Title :
Using the BPSO algorithm in image segmentation for dynamic thresholding
Author :
Djerou, L. ; Dehimi, H. ; Khelil, N. ; Batouche, M.
Author_Institution :
Comput. Sci. Dept., M. Khider Univ., Biskra, Algeria
Abstract :
A new dynamic Multilevel Thresholding method (DMTBPSO), based on Binary Particle Swarm Optimization and Otsu´s method, is proposed. This approach can automatically determine the appropriate number of thresholds as well as the adequate threshold values with saving a significant amount of computing time which is independent from the number of thresholds. The proposed method is validated by illustrative examples, comparison with the Otsu´s method shows its efficiency.
Keywords :
image segmentation; particle swarm optimisation; Otsu method; binary particle swarm optimization; dynamic multilevel thresholding method; image segmentation; image thresholding; threshold values; Biomedical optical imaging; Computer science; Genetic algorithms; Image analysis; Image processing; Image segmentation; Nonlinear optics; Optical character recognition software; Particle swarm optimization; Text analysis;
Conference_Titel :
Bio-Inspired Computing, 2009. BIC-TA '09. Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-3866-2
Electronic_ISBN :
978-1-4244-3867-9
DOI :
10.1109/BICTA.2009.5338061
