Please use this identifier to cite or link to this item: http://dspace.dtu.ac.in:8080/jspui/handle/repository/15094
Title: IMAGE SEGMENTATION USING PARTICLE SWARM OPTIMIZATION AND HARMONY SEARCH ALGORITHM
Authors: SETH, MANSI
Keywords: IMAGE SEGMENTATION
PARTICLE SWARM OPTIMIZATION
HARMONY SEARCH ALGORITHM
HARMONY MEMORY
BERKLEY DATA
Issue Date: Sep-2016
Series/Report no.: TD NO.2372;
Abstract: Segmentation holds a very important place in the field of Image Processing. It is a technique used to divide an image into segments which correlate with the real world. The regions having common characteristics are grouped together and are thus differentiated from other regions of the image making the image more clear and distinguishable. It also helps to differentiate the foreground and background of the image thus helping to analyze the image better. Segmentation can be performed by variety of evolutionary algorithms. In the present work Particle Swarm Optimization and Harmony Search Algorithm have been applied. PSO is an evolutionary computational technique which imitates the social behavior of bird flock. It is use to optimize variety of computational problems. Harmony Search algorithm is a population based algorithm which imitates the music improvisation process. It consists of Harmony memory which is initialized with initial population which are further updated and improvised until a termination criteria is met. The combination of the above two algorithms increases the convergence rate and accuracy of the result of the segmentation with low computational overhead. Finally the Berkley data set is used to to display the result of the algorithm.
URI: http://dspace.dtu.ac.in:8080/jspui/handle/repository/15094
Appears in Collections:M.E./M.Tech. Computer Engineering

Files in This Item:
File Description SizeFormat 
mansi_thesis (1).PDF2.4 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.