Talk:Signal-to-noise ratio (imaging)

$\mu _{\text{sig}}$ and $\mu _{\text{bkg}}$ have exactly the same formula, thus yielding a zero signal; if that is not corrected it must be removed.Fgnievinski (talk) 01:20, 28 March 2010 (UTC)

I think they're meant to be taken over different regions (see the figure), but it's not at all clear from the text. I'm still trying to untangle what it says! GyroMagician (talk) 16:11, 28 March 2010 (UTC)

Oh, now I see! I agree with your interpretation. The current explanation is rather sloppy, IMHO. I'll fix that later. Fgnievinski (talk) 04:33, 29 March 2010 (UTC)

RMS noise is described as "the square root of the absolute value of the sum of variances" but the absolute value does not appear in the following formula, either as $|x|$ or as ${\sqrt {x^{2}}}$. —Preceding unsigned comment added by 130.102.119.10 (talk) 01:24, 10 March 2011 (UTC)

No absolute value is needed, as variances are positive. Dicklyon (talk) 01:02, 30 September 2019 (UTC)

All wrong

From the beginning, this article has had a misleading and inaccurate lead, from which a lot more junk follows. It needs a major rework. I don't know if I can get to it, but maybe if someone is willing to help that will kick me into gear. Anyone? Dicklyon (talk) 05:12, 25 August 2019 (UTC)

OK, I tried to make the lead sensible, but the rest of the article is not. It's basically an attempt to copy a particular method from this doc, from which the image was taken without permission and the algorithm was incorrectly inferred from the text. I think there's nothing good left here, so will take it to AfD. Dicklyon (talk) 00:12, 28 August 2019 (UTC)

It seems some authoritative sources (ISO standards) were removed: [1] fgnievinski (talk) 04:22, 28 August 2019 (UTC)

I added those back and removed most of the rest. Let me know if you see anything of value that should be restored. Dicklyon (talk) 01:01, 30 September 2019 (UTC)