DocumentCode
626253
Title
Gel Electrophoresis Image Segmentation with Kapur Method Based on Particle Swarm Optimization
Author
Ahmad, Abd Rahman ; Hussain, Z. ; Ahmad, Farhan ; Noor, Mohd Halim Mohd ; Yahaya, S.Z.
Author_Institution
Fac. of Electr. Eng., Univ. Teknol. MARA, Shah Alam, Malaysia
fYear
2013
fDate
5-7 June 2013
Firstpage
393
Lastpage
396
Abstract
One of the important tool in genomic analysis is Gel Eletrophoresis. It is a tool that is routinely used in genetics, microbiology, forensics, molecular biology and biochemistry. GE is also used in separating DNA, RNA and protein molecules by using electric field applied to a gel matrix. This paper describes the application of Particle Swarm Optimization (PSO) that is a population-based optimization technique based on the sociological interaction associated with bird flocking using the Kapur thresholding method to segment the DNA bands from the background. PSO is employed to achieve the optimum threshold levels selection. In addition, PSO greatly reduces the computational time. Median filter is used prior image segmentation to remove noise and ambiguous pixels. The experimental results show that the application the optimization technique on Kapur method successfully produces good separation of DNA bands from the background.
Keywords
DNA; biology computing; image denoising; image segmentation; median filters; particle swarm optimisation; DNA band segmentation; GE; Kapur thresholding method; PSO; ambiguous pixel denoising; bird flocking; computational time; gel electrophoresis image segmentation; genomic analysis; median filter; noise removal; particle swarm optimization; population-based optimization technique; sociological interaction; threshold level selection; DNA; Histograms; Image analysis; Image segmentation; Noise; Optimization; Particle swarm optimization; Gel electrophoresis (GE); Kapur method; Multilevel Thresholding; Particle Swarm Optimization (PSO);
fLanguage
English
Publisher
ieee
Conference_Titel
Computational Intelligence, Communication Systems and Networks (CICSyN), 2013 Fifth International Conference on
Conference_Location
Madrid
Print_ISBN
978-1-4799-0587-4
Type
conf
DOI
10.1109/CICSYN.2013.60
Filename
6571397
Link To Document