[ITK-users] HistogramEqualization in ITK

[Francois Budin]

Hello Wang,

One good way to explore the parameters to figure out which set gives you
the result you want would be to write a short Python script:
reader=itk.ImageFileReader[itk.Image[itk.UC,2]].New(FileName="/home/fbudin/Downloads/chest.png")
myFilter=itk.AdaptiveHistogramEqualizationImageFilter.New(reader)
for alpha in range(0,11):
  for beta in range(0,11):
    myFilter.SetAlpha(alpha*.1)
    myFilter.SetBeta(beta*.1)
    filename="/tmp/myFilter"+str(alpha)+"_"+str(beta)+".png"
    itk.ImageFileWriter.New(hm,FileName=filename).Update()

I was not able to generate an image that looked exactly like the "opencv"
image you sent, but that may be due to:
-The implementation of this algorithm in OpenCV is different
-The difference of the output is only due to different visualization
parameters (Window/Level settings that are different for the different
images).

Hope this helps,
Francois

On Thu, Apr 13, 2017 at 8:25 AM, wangtaoiz <wangtao_ at sjtu.edu.cn> wrote:

> Dear all
>   I want to use itk::AdaptiveHistogramEqualizationImageFilter to do a
> HistogramEqualization filter on a image as follow:
> <http://itk-users.7.n7.nabble.com/file/n38108/snipaste20170413_200959.png>
> So I set the parameters SetAlpha(0.5), SetBeta(0.5), the result is as
> follow:
> <http://itk-users.7.n7.nabble.com/file/n38108/snipaste20170413_201446.png>
> but actually the result I want is showed as follow (which is generated by
> opencv cvEqualizeHist() function):
> <http://itk-users.7.n7.nabble.com/file/n38108/snipaste20170413_201132.png>
> So I want to ask you if I can get that HistogramEqualization result by ITK?
>
> Thanks a lot
> Wang
>
>
>
> --
> View this message in context: http://itk-users.7.n7.nabble.
> com/HistogramEqualization-in-ITK-tp38108.html
> Sent from the ITK - Users mailing list archive at Nabble.com.
> _____________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Kitware offers ITK Training Courses, for more information visit:
> http://www.kitware.com/products/protraining.php
>
> Please keep messages on-topic and check the ITK FAQ at:
> http://www.itk.org/Wiki/ITK_FAQ
>
> Follow this link to subscribe/unsubscribe:
> http://public.kitware.com/mailman/listinfo/insight-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-users/attachments/20170413/f4f706c4/attachment.html>