Image segmentation based on single seed region growing algorithm

Joint Authors

Hadi, Jullanar M.
Salman, Nasir H.

Source

ZANCO Journal of Pure and Applied Sciences

Publisher

Salahaddin University-Erbil Department of Scientific Publications

Publication Date

2016-06-30

Country of Publication

Iraq

No. of Pages

7

Main Subjects

Information Technology and Computer Science

English Abstract

In this paper, image segmentation based on single seed region growing algorithm is proposed to implement image segmentation, region boundary detection, region extraction and region information tasks for gray scale images.

The proposed method is used to segment number of selected regions (N) in the original image, this started with choosing arbitrary seed point inside each selected region, set intensity value equal to 10% of the (Max-Min) intensity value of the original image.

Then region growing algorithm used to test the entire pixels neighbor to the seed point whether they satisfy the intensity range motioned above or not.

If they then associated in one region, otherwise it labeled as boundary pixels.

This approach has been tested on many medical images to achieve region segmentation with closed boundary, edge map, calculate the minimum, maximum and average intensity of each region, and finally calculate the number of all associated pixels of the segmented region.

Our proposed method minimize the computation time.

In addition to the precisely output of segmented and extracted regions, another benefit comes from easy implementation of this method.

Data Type

Conference Papers

Record ID

BIM-786722

• APA
• MLA
• AMA