accurately cropping image via saliency map

I'm using Itti's saliency map via the matlab port. So given an example image, I could get a salient map as shown below(compare the saliency map with the color photo): enter image description here

The problem is that although the algorithms pinpoints roughly where the salient object is, it fails to reliably get the dimensions of the object. Thus, if I want my program to automatically crop out the most salient object in an image, I can only speculate the dimensions based on the shape of the salient map for the object. This is pretty unreliable since the salient shape could vary greatly.

Are there more reliable methods to do this?

asked Dec 01 '11 at 18:45

mugetsu
233●21●24●31

edited Dec 01 '11 at 18:45

Maybe looking at this can help: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.174.4259&rep=rep1&type=pdf ?

(Dec 05 '11 at 08:40) Andreas Mueller

thanks, I'll take a look

(Dec 07 '11 at 14:45) mugetsu

Subscription:

Once you sign in you will be able to subscribe for any updates here

Tags:

matlab ×41
image-processing ×27
computer-vision ×22

Asked: Dec 01 '11 at 18:45

Seen: 1,109 times

Last updated: Dec 07 '11 at 14:45

accurately cropping image via saliency map

Subscription:

Related questions