Hi all,
sorry about the long title :-)
actually my question is very simple:
I'm wondering what's the best method to extract the high values from a
tract density image in order to get a threshed binary image.
The main issue here is finding the optimal threshold that will remove the
pixels which represent the low density locations in the image.
In that way, just the high density values in the image will be maintained.
What I've done till now are the next steps:
a. moving to a logarithmic scale
b. calculating the median from a (the median is the threshold)
c. remove pixels lower then the median from b
d. turning back to a decimal scale
e. show the binary image
I manipulated that algorithm and the result is only half of the initial
number of pixels were removed (and I want more) ...
I'm open to new, creative or really any idea ...
Best,
Hila
------------------------------------------------------------------------------
Live Security Virtual Conference
Exclusive live event will cover all the ways today's security and
threat landscape has changed and how IT managers can respond. Discussions
will include endpoint security, mobile security and the latest in malware
threats. http://www.accelacomm.com/jaw/sfrnl04242012/114/50122263/
_______________________________________________
mitk-users mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/mitk-users
