Re: possible error in docs?

Posted by Avital Steinberg on Sep 26, 2016; 12:37pm
URL: http://imagej.273.s1.nabble.com/possible-error-in-docs-tp5017241p5017242.html

Hi Aryeh,
The area of an ellipse is: PI*(major/2)*(minor)/2

So the roundness would be: Area/(PI*major^2) =( 4*(major/2)(minor/2) )/
PI*major^2

And the 4 cancels out  - what you get for the roundness is minor/major.
This is 1 for a perfect circle.

Does this help?
Avital

On Mon, Sep 26, 2016 at 3:07 PM, Aryeh Weiss <[hidden email]> wrote:

> I was looking for how ImageJ calculates roundness, and I found the
> following:
> /
> Shape descriptors/ Calculates and displays the following shape descriptors:
>
>  *
>    /Circularity/ /4/π/ × [/Area/][/Perimeter/]^2 / with a value of 1.0
>    indicating a perfect circle. As the value approaches 0.0, it
>    indicates an increasingly elongated shape. Values may not be valid
>    for very small particles. Uses the heading*Circ*.
>  *
>    /Aspect ratio/ The aspect ratio of the particle’s fitted ellipse,
>    i.e., [/Major/ /Axis/][/Minor/ /Axis/]. If */Fit Ellipse/* is
>    selected the*Major* and *Minor* axis are displayed. Uses the
>    heading*AR*.
>  *
>    /Roundness/ 4 × [/Area/]/π/ × [/Major/ /axis/]^2 or the inverse of
>    /Aspect Ratio/. Uses the heading *Round*.
>
> https://imagej.nih.gov/ij/docs/guide/146-30.html
>
> I think that the 4  in the Roundness  definition is not correct, and it
> should be Area/[pi*(Major Axis)^2],
> and not 4 x Area /[pi*(Major Axis)^2]
>
> Am I correct?
>
> --aryeh
>
> --
> Aryeh Weiss
> Faculty of Engineering
> Bar Ilan University
> Ramat Gan 52900 Israel
>
> Ph:  972-3-5317638
> FAX: [phone]
>
>
> --
> ImageJ mailing list: http://imagej.nih.gov/ij/list.html
>

--
ImageJ mailing list: http://imagej.nih.gov/ij/list.html