Manuscript Number : CSEIT172493
Optimized connected Median filter using Particle Swarm Optimization
Authors(2) :-M. Rajalakshmi, Dr. P. Subashini In the image processing Median filter were used to remove the impulse noise. It preserves the edges for the next level operations such as segmentation and object recognition. The present paper deals with the preprocessing of chili x-ray images. The researcher has already preprocessed the chili x-ray images by adopting the Average filter, Median filter, Wiener filter, Gamma intensity correction, CLAHE, 4-connected Median filter and weighted 4-connected median filter. The result of the above stated preprocess methods to contain noise in the pixels, hence it is considered as unsuitable for next level operations. To remove such noise from the image, this paper contributes a precise and well-organized algorithm. The proposed noise removal algorithm replaces the noisy pixels by using '4-connected median value' and replaces the remaining pixels by using 'weighted 4-connected median value' in the selected window. The replacement of middle pixel value in 4-connected median filter is done through particle swarm optimization algorithm. Peak Signal to Noise Ratio used as the fitness function in the particle swarm optimization algorithm. The performance measures were taken for all the noise removal algorithm. Among the various results obtained, the proposed algorithm works better than others.
M. Rajalakshmi chili x-ray image, impulse noise, particle swarm optimization, weighted and 4-connected median filter, Optimized connected Median filter, Particle Swarm Optimization, Peak Signal to Noise Ratio. Publication Details Published in : Volume 2 | Issue 5 | September-October 2017 Article Preview
Department of Computer Science, Avinashilingam Institute for Women, Coimbatore, India
Dr. P. Subashini
Department of Computer Science, Avinashilingam Institute for Women, Coimbatore, India
Date of Publication : 2017-10-31
License: This work is licensed under a Creative Commons Attribution 4.0 International License.
Page(s) : 19-26
Manuscript Number : CSEIT172493
Publisher : Technoscience Academy