Matlab R2013b version and later contain FREAK implementation.

You can access to this descriptor using "extractFeature" function with the 'Method' argument set to 'FREAK'.

[features, points] = extractFeatures(Image, points,'Method','FREA:');

Here is a link describes and provides MEX interface for MATLAB to the implementation for FREAK features in OpenCV. I haven't tried myself as yet. Will try it soon and share my thoughts. You may want to look at it.

http://dovgalecs.com/blog/freak-descriptor-in-matlab/

Best.

you can use this cod

STATS = regionprops(BW, properties) measures a set of properties for each connected component (object) in the binary image, BW. The image BW is a logical array; it can have any dimension.

to detect features

Dear Madhav Sigdel ,

thanks for Help

i cant download it

Dear Anwar Al-Saleh ,

I need FREAK code not any other descriptor

Matlab R2013b version and later contain FREAK implementation.

You can access to this descriptor using "extractFeature" function with the 'Method' argument set to 'FREAK'.

[features, points] = extractFeatures(Image, points,'Method','FREA:');