Multiresolution Segmentation of Natural Images: From linear to Non-Linear Scale-Space Representations

In this paper, we introduce a framework that merges classical ideas borrowed from scale-space and multi-resolution segmentation with non-linear partial differential equations. A non-linear scale-space stack is constructed by means of an appropriate diffusion equation. This stack is analyzed and a tree of coherent segments is constructed based on relationships between different scale layers. Pruning this tree proves to be a very efficient tool for unsupervised segmentation of different classes of images (e.g. natural, medical ...). This technique is light on the computational point of view and can be extended to non-scalar data in a straightforward manner.


Published in:
IEEE Transactions on Image Processing, 13, 8, 1104-1114
Year:
2004
Keywords:
Laboratories:




 Record created 2006-06-14, last modified 2018-03-17

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)