All notes


Unsharp masking, usm

The unsharp masking technique comes from a publishing industry process in which an image is sharpened by subtracting a blurred (unsharp) version of the image from itself. Do not be confused by the name of this filter: an unsharp filter is an operator used to sharpen an image. $$ I_{highpass} = I - G * I $$ $$ I_{sharpened} = I + k\cdot I_{highpass}$$

An alternative way is using the negative Laplacian operator to extract the highpass information.

Sharpen RGB images

For a truecolor (RGB) image, converts the image to the L*a*b* colorspace, applies sharpening to the L* channel only, and then converts the image back to the RGB colorspace.


'Radius' - Standard deviation of the Gaussian lowpass filter. Defaults to 1. It affects the sharpening range / neighborhood.
'Amount' - Strength of the sharpening effect. Defaults to 0.8.
'Threshold' - Minimum contrast required for a pixel to be considered an edge pixel. Scalar in [0 1]. Defaults to 0. Higher values (closer to 1) allow sharpening only in high-contrast regions, such as strong edges, while leaving low-contrast regions unaffected.