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

Image quality evaluation and model generation method, device, equipment and storage medium

An evaluation model and model generation technology, applied in the image field, can solve the problems of inaccurate image quality evaluation, achieve objective quality evaluation results, reduce inaccurate problems, and improve objectivity and accuracy

Active Publication Date: 2022-06-03
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the evaluation result label of the sample image is often obtained by manually evaluating the content of the sample image, which often has high subjectivity and easily leads to the problem of inaccurate image quality evaluation.

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 quality evaluation and model generation method, device, equipment and storage medium
  • Image quality evaluation and model generation method, device, equipment and storage medium
  • Image quality evaluation and model generation method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] First, a model generation method according to an embodiment of the present invention will be introduced.

[0047] In specific applications, the evaluation model can be various. Exemplarily, the evaluation model may be a deep learning model

[0049] S104, the evaluation model in the current training stage is used as an image evaluation model.

[0065] According to the sum of the first error and the second error, it is judged whether the evaluation model in the current training stage is converged.

[0066] Wherein, the output of the preset loss function is the sum of the first error and the second error. Therefore, according to the first error and

[0067] The following takes FIG. 2 as an example for a detailed description. In order to generate an image evaluation model, the depth of the sample image can be extracted

[0069] The image quality evaluation method provided in the embodiment of the present invention can be applied to an electronic device.

[0070] As shown in F...

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

An image quality evaluation and model generation method, device, device, and storage medium provided by the embodiments of the present invention extract the basic features and depth features of the image to be evaluated respectively; wherein, the basic features are used to reflect the display effect of the image, And have interpretable features; depth features are used to reflect the features of the image content; input the basic features and depth features into the preset fusion model to obtain fusion features; input the fusion features into the image evaluation model to obtain the quality of the image to be evaluated An evaluation result; wherein, the image evaluation model is a model obtained by pre-training using fusion features of multiple sample images and evaluation result labels of multiple sample images. Through this solution, the accuracy of image quality evaluation can be improved.

Description

Image quality evaluation and model generation method, device, device and storage medium technical field The present invention relates to image technology field, particularly relate to a kind of evaluation of image quality and model generation method, device devices, devices, and storage media. Background technique [0002] With the development of image technology, images are widely used for content presentation. For example, an image can be used as a video cover face, electronic album cover and movie poster, etc. In this regard, in order to better present the content, the content reflected in the image needs to be It can carry out image quality evaluation to select images with suitable evaluation results for content presentation. In the related art, the image to be evaluated can be input into a preset model to obtain the image quality for the image content. Evaluation. Among them, the preset model is a neural network obtained by pre-training the sample images and ...

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): G06T7/00G06V10/80G06V10/774G06K9/62
CPCG06T7/0002G06T2207/30168G06F18/214G06F18/253
Inventor 邓桥
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD