New Principle Component Analysis Based Colorizing Method

Although many modern imaging systems are still producing grayscale images, colored-images are more preferred for the larger amount of information they are carrying. Computing the grayscale representation of a color image is a straightforward task, while the inverse problem has no objective solution. The search through out literature has not revealed much history of the past works. In this paper, after a brief review of related research, a new dimensionreduction method is proposed for natural color images and approved by both quantitative (PSNR) and subjective tests. Based on it a new class of colorizing methods is proposed and two sample formulations are presented, where the authors are aware of many other formulations available. Subjective test shows dominancy of our proposed method when our method is much faster than others. Our method is leading in face image colorizing where other methods have failed. Such colorization method can be used greatly in medical image processing, surveillance systems, and information visualization.

کلیدواژه ها:

Image Colorizing ، Principle Component Analysis (PCA) ، Color Attributes