Hi Nisreen,

Sorry to start answering your question with a question. Similar in what sense? Shape, color, curvature? Generally speaking, histogram matching could be of use. Other classification techniques such as SVM, RF, NN are also widely used in the image retrieval domain and are a good venue to explore.

Hi Mr. Cheddad,

I have a database of cerebral DSA images of scaular aneurysms, attached image is an example. I want to build Content Based Image Retrieval  system which enable to retrieve images from a database.

I think that shape features are good to retrieve the images, and I want to know more about this?

What are other features could be used?

Features extraction algorithm?

Features matching?

images are Grayscale.

Check the following page,  MATLAB code is apparently available as well.

Good luck!

http://vh.icg.tugraz.at/index.php?content=topics/beyondshape.php

Hi...

I think these links will help you.

http://link.springer.com/chapter/10.1007%2F978-3-642-38899-6_12

http://researcher.ibm.com/researcher/files/us-stf/paper738.pdf

A survey related to different shape features available in literature can be found here:

https://hal.archives-ouvertes.fr/hal-00446037/document

Thanks

Vipul

@ Mr. Cheddad

@ Mr. Sharma

Thank you for your answers

In order to design features for image retrieval, I think it's very important to first understand what makes two of these images similar.  I have no knowledge of these types of images so I can't help you with this, but there could be many possibilities, such as histograms of the image, shapes of the branches, number of branches, etc.  It's always better to be able to understand the basic idea of what these images similar and then design features to encode this information.