A novel modified SFTA approach for feature extraction
No Thumbnail Available
Date
9/22/2016
Journal Title
Journal ISSN
Volume Title
Publisher
© 2016 IEEE
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.
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/
Keywords
HGAPSO, Multilevel thresholing, Otsu function, SFTA (Segmentation Based Fractal Texture Analysis)
Citation
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