Natural colorization method of black and white video images in visible light based on color transfer

A video image and color transfer technology, applied in the field of image processing, can solve problems such as difficult real-time processing, unnatural visual effects, and affecting use effects, etc., and achieve the effect of improving observation efficiency and fast real-time colorization

Active Publication Date: 2017-02-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing black-and-white image colorization technologies not only require a lot of human intervention, but also have a slow processing speed and are difficult to process in real time
Although the black-and-white image colorization technology (such as rainbow coding) that can be processed in real time is fast, the visual effect of colorization is often unnatural, which is quite different from the common color perception in nature, and it is difficult to satisfy the long-term observation of human eyes. It makes people's eyes tired and even makes people feel irritable, which greatly affects the use effect
[0005] To sum up, how to colorize black-and-white video images of visible light in real time and in a natural sense, so that the colorized image can not only be viewed naturally and comfortably by human eyes, but also minimize unnecessary human intervention is still a challenging problem.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Natural colorization method of black and white video images in visible light based on color transfer
  • Natural colorization method of black and white video images in visible light based on color transfer
  • Natural colorization method of black and white video images in visible light based on color transfer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] figure 1 It shows a flow chart of a method for natural colorization of visible light black and white video images based on color transfer according to an embodiment of the present invention, specifically including the following steps:

[0032] Step S1: processing the visible light black-and-white video image to form an initial color video image;

[0033] Step S2: performing color transfer on the initial color video image to obtain a natural color video image.

[0034] figure 2 It shows a flow chart of a method for changing a black-and-white visible light video image into an initial color video image according to an embodiment of the present invention, that is, figure 1 The specific implementation method of step S1 shown in . Input the visible light black and white video image, for each pixel of the visible light black and white video image, use the maximum value MAX and the pixel value Y of the visible light black and white video image pixel respectively according t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a visible light black and white video image natural colorization method based on color transferring, and belongs to the technical field of image processing technology. According to the visible light black and white video image natural colorization method, firstly, inputted visible light black and white video image is subject to negation, so that a negative image is obtained; the inputted visible light black and white video image and the obtained negative image are subject to linear combination according to a ratio, so that an initial color video image is obtained; the color reference image of a natural environment is selected, and the obtained initial color video image is subject to color transferring, so that a natural color video image is obtained. According to the visible light black and white video image natural colorization method, a person can view the natural image after colorization pleasantly with little artificial interference, colorization can be quickly realized in a real-time manner, and observation efficiency of a human eye is greatly improved.

Description

technical field [0001] The invention relates to a natural colorization method of visible light black-and-white video images based on color transfer, and belongs to the technical field of image processing. Background technique [0002] The human eye's ability to distinguish color images is far greater than that of black and white grayscale images. Humans can distinguish thousands of hues and intensities, compared to only 20 grayscales. Therefore, color images have always been one of the goals pursued by people. [0003] The colorization of old black and white photos has been a research topic for many years. Similarly, for old black and white videos, or CCD / CMOS output black and white video images commonly used in military and industry (such as computed tomography CT and nuclear magnetic resonance MRI in medical treatment, micro Light night vision and other fields), in order to improve the observation effect and reaction speed of human eyes to image details, and improve the o...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T11/00G06T11/40
Inventor 金伟其朱进李力李家琨王霞金明磊夏润秋
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products