How can I extract sweat pores from a 1000 dpi fingerprint image using difference of Guassian approach?

I am working on a fingerprint recognition system, I need to extract pores which are present in the ridges.During my research I read that a blob detection technique can separate the pores from the ridges.However when I am applying a Gaussian Filter, it is smoothing the image. Also the DoG results in another similar image. If this is the right approach then where am I going wrong?

[Ashish Uthama]

A sample image might help...

[researcher]

Answer 1

[Image Analyst]

Well, you're using the wrong sigmas. Put them into a loop over a bunch of values and save the images and see what combination gives you the best image. I attach my DoG filter but with R2015a there is a new imgaussfilt() function that you can use.

[researcher]

Thanks but still am unable to achieve desired outcome. I am getting the gray colour variations throughout.

<<

>>

[researcher]

while I am looking for this pattern

[researcher]

Can you please tell me the range of sigma which retains the black and white colour in the original image?

[researcher]

I did some changes and got the following result.The DoG is still not satisfactory.Can somebody point the mistake

<<

>>