A novel modified SFTA approach for feature extraction

A novel modified SFTA approach for feature extraction

This conference paper was published in the IEEE Xplore [© 2017 IEEE] and the definite version is available at : http://doi.org/10.1109/CEEICT.2016.7873115 The Journal's website is at: http://ieeexplore.ieee.org/document/7873115/

Detalhes bibliográficos
Principais autores: Hasan, Md Junayed, Uddin, Jia, Pinku, Subroto Nag
Outros Autores: Department of Computer Science and Engineering, BRAC University
Formato: Conference paper
Idioma:English
Publicado em: © 2016 IEEE 2018
Assuntos:
HGAPSO
Multilevel thresholing
Otsu function
SFTA (Segmentation Based Fractal Texture Analysis)
Acesso em linha:http://hdl.handle.net/10361/9502
http://doi.org/10.1109/CEEICT.2016.7873115
id 10361-9502
record_format dspace
spelling 10361-95022022-01-27T03:12:53Z A novel modified SFTA approach for feature extraction Hasan, Md Junayed Uddin, Jia Pinku, Subroto Nag Department of Computer Science and Engineering, BRAC University HGAPSO Multilevel thresholing Otsu function SFTA (Segmentation Based Fractal Texture Analysis) This conference paper was published in the IEEE Xplore [© 2017 IEEE] and the definite version is available at : http://doi.org/10.1109/CEEICT.2016.7873115 The Journal's website is at: http://ieeexplore.ieee.org/document/7873115/ To increase the efficiency of conventional Segmentation Based Fractal Texture Analysis (SFTA), we propose a new approach on SFTA algorithm. We use an optimum multilevel thresholding hybrid method of Genetic Algorithm (GA) and Particle Swarm Optimization (PSO), called HGAPSO with the optimization technique for classification based on grey level range to get more accurate output. Experimental results show that proposed approach exhibits average 2% higher classification accuracy than conventional SFTA for our tested dataset. Published 2018-02-18T08:50:52Z 2018-02-18T08:50:52Z 9/22/2016 Conference paper Hasan, M. J., Uddin, J., & Pinku, S. N. (2017). A novel modified SFTA approach for feature extraction. Paper presented at the 2016 3rd International Conference on Electrical Engineering and Information and Communication Technology, iCEEiCT 2016, 10.1109/CEEICT.2016.7873115 978-150902906-8 http://hdl.handle.net/10361/9502 http://doi.org/10.1109/CEEICT.2016.7873115 en http://ieeexplore.ieee.org/document/7873115/ © 2016 IEEE
institution Brac University
collection Institutional Repository
language English
topic HGAPSO
Multilevel thresholing
Otsu function
SFTA (Segmentation Based Fractal Texture Analysis)
spellingShingle HGAPSO
Multilevel thresholing
Otsu function
SFTA (Segmentation Based Fractal Texture Analysis)
Hasan, Md Junayed
Uddin, Jia
Pinku, Subroto Nag
A novel modified SFTA approach for feature extraction
description This conference paper was published in the IEEE Xplore [© 2017 IEEE] and the definite version is available at : http://doi.org/10.1109/CEEICT.2016.7873115 The Journal's website is at: http://ieeexplore.ieee.org/document/7873115/
author2 Department of Computer Science and Engineering, BRAC University
author_facet Department of Computer Science and Engineering, BRAC University
Hasan, Md Junayed
Uddin, Jia
Pinku, Subroto Nag
format Conference paper
author Hasan, Md Junayed
Uddin, Jia
Pinku, Subroto Nag
author_sort Hasan, Md Junayed
title A novel modified SFTA approach for feature extraction
title_short A novel modified SFTA approach for feature extraction
title_full A novel modified SFTA approach for feature extraction
title_fullStr A novel modified SFTA approach for feature extraction
title_full_unstemmed A novel modified SFTA approach for feature extraction
title_sort novel modified sfta approach for feature extraction
publisher © 2016 IEEE
publishDate 2018
url http://hdl.handle.net/10361/9502
http://doi.org/10.1109/CEEICT.2016.7873115
work_keys_str_mv AT hasanmdjunayed anovelmodifiedsftaapproachforfeatureextraction
AT uddinjia anovelmodifiedsftaapproachforfeatureextraction
AT pinkusubrotonag anovelmodifiedsftaapproachforfeatureextraction
AT hasanmdjunayed novelmodifiedsftaapproachforfeatureextraction
AT uddinjia novelmodifiedsftaapproachforfeatureextraction
AT pinkusubrotonag novelmodifiedsftaapproachforfeatureextraction
_version_ 1814308601740656640

Registros relacionados