<p>In <a href="https://github.com/mlpack/mlpack/pull/683#discussion_r66470019">src/mlpack/methods/edge_boxes/feature_extraction_impl.hpp</a>:</p>
<pre style='color:#555'>> + table(i) = i / 1024.0;
> +
> + if (table(i) > y0)
> + table(i) = 116 * pow(table(i), 1.0/3.0) - 16.0;
> + else
> + table(i) = table(i) * a;
> +
> + table(i) = table(i) * maxi;
> + }
> +
> + MatType rgb2xyz(3,3);
> + rgb2xyz(0,0) = 0.430574; rgb2xyz(0,1) = 0.430574; rgb2xyz(0,2) = 0.430574;
> + rgb2xyz(1,0) = 0.430574; rgb2xyz(1,1) = 0.430574; rgb2xyz(1,2) = 0.430574;
> + rgb2xyz(2,0) = 0.430574; rgb2xyz(2,1) = 0.430574; rgb2xyz(2,2) = 0.430574;
> +
> + //see how to calculate this efficiently. numpy.dot does this.
</pre>
<p>Here is the implementation of <a href="http://www.mathworks.com/matlabcentral/fileexchange/36433-stereo-testbed-v0-1/content/ALGORITHMS/3DStereoDisp/msseg/RGB2Luv.m">matlab</a>, if we want speed, I think we better make use of the operations provided by armadillo, because armadillo do a lot of heavy optimization on matrix operations(matlab codes show us how to vectorize it)</p>
<p style="font-size:small;-webkit-text-size-adjust:none;color:#666;">—<br />You are receiving this because you are subscribed to this thread.<br />Reply to this email directly, <a href="https://github.com/mlpack/mlpack/pull/683/files/9d85b64c6c6bdff608331195351d09abf56cfc96#r66470019">view it on GitHub</a>, or <a href="https://github.com/notifications/unsubscribe/AJ4bFN4Z6kZJxoNy9TTQ0vY-8XdBwV-iks5qKDkugaJpZM4IvUrl">mute the thread</a>.<img alt="" height="1" src="https://github.com/notifications/beacon/AJ4bFBRQbTxd3qy9JAWqmNVxgKBFQ9Thks5qKDkugaJpZM4IvUrl.gif" width="1" /></p>
<div itemscope itemtype="http://schema.org/EmailMessage">
<div itemprop="action" itemscope itemtype="http://schema.org/ViewAction">
<link itemprop="url" href="https://github.com/mlpack/mlpack/pull/683/files/9d85b64c6c6bdff608331195351d09abf56cfc96#r66470019"></link>
<meta itemprop="name" content="View Pull Request"></meta>
</div>
<meta itemprop="description" content="View this Pull Request on GitHub"></meta>
</div>