Re: (statistics)how to make date more like Laplacian distribution?

"walala" <[EMAIL PROTECTED]>

> Yeah, the error for integer hardware implementation comes from 1)
round-off
> floating-point transform basis matrix to integer matrix; 2) after
> quantization, there is a round operation... I guess this one is the big
> lossy step...

Probably, maybe not ... depending how big the error is and at what bitrate
you are coding. 1 might be small, but it's avoidable.

> I looked into BinDCT... and I was amazed that they did not use
> quantization/round-off as appeared in JPEG standard to do this big lossy
> step...

They call the transform BinDCT, not the coders they build with it.

> instead, they use EZW like progressive transmission coefficient
> method to do the packadization of the coefficients...  silimar to
> JPEG2000... then the result is better than JPEG coding. I have no way of
> telling if it is good or not... it is difficult to judge a research if the
> comparison basis is shifted... But I think that packadization
> step(equivalent to quantization and scaning in JPEG) is of high
> complexity... right?

They have compared the transform to DCT with a drop in replacement in
standard JPEG ... given what you said I doubt your DCT is standard compliant
though, so that still doesnt allow you to make a real comparison with your
own transform.

http://thanglong.ece.jhu.edu/Tran/Pub/bindct-IEEESP.pdf
Software is here:
http://thanglong.ece.jhu.edu/~jliang/software.html

> Marco, have you tried the "coefficient correction" method in that paper to
> make received coefficient statistically better? I tried ... but failed to
> get any "better" result... in fact, the PSNR is even worse...


No, Im taking it on faith.

Try this for PSNR numbers :
"Biased Reconstruction for JPEG Decoding"

> Here is my code: first a function to compute the bias for each 8x8 block.
Q
> is the quantization table... x is the received coefficients(not
dequantizaed
> yet...)  output y is also in un-dequantized coefficient domain... both x,
y,
> Q are 8x8 in size.... I use the equations in that paper...

Working with unquantized coefficients will only work as long as you have a
constant multiplier for the entire image of course.

> function y=mybias(x, Q)
> sigma=abs(x.*Q);

That is a strange way of calculating variance ... what exactly are you
trying to accomplish there?

> It is interesting to me that why it does not work as claimed...

Dont forget BTW ... DC does not have a zero centered laplacian distribution.

Marco