A reference-free image quality assessment method based on convolutional neural network

A convolutional neural network and image quality assessment technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as ignoring the importance of image spatial structure information, and achieve the effect of improving quality assessment performance

Active Publication Date: 2022-04-05
FUZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Since the existing convolutional neural network-based image quality evaluation algorithms generally use image division to generate more data, these algorithms pay more attention to the local distortion information of the image, while ignoring the importance of image spatial structure information

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
  • A reference-free image quality assessment method based on convolutional neural network
  • A reference-free image quality assessment method based on convolutional neural network
  • A reference-free image quality assessment method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0043] The present invention provides a no-reference image quality assessment method based on convolutional neural network, such as figure 1 shown, including the following steps:

[0044] Step S1: Perform local normalization processing on the images in the training image set and the image set to be predicted. Specifically include the following steps:

[0045] Step S11: For any image, calculate the local weighted average value μ(i,j) and local weighted standard deviation σ(i,j) of the brightness value of each pixel, the calculation formula is:

[0046]

[0047]

[0048]Among them, i and j are the spatial positions of the pixels, K and L are used to define the height and width of the window during the local normalization process, and the height and width of the window are 2*K+1 and 2*L+1 respectively , k and l are the relative ...

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 present invention relates to a non-reference image quality assessment method based on a convolutional neural network, comprising the following steps: step S1: perform local normalization processing on training images in a training image set; step S2: overlap the training images is divided into tiles of different scales; step S3: use convolutional neural network to learn the features of tiles of different scales, and input the features generated on multiple different scales to three fully connected layers to learn the quality evaluation scores of tiles ; Step S4: Use the trained convolutional neural network to predict the quality evaluation scores of all blocks of the image to be predicted, and calculate the average quality evaluation score of all blocks of the image to be predicted as the final quality evaluation score of the image. The algorithm comprehensively considers the characteristics of images at different scales, and can significantly improve the performance of unreferenced image quality assessment based on convolutional neural networks.

Description

technical field [0001] The invention relates to the fields of image and video processing and computer vision, in particular to a method for evaluating image quality without reference based on a convolutional neural network. Background technique [0002] Digital images are usually affected by different degrees and types of image distortions during acquisition, compression, storage or other image processing. People hope to evaluate the distortion of the image, and then restore the image through a specific image restoration technology, thereby reducing the impact on other subsequent image processing links caused by the image distortion. At present, many unreferenced image quality assessment algorithms based on convolutional neural networks have been proposed. In 2014, Kang et al first proposed an image quality assessment algorithm based on convolutional neural network. This algorithm does not use manually extracted features like most traditional quality assessment algorithms, ...

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 Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0002G06T2207/20081G06T2207/20084G06T2207/30168
Inventor 牛玉贞陈培坤郭文忠
Owner FUZHOU UNIV
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