An image quality assessment method based on the importance of deep network features

An image quality assessment, deep network technology, applied in the field of image quality assessment based on the importance of deep network features

Active Publication Date: 2020-08-18
XI AN JIAOTONG UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This network introduces the SeNet network used in the image classification field into the IQA problem, making it easy to distinguish the difference between the different channel features in the convolutional layer caused by sending the image into the IQA network

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
  • An image quality assessment method based on the importance of deep network features
  • An image quality assessment method based on the importance of deep network features
  • An image quality assessment method based on the importance of deep network features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Whole flow chart of the present invention is attached figure 1 Shown, the present invention is elaborated below in conjunction with accompanying drawing:

[0031] Step 1: Dataset Preparation

[0032]The image quality evaluation dataset is randomly divided into training set and test set according to the image content. The present invention selects four public IQA data sets, which are LIVE (including 779 distorted images, 5 types of distortion), TID2013 (including 3000 distorted images, 24 types of distortion), CSIQ (including 866 distorted images, 6 kinds of distorted images), LIVEMD (including 450 pairs of distorted images, 2 kinds of distortion types), and divide them according to the content of the original reference images in each database. The distorted images corresponding to 80% of the content are training sets, and the remaining 20% ​​correspond to The distortion map of is the test set. During the specific implementation, the training set and test set in each ...

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 image quality evaluation method based on the importance of deep network features. In the end-to-end neural network model training, the method adds a module for distinguishing the importance relationship between feature maps, which can predict image quality more accurately. And it shows strong generalization ability on various image quality assessment (IQA) datasets. The specific steps include: 1) preparing the image quality assessment data set used for training and testing the network model, and randomly dividing the image quality assessment data set into training set and test set according to the image content; 2) adding the SeNet module to the VGG‑16 network to build A neural network model VGG with multiple different combinations for image quality assessment * ‑SE, use the training data set to train them separately, when the trained model reaches the expected accuracy on the test data set, select this model as the final model, and save the parameters of the network model after training; 3) Use the selected final model Calculate the prediction accuracy on the test set.

Description

technical field [0001] The invention belongs to the field of computer image processing, in particular to an image quality evaluation method based on the importance among deep network features. Background technique [0002] As the basic content in the field of image processing, image quality assessment has a wide range of practicability in many fields, such as image compression, video codec, video surveillance and so on. Since it is difficult to obtain reference images of images to be evaluated in many practical applications, it is becoming increasingly important to develop effective no-reference image quality assessment (NR-IQA) methods; NR-IQA methods mainly include traditional methods and deep learning methods . Traditional methods mainly use low-level features manually extracted and related to human perception, and evaluate image quality through shallow regression methods. The main disadvantage of this method is that the manually extracted low-level features are not eno...

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): G06T7/00G06N3/04G06N3/08
CPCG06N3/08G06T7/0002G06T2207/30168G06T2207/20084G06T2207/20081G06N3/045
Inventor 李凡李梦月杨晓晗张扬帆
Owner XI AN JIAOTONG 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