Global Image Understanding from Local Hints

		/vol03/paper2/	© Copyright 1996
		Volume 03	Received: Accepted:	---- ----

Global Image Understanding from Local Hints Jacques Blanc-Talon
Abstract
	This paper addresses the problem of finding structural information within fractal images so as to enhance their symbolical encoding. Multifractal edge-detection is considered as a reference for a fractal region segmentation algorithm. Regions are compared with the edges by using a Hausdorff distance operator. Curves qualifying the result according to the algorithm parameters are derived. The space spanned by the parameter vector is analyzed with the purpose of tuning the parameters so as to yield a better segmentation. In the same time, the parameter space provides the needed structural information.

Full Text

Multimedia Links
(none)

Reference Links
(none)

Citation Reference

Get viewers
for PS & PDF

[CI Editor] [Site Manager]