Novel feature extraction methodology based on histopathalogical images and subsequent classification by support vector machine

Abu Mahmoud, MK; Al-Jumaily, A

Novel feature extraction methodology based on histopathalogical images and subsequent classification by support vector machine

Abu Mahmoud, MK Al-Jumaily, A

Permalink

Publication Type:: Conference Proceeding
Citation:: 2014 World Symposium on Computer Applications and Research, WSCAR 2014, 2014
Issue Date:: 2014-01-01

Closed Access

	Filename	Description	Size
	5_2014 IEEE_ICCVIA_RAK_Novel feature_06916803.pdf	Published version	1.88 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Abu Mahmoud, MK	en_US
dc.contributor.author	Al-Jumaily, A https://orcid.org/0000-0003-0297-2463	en_US
dc.date.issued	2014-01-01	en_US
dc.identifier.citation	2014 World Symposium on Computer Applications and Research, WSCAR 2014, 2014	en_US
dc.identifier.isbn	9781479928057	en_US
dc.identifier.uri	http://hdl.handle.net/10453/30483
dc.description.abstract	© 2014 IEEE. A novel methodology for automatic feature extraction from histo-pathological images and subsequent classification is presented. The proposed automated system use a number of features extracted from images of skin lesions through image processing techniques which consisted of a spatially winner and adaptive median filter then applied Gabor filter bank to improve diagnostic accuracy. Histogram equalization to enhance the contrast of the images prior to segmentation is used. The extracted features are reduced by using sequential feature selection and finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier to diagnose skin biopsies from patients as either malignant melanoma or benign nevi. The obtained classification accuracies show better performance in comparison to similar approaches for feature extraction. The proposed system is able to achieve a good result with classification accuracy of (81)%, sensitivity of(76)% and specificity of (100)%and 17 times faster than some of the reported results.	en_US
dc.relation.ispartof	2014 World Symposium on Computer Applications and Research, WSCAR 2014	en_US
dc.relation.isbasedon	10.1109/WSCAR.2014.6916803	en_US
dc.title	Novel feature extraction methodology based on histopathalogical images and subsequent classification by support vector machine	en_US
dc.type	Conference Proceeding
utslib.for	080101 Adaptive Agents and Intelligent Robotics	en_US
utslib.for	080109 Pattern Recognition and Data Mining	en_US
utslib.for	080108 Neural, Evolutionary and Fuzzy Computation	en_US
dc.location.activity	American University of Ras al Khaimah, UAE
dc.location.activity	Sousse, Tunisia
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
utslib.copyright.status	closed_access
pubs.publication-status	Published	en_US

Abstract:

© 2014 IEEE. A novel methodology for automatic feature extraction from histo-pathological images and subsequent classification is presented. The proposed automated system use a number of features extracted from images of skin lesions through image processing techniques which consisted of a spatially winner and adaptive median filter then applied Gabor filter bank to improve diagnostic accuracy. Histogram equalization to enhance the contrast of the images prior to segmentation is used. The extracted features are reduced by using sequential feature selection and finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier to diagnose skin biopsies from patients as either malignant melanoma or benign nevi. The obtained classification accuracies show better performance in comparison to similar approaches for feature extraction. The proposed system is able to achieve a good result with classification accuracy of (81)%, sensitivity of(76)% and specificity of (100)%and 17 times faster than some of the reported results.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/30483