Open AccessSegmentation of Blood cell Images using Hybrid K-means with Cluster Center Estimation Technique
Author(s) -
A A Mariena,
J. G. R. Sathiaseelan
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.b1026.0982s1119
Subject(s) - centroid , initialization , image segmentation , artificial intelligence , segmentation , computer science , cluster analysis , pattern recognition (psychology) , scale space segmentation , histogram , segmentation based object categorization , k means clustering , cluster (spacecraft) , image (mathematics) , computer vision , region growing , mean shift , programming language
Image segmentation plays a predominant role in the field of image processing. k- Means clustering is one of the most powerful algorithms for medical image segmentation. However, the randomly selected cluster number and initial centroids cause inconsistency in the image segmentation results. To overcome this limitation we have proposed a combined approach namely Hybrid K-Means with Cluster Center Estimation (HKMCCE) for image segmentation. The proposed technique use histogram peaks of the image to find the cluster number and initial cluster centers automatically.Moreover, it requires lessuser interaction to determine k-means initialization parameters. The performance of the proposed technique is compared with traditional segmentationmethods and it yields better results with less execution time.