Abstract—Segmentation of image has wide application in the field of medical, military, surveillance, etc. This work segments medical resonance image for detection of tumor in brain where work identify three parts in the image. First is skull, second is brain and third is tumor. Presented paper includes description of image segmentation in unsupervised manner where proposed model identify all segments of image without any training. Here, wiener filter preprocessed the input images by removing unwanted information from the image matrix. Filtered image then passed in Intelligent Water Drop (IWD) genetic algorithm for finding representative pixel value sets of image segments. Graphical water drop movement in the IWD algorithm has representative pixels value set selection accuracy. Experiment is performed in real dataset of brain tumor and detection is done by taking reference of ground truth images. Proposed model evaluated average precision value 0.98 and average accuracy 96%. Hence, when results is compared with existing methods then it is obtained that proposed segmentation work increased the segmentation evaluation parameter values.
Index Terms—Brain tumor detection, digital image processing, genetic algorithm, image segmentation.
Ashish Kumar Dehariya and Pragya Shukla are with Computer Engineering Department, Institute of Engineering and Technology, Devi Ahilya Viswavidhyalay, Indore, India (e-mail: ashishdehariya.cat@gmail.com, pragyashukla_iet@yahoo.co.in).
[PDF]
Cite:Ashish Kumar Dehariya and Pragya Shukla, "Brain Image Segmentation to Diagnose Tumor by Applying Wiener Filter and Intelligent Water Drop Algorithm," International Journal of Computer Theory and Engineering vol. 13, no. 3, pp. 84-90, 2021.
Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
