The Equation of YUV to RGB

[egg126]

Hi, all

What's the Equation of IPP to implement the YUV to RGB

ippiYUV420ToRGB_8u_P3C3(const Ipp8u* const pSrc[3], Ipp8u* pDst, IppiSize imgSize);

There are difference of my result with IPP. So I want to know what's the equation of IPP to implementation...

Thanks for your reply.

[pvonkaenel]

Quoting - egg126

Hi, all

What's the Equation of IPP to implement the YUV to RGB

ippiYUV420ToRGB_8u_P3C3(const Ipp8u* const pSrc[3], Ipp8u* pDst, IppiSize imgSize);

There are difference of my result with IPP. So I want to know what's the equation of IPP to implementation...

Thanks for your reply.

I don't know how the internals are implemented, but if you're getting different results then you might not be using the correct conversion routine. Are you sure you have a YUV source and not a YCbCr source? If you're working with video then it's probably YCbCr.

Peter

[egg126]

Quoting - pvonkaenel

I don't know how the internals are implemented, but if you're getting different results then you might not be using the correct conversion routine. Are you sure you have a YUV source and not a YCbCr source? If you're working with video then it's probably YCbCr.

Peter

Yes, that's YUV Source, and the I find in ippiman, the Equation is:
R' = Y' + 1.140*V'
G' = Y' - 0.394*U' - 0.581*V'
B' = Y' + 2.032*U'

But my result is different, so I want to know How IPP implement this Equation in Integer Operation.

Also, I find the YCbCr to RGB is available. That's ippiYCbCrToRGB_8u_C3R
And the Equation is:

R' = 1.164*(Y' - 16) + 1.596*(Cr' - 128)
G' = 1.164*(Y' - 16) - 0.813*(Cr' - 128) - 0.392*(Cb' - 128)
B' = 1.164*(Y' - 16) + 2.017*(Cb' - 128)

And, at present, I want to know How to implement them(YUV2RGB, YCbCr2RGB) in Integer Operation.

Thanks very much...

[egg126]

Is there anybody know how to optimization this equation in Integer Operation.

R' = Y' + 1.140*V'
G' = Y' - 0.394*U' - 0.581*V'
B' = Y' + 2.032*U'

and

R' = 1.164*(Y' - 16) + 1.596*(Cr' - 128)
G' = 1.164*(Y' - 16) - 0.813*(Cr' - 128) - 0.392*(Cb' - 128)
B' = 1.164*(Y' - 16) + 2.017*(Cb' - 128)


And Iuse floating point operation, but the result is different with IPP, the gap is just 1, therefore, I think this is round error, however, I don't know, How IPP round this equation?

Thanks very much.

[Vladimir_Dudnik]

IPP use SSE optimized fixed point calculations in YUVToRGB conversion for 8-bit input and output data. This is much faster comparing with SSE floating point calculations (which will require integer to float and back conversion) but introduce rounding error.

Regards,
Vladimir