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

Automatic analysis system and method for subjective image quality evaluation

An image quality and automatic analysis technology, applied in image communication, television, electrical components, etc., can solve problems such as the small number of image quality experts, ignoring local problems, and staying at the method level, so as to avoid differences of opinions, achieve objective and unified results, and save money. the effect of time

Active Publication Date: 2019-01-01
易诚高科(大连)科技有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] 1. The image processing process such as grouping photos by testers and experts selecting appropriate images and regions for report writing is too cumbersome and time-consuming;
[0009] 2. The number of image quality experts is small, and with the rapid update of device versions with camera functions, the amount of image quality evaluation tasks has increased dramatically
However, it takes a long period of time to train professional image quality experts according to the traditional method, and it is difficult to meet the demand;
[0010] 3. Subjective errors of image quality experts are unavoidable,

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
  • Automatic analysis system and method for subjective image quality evaluation
  • Automatic analysis system and method for subjective image quality evaluation
  • Automatic analysis system and method for subjective image quality evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0109] 1. Raw input data such as image 3 , as shown in 4 and 5, the 3 models are a, b, and c respectively, and each model has 3 pictures

[0110] 2. The image description module groups the images of the same shooting scene into one group, a total of 3 groups, such as image 3 , 4, 5 as shown:

[0111] 1) Take the image of model a and extract features to build a retrieval set. The method for extracting image features can use a convolutional neural network model or a traditional feature extraction method, such as HOG features and SIFT features.

[0112] 2) For the images (query images) of models b and c, extract features according to the method in step 1), and perform distance measurement with the retrieval set. The distance measurement method can adopt Euclidean distance, Manhattan distance, and distance measurement methods such as cosine of included angle.

[0113] 3) Group the query image and the retrieval set images closest to it into one group.

[0114] 3. The image d...

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 automatic analysis system and method for subjective image quality evaluation. The automatic analysis system comprises an image grouping module, an image description module,a problem region segmentation module, an image quality evaluation module, and an evaluation report generation module. The image grouping module is used for carrying out group division on inputted original images based on scenes to obtain different image groups. The image description module is used for carrying out image description on image groups obtained by the image grouping module respectively. The problem region segmentation module divides the image into different problem regions according to the image description obtained by the image description module. The image quality evaluation module carries out image quality analysis based on the statistic features and contents of the problem regions and provides various problem analysis results for different problems. The evaluation report generation module generates an evaluation report including analysis results of all scenes and analysis results of all problems.

Description

technical field [0001] The invention belongs to the field of subjective evaluation of image quality, and can obtain evaluation results and generate evaluation reports by analyzing pictures of the same scene taken by different models. Background technique [0002] The current subjective evaluation process of image quality in this field includes: [0003] 1. Testers use different shooting equipment to take photos in the same scene; [0004] 2. The testers group and name the pictures according to the scene and send them to the image quality experts; [0005] 3. Image quality experts analyze the image quality of the same group of pictures according to multiple indicators; [0006] 4. According to the analysis results, select the images and areas with problems, typesetting and generating reports. [0007] The above methods can achieve subjective evaluation of image quality and have been used in practical projects for several years, but the disadvantages are: [0008] 1. The i...

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
IPC IPC(8): H04N17/00
CPCH04N17/00
Inventor 马壮王道宁张亚东
Owner 易诚高科(大连)科技有限公司
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