Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image colorization method based on over-segmentation and local and global consistency

An over-segmentation and colorization technology, applied in image communication, image analysis, image data processing, etc., to solve problems such as color miscoloring

Inactive Publication Date: 2015-12-02
SHANGHAI INST OF TECH
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For the method based on local color diffusion, Levin's method, TaeHoonKim's method and TengSheng-hua's method have a certain dependence on the position of the initial color mark. If the position of the color mark is not accurate enough, color miscoloring may occur.

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
  • Image colorization method based on over-segmentation and local and global consistency
  • Image colorization method based on over-segmentation and local and global consistency
  • Image colorization method based on over-segmentation and local and global consistency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The method of the present invention: firstly, the grayscale image to be dyed is roughly over-segmented using a graph-based segmentation algorithm, and a small number of interesting colors are marked in the segmented area, which not only provides coloring basis for the subsequent colorization process , and also reduces the dependence on the position of the initial color mark, and obtains an initial color mark image; then, use the gray histogram to count the position of the mark point in the segmented area, that is, the position of the peak value of the histogram, according to the initial The color of the mark, attaching a reasonable color to these mark points, so as to generate more and more dispersed color mark points, can not only reduce the complexity of manual interaction, but also provide more coloring basis for the subsequent color diffusion processing, and get A semi-automatic color-labeled image; finally, introduce the idea of ​​graph-based semi-supervised learnin...

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 an image colorization method based on over-segmentation and local and global consistency. The method comprises the following steps of performing initial color marking on a roughly segmented gray scale image; converting the initial color marked image from an RGB color space to a YUV color space characterized by brightness and color component separation; calculating the position of the mark point by using a gray scale histogram; acquiring a semi-automatic color marked image after a color for the mark point is automatically selected; minimizing a colorization framework based on local and global consistency learning to acquire final color components U<^> and V<^>; making an original brightness component Y and the final color components U<^> and V<^> integrated and converted into the RGB space to acquire a final colorized image. The acquired image color is clear and natural. The method has relatively great robustness and stability. A relatively high peak value signal to noise ratio is acquired. The manual interaction complexity is lowered while the image colorization quality is improved. The method can be used in fields of movie and television making, medical image enhancement, advertisement designing, etc.

Description

technical field [0001] The invention relates to a computer image processing technology, in particular to an image colorization method based on over-segmentation and local and global consistency. Background technique [0002] Image colorization is the process of automatically adding color to grayscale images using a computer. Color images play an important role in the process of modern information exchange and transmission. The amount of information contained in a color image is quite rich. Compared with the grayscale image, the colorized image highlights the details of the image and is convenient for people. Eye observation, such as adding color to black and white movies to make it more enjoyable, adding color to medical images to make it more eye-catching, etc., can be widely used in advertising design, restoration of ancient paintings, and video processing. Therefore, the colorization of grayscale images Processing technology is of great significance. [0003] Color mark...

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 Applications(China)
IPC IPC(8): G06T11/00G06T7/00H04N1/46
Inventor 陈颖宗盖盖曹广成
Owner SHANGHAI INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com