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

No-reference image quality evaluation method based on double-flow convolutional neural network

A convolutional neural network, image quality assessment technology, applied in neural learning methods, biological neural network models, image enhancement, etc. The effect of strong presentation ability and accurate quality assessment scores

Active Publication Date: 2020-05-08
FUZHOU UNIV
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to bandwidth limitations and the characteristics of physical equipment, images are prone to distortion during the process of acquisition, storage, compression, and transmission. The distortion will affect people's perception of images; the information contained in the original image will be lost to varying degrees, thus Influence people to get information from images

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 double-flow convolutional neural network
  • No-reference image quality evaluation method based on double-flow convolutional neural network
  • No-reference image quality evaluation method based on double-flow convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0047] Please refer to figure 1 , the present invention provides a kind of non-reference image quality assessment method based on two-stream convolutional neural network, comprising the following steps:

[0048] Step S1: Perform data preprocessing on the data to be trained.

[0049] Step S11: first perform local normalization on all distorted images, and calculate the normalized value for a given intensity image I(i,j) The formula is as follows:

[0050]

[0051]

[0052]

[0053] Among them, (i, j) is the pixel position, I(i, j) is the pixel value of image I at position (i, j), Indicates the pixel value of image I at position (i, j) after normalization of image I, C is a constant used to prevent the denominator from being zero; K and L are the normalization window size. ω k,l is a two-dimensional circular symmetric Gaussian weighting fu...

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 a double-flow convolutional neural network, and the method comprises the following steps: S1, carrying out data preprocessing of distorted image data to acquire a to-be-trained image pair as training data; S2, constructing a double-flow convolutional neural network model, and training the model according to the obtained training data to obtain a trained image quality evaluation model; and S3, preprocessing a to-be-detected image, generating an image pair of the to-be-detected image, predicting the quality of the image pair of the to-be-detected image by using the trained image quality evaluation model, and calculating the score of the to-be-detected image according to the score of the image pair of the to-be-detected image. According to the invention, the performance of no-reference image quality evaluation can be significantly improved.

Description

technical field [0001] The invention relates to the fields of image and video processing and computer vision, in particular to a no-reference image quality assessment method based on a two-stream convolutional neural network. Background technique [0002] Digital imaging and image processing technologies have revolutionized the way people acquire, view, use and share pictures. The application fields of digital images include biomedical, aerospace, industrial and agricultural fields, automotive autonomous driving, military and live video broadcasting, etc. With the development of multimedia technology, people now have higher and higher requirements for real-time sharing, sending and receiving of pictures, and instant online live broadcast, which makes the requirements for image quality evaluation algorithms higher and higher. Due to bandwidth limitations and the characteristics of physical equipment, images are prone to distortion during the process of acquisition, storage, ...

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): G06T7/00G06N3/04G06N3/08
CPCG06T7/0002G06N3/084G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30168G06N3/045
Inventor 牛玉贞陈锋陈沛祥黄栋
Owner FUZHOU 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