On Jun 12, 10:05=A0am, AJ <arandal...@[EMAIL PROTECTED]
> wrote:
> On Jun 11, 6:12 pm, aruzinsky <aruzin...@[EMAIL PROTECTED]
> wrote:
>
>
>
>
>
> > On Jun 9, 5:38 am, AJ <arandal...@[EMAIL PROTECTED]
> wrote:
>
> > > Hi All,
>
> > > I have an image which is very blocky (image can be seen
athttp://img22=
2.imageshack.us/my.php?image=3Ddegradedimagesh2.png) and
> > > would like to try and improve it's quality as much as possible.
>
> > > I understand that the image is of such a poor quality that I do not
> > > expect any huge improvements - that is not my aim, my aim is to see
if=
> > > it can be improved at all, and if so, which method(s) could yield
the
> > > best results.
>
> > > So far I have tried some iterative restoration techniques such as
> > > Richardson-Lucy deconvolution and Blind deconvolution - both have
> > > proved to give a slight improvement.
>
> > > I was hoping someone would have some other suggestions as to how I
> > > could possibly improve the image.
>
> > > Just in case understanding how the image was degraded in the first
> > > place might help lead to a good suggestion for improvement
algorithms,=
> > > I created the image using the following steps:
>
> > > * 8x8 Sub-Block and DCT image
> > > * store top 2 coefficients from each sub-block
> > > * use these to create a new image
>
> > > Many thanks,
>
> > > AJ
>
> > Okay, this improved result,
>
> >http://www.general-cathexis.com/images/degradedimagesh2_4.jpg
>
> > , was obtained by incor****ating some information from the cosine half
> > wave within each 8 pixel interval. =A0The values are all of the same
> > sign within each half interval so I can get a fairly natural looking
> > image by reducing to 128 x 64 using a box kernel. =A0Whereas, a 64 x
64
> > reduction averages the half cosine to zero, the 128 x 64 reduction
> > sort of makes it a half square wave.
>
> > Here is the reduced image in 16 bit format,
>
> >http://www.general-cathexis.com/images/degradedimagesh2_Reduced.png
>
> > , which I enlarged 8X using a proprietary nonlinear method and then
> > reduced the width 0.5X using box interpolation.
>
> Just a quick thank you to everyone who has made the effort to
> experiment with my degraded image, I really appreciate it! :)
>
> I have measured the PSNR of each submitted (including some suggestions
> from the 'comp.compression' group, which can be found here - 'http://
> groups.google.com/group/comp.compression/browse_thread/thread/
> 7c7b9058de482155#'), against the original copy of the image. =A0The
> results are as follows:
>
> Aruzinsky (http://www.general-cathexis.com/images/
> degradedimagesh2_2.png) =A0- =A025.81 dB
> Aruzinsky (http://www.general-cathexis.com/images/
> degradedimagesh2_3.png) =A0- =A025.51 dB
> Aruzinsky (http://www.general-cathexis.com/images/
> degradedimagesh2_4.jpg) =A0- =A027.91 dB
> pisz_na =A0(http://i287.photobucket.com/albums/ll123/ememek/r23.png)
=A0-
> 19.27 dB
> jacko (http://indi.hpsdr.com/degradedmagesh11.png)
=A0- =A020.05 dB
> jacko (http://indi.hpsdr.com/image2.png)
=A0- =A019.37 dB
> jacko (http://indi.hpsdr.com/diffusiontop.png)
=A0- =A022.73 dB
> mine (AJ) (http://i287.photobucket.com/albums/ll146/arandall85/
> interpolated_iterated_image.png) 24.55 dB
>
> If there was a prize, you would get it Aruzinsky! =A0The only issue I
> have got is that ideally I would like to implement the technique
> described in Matlab, since the rest of my image processing techniques
> are written using it.
>
> Does anyone have any idea how I could go about converting Arunzinsky's
> method (shown below) into a format Matlab would understand?:
>
> [snip]"was obtained by incor****ating some information from the cosine
> half
> wave within each 8 pixel interval. =A0The values are all of the same
> sign within each half interval so I can get a fairly natural looking
> image by reducing to 128 x 64 using a box kernel. =A0Whereas, a 64 x 64
> reduction averages the half cosine to zero, the 128 x 64 reduction
> sort of makes it a half square wave."[snip]
>
> Many thanks,
>
> AJ- Hide quoted text -
>
> - Show quoted text -
I can't help you with matlab, but I think you are reading too much
into this. Each pixel of the 128 x 64 image was produced by averaging
4 x 8 pixels corresponding to half your 8x8 block in the input image.
That should be easy enough to program in any language.
|
