since 2019-10-13
This python project implements the algorithm described in "Real-Time Video Abstraction" (Winnemöller, Olsen, & Gooch, 2006).
The algorithm includes the following steps.
-
Convert the input image from RGB space to CIELab space. "color.rgb2lab" is used to do the conversion, which separates the luminance channel (L) from the chrominance channel (a, b).
-
Bilateral filter.
-
Color quantization of L channel.
-
DoG Edge detection.
-
Color space conversion.