A novel modified SFTA approach for feature extraction.

Hasan, Md. Junayed; Uddin, Jia; Pinku, Subroto Nag

Abstract

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.

Citation

HASAN, M.J., UDDIN, J. and PINKU, S.N. 2016. A novel modified SFIA approach for feature extraction. In Proceedings of 3rd International conference on electrical engineering and information and communication technology 2016 (iCEEiCT 2016), 22-24 September 2016, Dhaka, Bangladesh. Piscataway: IEEE [online], article 7873115. Available from: https://doi.org/10.1109/CEEICT.2016.7873115

• Conference Name: 3rd International conference on electrical engineering and information and communication technology 2016 (iCEEiCT 2016)
• Conference Location: Dhaka, Bangladesh
• Start Date: Sep 22, 2016
• End Date: Sep 24, 2016
• Acceptance Date: Aug 10, 2016
• Online Publication Date: Sep 24, 2016
• Publication Date: Mar 9, 2017
• Deposit Date: May 16, 2022
• Publicly Available Date: Jun 7, 2022
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• ISBN: 9781509029068
• DOI: https://doi.org/10.1109/CEEICT.2016.7873115
• Keywords: SFTA (segmentation based fractal texture analysis); Multilevel thresholing; HGAPSO; Otsu function
• Public URL: https://rgu-repository.worktribe.com/output/1669589