Simple pattern recognition

Hello all,

I want to be able to count predefined simple rectangle shapes on an image as shown like in this one: http://img7.imageshack.us/img7/2327/particles.png

Which is in my case to count all the blue pixels (they are ice-snow flake shadows in reality) in one of the column.

What is the way to automate this task, which library or technique should I study to tackle it.

Thanks.

···


Gökhan

You should check out the ndimage subpackage in scipy.

This tutorial should help you get started:

http://docs.scipy.org/doc/scipy/reference/tutorial/ndimage.html

The section on “segmentation and labeling” will be particularly useful for you.

Best,

-Tony

···

On Sep 16, 2009, at 8:22 PM, Gökhan Sever wrote:

Hello all,

I want to be able to count predefined simple rectangle shapes on an image as shown like in this one: http://img7.imageshack.us/img7/2327/particles.png

Which is in my case to count all the blue pixels (they are ice-snow flake shadows in reality) in one of the column.

What is the way to automate this task, which library or technique should I study to tackle it.

Right into the eye.

“Segmentation is the process of separating objects of interest from
the background.”

Once I finish this task, I should be able to count the occurrences of the shadowed instances so that I would have an idea regarding to their sizes.

···

On Wed, Sep 16, 2009 at 10:46 PM, Tony S Yu <tonyyu@…2705…66…> wrote:

On Sep 16, 2009, at 8:22 PM, Gökhan Sever wrote:

Hello all,

I want to be able to count predefined simple rectangle shapes on an image as shown like in this one: http://img7.imageshack.us/img7/2327/particles.png

Which is in my case to count all the blue pixels (they are ice-snow flake shadows in reality) in one of the column.

What is the way to automate this task, which library or technique should I study to tackle it.

You should check out the ndimage subpackage in scipy.

This tutorial should help you get started:

http://docs.scipy.org/doc/scipy/reference/tutorial/ndimage.html

The section on “segmentation and labeling” will be particularly useful for you.

Best,

-Tony


Gökhan