Open AccessMultilevel Image Thresholding for Image Segmentation using Hybrid Algorithm
Author(s) -
M.S.R. Naidu,
Pardeep Kumar
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a4847.119119
Subject(s) - artificial intelligence , image segmentation , thresholding , pattern recognition (psychology) , cuckoo search , segmentation based object categorization , computer science , scale space segmentation , computer vision , entropy (arrow of time) , image texture , segmentation , balanced histogram thresholding , mathematics , image processing , algorithm , image (mathematics) , particle swarm optimization , physics , quantum mechanics , histogram equalization
Image thresholding is an extraction method of objects from a background scene, which is used most of the time to evaluate and interpret images because of their advanced simplicity, robustness, time reduced, and precision. The main objective is to distinguish the subject from the background of the image segmentation. As the ordinary image segmentation threshold approach is computerized costly while the necessity for optimization techniques are highly recommended for multi-tier image thresholds. Level object segmentation threshold by using Shannon entropy and Fuzzy entropy maximized with hGSA-PS. An entropy maximization of hGSA-PS dependent multilevel image thresholds is developed, where the results are best demonstrated in PSNR, misclassification, structural similarity index and segmented image quality compared to the Firefly algorithm, adaptive cuckoo search algorithm and the search algorithm gravitational.