Font Size: a A A

Research On Colorization Of Monochrome Images And Videos

Posted on:2007-03-11Degree:DoctorType:Dissertation
Country:ChinaCandidate:S H TengFull Text:PDF
GTID:1118360185996363Subject:Signal and Information Processing
Abstract/Summary:PDF Full Text Request
Colorization is a computer-assisted technique of adding colors to monochrome images, movies or TV programs. The technique has been widely used in movie-making, medical instruments, image enhancement for space exploring, and many other industrial and scientific fields. Up to now, however, the colorization technique remains an active and challenging area in the realm of image processing.According to its application and processing mode, colorization is divided into two categories, namely pseudo colorization and false colorization. Pseudo colorization implies that the original image may have.not a color attribute and the aim of colorization is to enhance the image for inspection. In contrast, false colorization means the image originally has a color attribute but such an attribute has been lost in the imaging process and the technique intends to imitate the actual scene. This dissertation mainly discusses false colorization of monochrome images and videos. After summarizing and analyzing all the available existing techniques of false colorization, a few new and applicable colorization techniques are developed in this paper.The main contributions in the dissertation are as follows:1. Theoretically summarizing of current colorization methods. Colorization is treated as an ill-posed problem. Colorization methods are divided into two kinds according to their regularization forms: the one on the basis of color transfer and the other one by using color propagation. The color propagation method is considered to be more reasonable. The underlying mechanism of the method is the local coherence of image colors. The controlling modes of color propagation are classified into two classes: micro-controlling and macro-controlling.2. Two image colorization methods based on color propagation principle are proposed and verified. (1) Levin's colorization method is investigated and considered to be inefficient for large images. Choosing small regions as processing units instead of pixels just as Levin's method, an improved colorization method base on over-segmentation is proposed. (2) In virtue of the local coherence of color attribute, a cost function defined by the total square of...
Keywords/Search Tags:Colorization, Color propagation, Motion estimation, Color transfer, Image quality assessment
PDF Full Text Request
Related items