B. Shanthi Gowri, Gnanambal Ilango
Department of Mathematics
Sri Krishna College of Engineering and Technology
Coimbatore, 641 008, INDIA
Department of Mathematics,
Government Arts College,
Coimbatore, 641 018, INDIA

Abstract. One of the important techniques in image processing is image segmentation. It plays a vital role in the field of medicine for segmentation of tumor from the medical images. One of the useful methods of segmentation is region growing. In this article, a novel region growing segmentation algorithm is proposed based on the neighbourhoods of different new metric topology to segment tumor from brain magnetic resonance images (MRI). The quality of the segmented images is measured by the traditional performance evaluation measures Accuracy, Sensitivity, Specificity, PSNR and the new evaluation measure entropy.

Received: February 15, 2016

AMS Subject Classification: 54A99

Key Words and Phrases: metrics, metric topology, neighbourhoods, region growing segmentation

Download paper from here.

Google Scholar; DOI (International DOI Foundation); WorldCAT.

This work is licensed under the Creative Commons Attribution International License (CC BY).