Digital Image Colorization Based on Probabilistic Distance Transform

Authors:
Przemyslaw Lagodzinski;Bogdan Smolka
Affiliations:
Institute of Computer Science, Silesian University of Technology, Gliwice, Poland 44-100;Institute of Automatic Control, Silesian University of Technology, Gliwice, Poland 44-100
Venue:
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Year:
2008

Citing 7
Cited 1

Random walk approach to image enhancement

Signal Processing - Special section on digital signal processing for multimedia communications and services
Transferring color to greyscale images

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Color Transfer between Images

IEEE Computer Graphics and Applications
Estimation of Color for Gray-level Image by Probabilistic Relaxation

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Digital Geometry: Geometric Methods for Digital Picture Analysis

Digital Geometry: Geometric Methods for Digital Picture Analysis
Colorization using optimization

ACM SIGGRAPH 2004 Papers
Fast image and video colorization using chrominance blending

IEEE Transactions on Image Processing

Application of the Extended Distance Transformation in digital image colorization

Multimedia Tools and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Colorization denotes a process of adding color to gray-scale images, movies and TV programs. This process replaces the intensity value of an image pixel with a vector in a three dimensional color space composed of hue, saturation and luminance, and since this mapping - between intensity and color, has no inherently 'correct solution', human interaction and external information usually plays a large role. In this paper we present a novel colorization method that takes advantage of the modified morphological distance transform to automatically propagate the color scribbled by a user on the gray-scale image. The introduced modification of the distance transform is based on the Gibbs distribution which governs the behavior of a virtual particle performing a random walk on the image domain. Such a modification allows for the application of the distance transform to the gray-scale images and yields high quality colorization results.