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

Color image quality evaluation method based on color descriptor

A color image, quality evaluation technology, applied in the field of image processing, can solve problems such as troublesome operation, inability to give quality scores, poor generalization, etc., and achieve the effect of accurate results

Active Publication Date: 2019-02-26
XIDIAN UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is not only cumbersome to operate and poor in generalization, but also can only give the ranking results between images, and cannot give a quality score that is more acceptable to humans.

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
  • Color image quality evaluation method based on color descriptor
  • Color image quality evaluation method based on color descriptor
  • Color image quality evaluation method based on color descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention is described in further detail below with reference to accompanying drawing and embodiment:

[0040] refer to figure 1 , the specific implementation steps of this example are as follows.

[0041] Step 1, input an image to be tested that is not included in the training database.

[0042] Use Matlab software in the computer to read the images to be tested stored in the hard disk space of the computer and not included in the training database.

[0043] Step 2, obtain the color harmony descriptor of the image to be tested.

[0044] (2a) Sampling the image to be tested, the sampling size is 32 by 32 local image blocks, and sampling every 5 pixels, if the remaining pixels on the edge are greater than 20, fill in zeros; if less than or equal to 20 pixels, then discard, Filter out the required image local blocks;

[0045] (2b) Convert the local image block from the RGB color space to the Munsell color space, and calculate the hue value of each local bl...

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 color image quality evaluation method based on a color descriptor, which mainly solves the problem that the prior art can only give the sorting result between images, and cannot give the quality fraction which is more easily accepted by human beings. The implementation scheme is as follows: the preference image pair is constructed by selecting two images, and the color harmony descriptor, color contrast descriptor and color richness of each image are extracted; The difference between the two image features in the image pair is used as the feature difference of the image pair, and the preference class label of the image pair is estimated. The training data set is established by using the feature difference of each image pair and the corresponding preference class label; Mapping feature difference vectors of all image pairs to their corresponding preference class labels; The perceptual quality score is calculated according to the preference scale and the perceptual quality score. The invention improves the accuracy of the color layout, the hue and the quality evaluation of the harmonious color of the image, the quality fraction conforms to the human habit, and can be used in the compression, storage and transmission process of the color image.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for evaluating the quality of a color image, which can be used for color image processing in the process of color image compression, storage and transmission. Background technique [0002] With the rapid development of color imaging technology, color digital images have been widely used in the field of data visualization. Compared with grayscale images, color images contain a higher level of information, which can truly and vividly describe the objective world. However, when digitally processing color images, such as information collection, transformation processing, compression storage, channel transmission, terminal display, etc., some distortion will inevitably be introduced, resulting in distortion or loss of color information in the image. The quality of color images is degraded to varying degrees. Degradation will lead to the phenomenon of mixed colors b...

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): G06T7/00G06T7/90
CPCG06T7/0002G06T7/90G06T2207/10024G06T2207/20081G06T2207/30168
Inventor 路文关若瑄周自衡何立火何维佺沙丰贺然姚晶晶
Owner XIDIAN UNIV
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