Still Image Colorization |
|
| This is a cource project of ECE420 Digital Image Processing | |
| Colorization represents a computer-assisted process of adding color to grey-scale still images or monochrome movies. Since the mapping from grey-scale pixel to color pixel is not unique, this process generally requires some user interactions to help confine the color selection.This project implemented a colorization algorithm blending the color of pixels according to the intrinsic distances and a user-friendly interface with Visual C++ and OpenCV41 library. After user scribbles the color of some selected pixels, the program will automatically propagate the color to the remaining regions to generate a comfortable color image with good subjective quality. |  |
| Binary code download: Colorization.rar (updated!) | Report: FinalReport.pdf |
New
features: 1)  Zoom-in
and 
zoom-out for subtle fine
changes; 2) support for high-resolution
images; 3) 
full processing
and  fast
processing for
high-resolution images; 4) save and load the mask of scribble; 5) 
selective
full processing a rectangle region after fast processing. (I'll
appreciate if you could inform me any bugs). |
|
Original Image |
Mask Image |
Result Image |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| Reference |
| [1] Anat Levin, Dani Lischinski and Yair Weiss. "Colorization using Optimization". ACM Transactions on Graphics, Aug 2004, Siggraph¡¯04, pp.689-693. |
| [2] Liron Yatziv and Guillermo Sapiro. "Fast Image and Video Colorization using Chrominance Blending", May 2006, Trans. on Image Processing, pp.1120 - pp.1129. |
