Similar image colorization algorithm based on classification learning

A similar image and colorization technology, applied in computing, computer components, instruments, etc., can solve problems such as there is no absolutely correct solution

Active Publication Date: 2014-06-04
ZHEJIANG NORMAL UNIVERSITY
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So the colorization problem is a problem for which there is no absolute correct solution
In most cases, although these methods can reduce the time spent on manual labeling, these methods often require careful tuning of a large number of parameters to obtain satisfactory results.

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
  • Similar image colorization algorithm based on classification learning
  • Similar image colorization algorithm based on classification learning
  • Similar image colorization algorithm based on classification learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] A kind of similar image colorization algorithm based on classification learning of the present invention, comprises the following steps successively:

[0026] a) Collect multiple sets of sample images on the network. For each set of images, take one of them as a reference image, and the other grayscaled image as the target image to be colored, and add no grayscale The original image is used as the correct coloring scheme, and then the gray level co-occurrence matrix of the target image is extracted, and the above-mentioned multiple groups of sample images are divided into 5 categories by using the AP algorithm;

[0027] b) Using a geometric flow-based superpixel algorithm to extract superpixels from the target image and the reference image, each superpixel of the target image and the reference image includes four features: brightness value, standard deviation, Gabor and SURF;

[0028] c) In order to obtain the optimal linear combination of the brightness value, standard...

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 discloses a similar image colorization algorithm based on classification learning. The similar image colorization algorithm comprises the following steps: sample images are collected, an image gradation co-occurrence matrix attribute is extracted, the sample images are classified into five categories through the AP algorithm, superpixels of a target image and superpixels of a reference image are calculated respectively, then, colors are transferred from the reference image to the target image, colors of the superpixels are corrected afterwards according to continuity of image space, and finally the algorithm is used for conducting color diffusion to complete colorization. According to the similar image colorization algorithm, the influence on an image by a global attribute of the image is considered, the image gradation co-occurrence matrix attribute is extracted to conduct classification learning on parameters of a superpixel matching function, as a result, different parametric functions can be provided for superpixel matching on images with different compositions, and the universality of the similar image colorization algorithm on the images is improved; besides, after the matching process, region growing algorithm partition can be conducted at a superpixel level, and color correction can be conducted in a region.

Description

【Technical field】 [0001] The invention relates to the technical field of similar image colorization algorithms, in particular to the technical field of similar image colorization algorithms based on classification learning. 【Background technique】 [0002] The goal of image colorization is to add color to the grayscale image so that the colorized image has perceptual meaning and visual appeal. But the crux of the colorization problem is that there are many potential colors that can be assigned to the pixels of the target grayscale image (eg, leaves can be yellow, green, and brown). So the colorization problem is a problem for which there is no absolute correct solution. [0003] To reduce the impact of potential color assignments, human interaction plays an important role in the colorization process. The interactive colorization method requires the user to manually mark the color of the target image, and then smoothly spread the manually marked color value to the entire ima...

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): G06K9/62
Inventor 蒋云良罗育宏刘勇范婧
Owner ZHEJIANG NORMAL UNIVERSITY
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap