Check patentability & draft patents in minutes with Patsnap Eureka AI!

Image sparse multi-dimension feature extraction method used for image quality evaluation

An image quality evaluation and feature extraction technology, applied in the field of image processing, can solve the problems of low quality evaluation, lack, information redundancy and so on

Inactive Publication Date: 2015-09-09
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The object of the present invention aims at the defects of low quality evaluation due to the information redundancy of image features and the lack of spatial domain information of transform domain features in the existing image quality evaluation process, and proposes an image sparse multi-dimensional image quality evaluation method. feature extraction method

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 sparse multi-dimension feature extraction method used for image quality evaluation
  • Image sparse multi-dimension feature extraction method used for image quality evaluation
  • Image sparse multi-dimension feature extraction method used for image quality evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The method of the present invention will be further described below in conjunction with the accompanying drawings.

[0042] As shown in Figure 1, the image sparse multi-dimensional feature extraction method for image quality evaluation includes the following steps:

[0043] Step (1). Input image I, and press a certain block width N patch Divide the image I into non-overlapping blocks as the reference block space P Ref ={P i ∈I:i∈￥ + ,i≤m}, where P is the general name of the reference image block, i is the index of the image block, ￥ + is a positive integer, and m is the number of assumed reference blocks.

[0044] In this embodiment, the size of image I is 256*256, N patch is 8, so m is 1024.

[0045] Step (2). According to the image I input in step (1), and press a certain step size N step , according to the same block width N patch Divide the image I into overlapping blocks as the reference block search space P search ={P j '∈I:j∈￥ + ,j≤n}, where P' is the ...

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 an image sparse multi-dimension feature extraction method used for image quality evaluation. The method comprises following steps of 1: constructing reference blocks and searching space of images; 2: searching blocks in the same distance in space domain and transformation domain and piling the blocks into groups; 3: performing 3D coefficient transformation for piled groups and obtaining multi-dimensional sparse transformation domain information; 4: extracting histogram statistical features of the transformation domain information and related coefficient of position linear fitting; and 5: training and classifying the above feature vectors formed by the above features by use of a support vector machine so as to obtain image quality evaluation scores. According to the invention, by taking full advantages of whole block similarity information of images, elimination of redundant features and extraction of effective multi-dimensional sparse features are achieved, and the extracted features can be used for objective evaluation of the image quality.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image sparse multi-dimensional feature extraction method for image quality evaluation. Background technique [0002] Image quality evaluation refers to the method of analyzing the distortion or noise introduced by image compression and channel transmission, and quantifying it into scores, so as to reflect the image quality. In the image processing intelligent system, the image quality evaluation becomes the key feedback in the closed loop of optimizing the system parameters by imitating the human perception of image quality through the machine. In addition, image quality evaluation is also an important index to evaluate the pros and cons of various image processing algorithms. How to objectively reflect human's subjective cognition is the research focus and difficulty of image quality evaluation. [0003] Traditional subjective image quality evaluation r...

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): G06T7/00
CPCG06T7/0002G06T2207/30168
Inventor 丁勇李楠陈宏达钱大宏赵新宇商小宝
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com