Extracting salient curves from images
Software Download Page
For Aim@Shape Members
Department of Computer Science and Applied Mathematics
Description
This software implements the salient
curves extraction method based on the paper by Alter and Basri. The Saliency
Network proposed by Shashua and Ullman (1988) is a well-known approach to the
problem of extracting salient curves from images while performing gap
completion. The Saliency Network is attractive for several reasons. First, the
network generally prefers long and smooth curves over short or wiggly ones.
While computing saliencies, the network also fills in gaps with
smooth completions and tolerates noise. Finally, the network is locally
connected, and its size is proportional to the
size of the image.
For the paper click here PDF.
Reference
Alter, T.D., Basri, R. – "Extracting Salient Curves from Images: An Analysis of the Saliency Network" IJCV(27), No. 1, March 1998, pp. 51-69.
A. Shashua and S. Ullman. Structural Saliency: the Detection of Globally Salient Structures Using a Locally Connected Network. In Proc. of the International Conference on Computer Vision (ICCV), Dec. 1988, Tarpon Springs, Florida. (Available here)
Results sample
Input Saliency map Most salient curve
Download
To Download Software click here and for the manual click here.
Acknowledgment
Web page and Linux modifications by :Sharon Alpert