Home Research Teaching Forums Staff Contact Search Intranet
 
 

Research Projects
Past and current research projects in the areas of virtual reality, media processing and web-based information systems.

Student and Thesis Projects, Jobs
Available student and thesis projects and job offers.

Scientific Publications
Details and downloads publications, technical reports and thesis papers.

  

Image Segmentation Via Iterative Geodesic Averaging

by Asmaa Hosni, Michael Bleyer, Margrit Gelautz

Abstract

We present a simple and fast method for performing unsupervised segmentation. Our method works by centering a square window on each pixel of the input image. Each pixel is then assigned to a new color which is computed by averaging the pixel colors inside the window. The idea is that if this averaging operation is repeated a few times then we should obtain an image in which pixels of the same color surface are assigned to the same (or at least to very similar) color values. Consequently, the desired color segments are formed by groups of spatially neighboring pixels that share the same color in the convolved image.
Obviously, our method would deliver poor performance if the averaging operation is applied in a naive manner, as pixel colors of different segments would be mixed. To overcome this problem, we propose to compute a geodesic weight mask that regulates a pixel's influence in the averaging operation. A pixel's weight in the window is determined by computing the geodesic distance to the center pixel. In other words, we enforce that a pixel obtains high influence only if there exists a path to the center pixel along which the color does not change significantly (connectivity). The proposed method is evaluated on some widely used test images. Our method seems to produce accurate segmentation results and to capture object outlines correctly. We show by quantitative evaluation that our segmentation algorithm outperforms two competing segmentation methods.

Download

Follow the link below to download the document. To view PDF documents, you need Acrobat Reader. For PostScript files, use either Acrobat Distiller (commercial) or GhostScript (free).

Details

Image Segmentation Via Iterative Geodesic Averaging
TR Number: TR-188-2-2009-09
First Published: 2009
Publishing History: International Conference on Image and Graphics (ICIG) 2009.
Keywords: Color Segmentation, Geodesic Distance Transform;
 
 

 

 

 

Print this Page
Display a printer-friendly version of this page.

  

 

 

 

Interactive Media Systems Group
Institute for Software Technology and Interactive Systems
Vienna University of Technology

Favoritenstrasse 9-11/188/2
A-1040 Vienna, Austria

http://www.ims.tuwien.ac.at/