Unlock instant, AI-driven research and patent intelligence for your innovation.

A no-reference image quality assessment method based on pre-attention mechanism and spatial dependence

An attention mechanism and reference image technology, applied in the field of image analysis, can solve problems such as poor algorithm stability, poor subjective consistency, and poor database independence, and achieve high database independence, high subjective consistency, and prevent physical and mental health effects

Active Publication Date: 2019-02-15
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF8 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] The purpose of the present invention is to solve the problems that the simulation method of the human visual perception system is not perfect enough, the color information in the image is not fully utilized, the subjective consistency is poor, the independence of the database is poor, and the stability of the algorithm is poor in the evaluation of image quality without reference.

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 no-reference image quality assessment method based on pre-attention mechanism and spatial dependence
  • A no-reference image quality assessment method based on pre-attention mechanism and spatial dependence
  • A no-reference image quality assessment method based on pre-attention mechanism and spatial dependence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] The procedure of this method is as follows figure 1 As shown, the specific implementation process is:

[0043] According to step 1, the input image to be tested is decomposed into two parts, color information and grayscale information, wherein the color information is obtained by transforming the SCIELAB color space, and color information maps A and B are obtained after transformation.

[0044] According to step 2, apply the scale space to process the grayscale information, the calculation method is as follows:

[0045]

[0046]

[0047] Among them, (x, y) is the coordinate, I(x, y) represents the pixel in the grayscale image, g(x, y; σ) represents the Gaussian kernel function, σ is its standard deviation, S(x, y; σ) represents the grayscale image after scale space processing. Both the original grayscale image and the scale-space processed grayscale image will be used for subsequent feature extraction.

[0048] According to step 3, for the four information maps...

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 an image quality evaluation method, in particular relates to an unreferenced image quality evaluation method based on a pre-attention mechanism and spatial dependence, and belongs to the field of image analysis. The unreferenced image quality evaluation method disclosed by the invention comprises the steps of: decomposing an input image into colour information and grey information at first, wherein the colour information is obtained by SCIELAB colour space transformation; and simultaneously, the grey information is further processed by adoption of the scale space; secondly, extracting feature vectors from two parts of information by using a grey hue co-occurrence matrix; and then, respectively training features by using a support vector machine and a BP neural network to obtain a predication model, and performing quality prediction and evaluation by using the predication model and tested corresponding feature vectors. The method disclosed by the invention has the characteristics of being high in subjective consistency, the independence of a database and stability, can be embedded into an application system relative to image / video processing, and has high 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 a pre-attention mechanism and space dependence, and belongs to the field of image analysis. Background technique [0002] In recent years, with the development of science and technology, the cost of image generation and dissemination has become lower and lower, which makes images, as an excellent medium of information dissemination, more and more common in our daily life. increasingly indispensable. However, image distortion will inevitably be introduced in various stages of scene acquisition, encoding, network transmission, decoding, post-processing, compression storage and projection. Fuzzy distortion; compression distortion caused by image compression storage, etc. The introduction of distortion will greatly reduce people's visual experience, and seriously affect people's physical and mental health. How to curb t...

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): H04N17/00
CPCH04N17/004
Inventor 刘利雄王天舒黄华
Owner BEIJING INSTITUTE OF TECHNOLOGYGY