal of Electronics and Communications, Vol. SpecialVolume3, 01.01.2016, p. 161-168.

Research output: Contribution to journalArticle

Vaibhav, Kumar ; Rawat, Sanyog ; Yadav, Ashwani Kumar ; Singh, Sudhanshu ; Shekhawat, Sangeeta. / Texture feature extraction and classification using radial basis function for diagnosis of brain tumour. In: Far East Journal of Electronics and Communications. 2016 ; Vol. SpecialVolume3. pp. 161-168.
@article{a1156c9dec3d453a9566490d7370c01f,
title = "Texture feature extraction and classification using radial basis function for diagnosis of brain tumour",
abstract = "Texture features are playing major role now-a-days for the analysis of medical images. With the help of texture features extraction and classification, we can differentiate between pathological and healthy issues in various organs. In this paper, we have formed gray level cooccurrence matrix (GLCM) for MR brain images. Then, we have extracted Haralick texture features and then used support vector machine (SVM) using Gaussian radical basis function for classification between malignant and healthy brain. The performance of various texture features are compared in terms of percentage accuracy for the correct classification of images.",
author = "Kumar Vaibhav and Sanyog Rawat and Yadav, {Ashwani Kumar} and Sudhanshu Singh and Sangeeta Shekhawat",
year = "2016",
month = "1",
day = "1",
doi = "10.17654/ECSV3PI16161",
language = "English (US)",
volume = "SpecialVolume3",
pages = "161--168",
journal = "Far East Journal of Electronics and Communications",
issn = "0973-7006",
publisher = "Pushpa Publishing House",

}

TY - JOUR

T1 - Texture feature extraction and classification using radial basis function for diagnosis of brain tumour

AU - Vaibhav, Kumar

AU - Rawat, Sanyog

AU - Yadav, Ashwani Kumar

AU - Singh, Sudhanshu

AU - Shekhawat, Sangeeta

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Texture features are playing major role now-a-days for the analysis of medical images. With the help of texture features extraction and classification, we can differentiate between pathological and healthy issues in various organs. In this paper, we have formed gray level cooccurrence matrix (GLCM) for MR brain images. Then, we have extracted Haralick texture features and then used support vector machine (SVM) using Gaussian radical basis function for classification between malignant and healthy brain. The performance of various texture features are compared in terms of percentage accuracy for the correct classification of images.

AB - Texture features are playing major role now-a-days for the analysis of medical images. With the help of texture features extraction and classification, we can differentiate between pathological and healthy issues in various organs. In this paper, we have formed gray level cooccurrence matrix (GLCM) for MR brain images. Then, we have extracted Haralick texture features and then used support vector machine (SVM) using Gaussian radical basis function for classification between malignant and healthy brain. The performance of various texture features are compared in terms of percentage accuracy for the correct classification of images.

UR - http://www.scopus.com/inward/record.url?scp=85057638004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057638004&partnerID=8YFLogxK

U2 - 10.17654/ECSV3PI16161

DO - 10.17654/ECSV3PI16161

M3 - Article

AN - SCOPUS:85057638004

VL - SpecialVolume3

SP - 161

EP - 168

JO - Far East Journal of Electronics and Communications

JF - Far East Journal of Electronics and Communications

SN - 0973-7006

ER -