No-reference image quality evaluation method based on Curvelet transformation and phase coincidence

A quality evaluation and reference image technology, applied in the field of image analysis, can solve the problems of long time-consuming feature dimension classification and regression model training, long time-consuming feature extraction process, and large time complexity

Inactive Publication Date: 2013-07-10
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the time complexity is too large. First, the feature extraction process is complex and lengthy, which leads to a l

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
  • No-reference image quality evaluation method based on Curvelet transformation and phase coincidence
  • No-reference image quality evaluation method based on Curvelet transformation and phase coincidence
  • No-reference image quality evaluation method based on Curvelet transformation and phase coincidence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0095] We use the most popular LIVE image quality database to run CPNR to evaluate the performance of the algorithm, divide the entire database into two parts, the training set and the test set, and use the 5-fold cross-validation to select the optimal training parameters, and use the training set to train and build The classifier and regression model required by the algorithm, and then run the test set to evaluate the performance of the algorithm. In order to improve the effectiveness of the results, we follow the following rules when dividing the training and test sets: 1) The training set and the test set are absolutely isolated in terms of image content; 2) The training set and the test set account for 80% and 20% respectively Proportion; 3) When the rules 1 and 2 are met, the training set and the test set are randomly divided to evaluate the performance of the algorithm. This process is repeated 1000 times, and the median value of the results is taken as the final algorith...

Embodiment 2

[0102] In this implementation we use the entire LIVE database to train CPNR and run it on another popular image quality database TID2008 (see figure 2 ), and compare the results with two classical full-reference methods (see Table 5). It can be seen that although we are training on the LIVE database, the obtained CPNR also shows high subjective consistency in the TID2008 library, which is enough to prove that the method proposed in the present invention has a better ability to be independent of the database .

[0103] Table 5 SROCC comparison of the three methods in the TID2008 database

[0104]

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 no-reference image quality evaluation method based on Curvelet transformation and phase coincidence. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence comprises the following steps: (1), images are transformed to a Curvelet domain and a phase coincidence domain; (2), a series of natural scene statistical characteristics are extracted from the Curvelet domain and the phase coincidence domain; the series of natural scene statistical characteristics comprise logarithm histogram peak value coordinates of Curvelet coefficients and phase coincidence coefficients, direction energy distribution characteristics and dimension energy distribution characteristics; and (3), a two-step frame is used, the series of characteristics extracted in the step 2 and a support vector machine are utilized for firstly classifying distorted images of unknown types, and then nonlinear regression of a specific type is conducted on the distorted images according to a classification result, and DMOS is forecasted according to an objective quality evaluation result of the images. The no-reference image quality evaluation method based on Curvelet transformation and phase coincidence has the advantages of being high in human eye subjective consistency, small in time complexity, and high in application value.

Description

technical field [0001] The invention relates to an image quality evaluation method, in particular to a reference-free image quality evaluation method based on Curvelet transformation and phase consistency, and belongs to the field of image analysis. Background technique [0002] 70% of human beings obtain external information comes from the visual system. As an important medium for information transmission and communication, images are playing an increasingly important role in human life. Especially with the rapid development of multimedia technology and computer network technology, image processing technology is also moving towards digitization, networking and intelligence. Such as video conferencing, security monitoring, medical detection, satellite remote sensing, etc. However, in the process of digital image processing, due to the limitations of physical equipment and image processing algorithms, it will inevitably affect the quality of the image, which will greatly red...

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
IPC IPC(8): H04N17/00G06T7/00
Inventor 刘利雄董宏平黄华
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

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