No-reference image quality assessment method based on multi-level dictionary set

Abstract

The invention discloses a non-reference quality evaluation method based on multi-level dictionary coding, which mainly solves the problem that the evaluation of noise images by a computer does not match the perception of human eyes. The implementation steps are: 1. Divide the image database; 2. Extract the eigenvector of a single experimental sample; 3. Calculate the quality value of the eigenvector of a pollution map of the training sample; 4. Calculate the eigenvector of all the training samples; 5. Calculate the training The quality value of the eigenvectors of all pollution maps in the sample; 6. Construct the first-level dictionary set with the feature vectors of the reference images of the training samples; 7. Build the second-level dictionary set with the feature vectors of the pollution maps of the training samples; 8. Calculate the second The quality value of each cluster center in the first-level dictionary set; 9. Project the test sample to the second-level dictionary set to calculate the quality value of the test sample; 10. Judge the sample quality according to the sample quality value. The evaluation result of the present invention is consistent with human perception, and can be used for image screening, transmission and compression on the Internet.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a non-reference image quality evaluation method based on a multi-level dictionary set, which can be used for image screening, transmission, retrieval, compression and identification of massive image data with uneven quality levels on the Internet middle. technical background [0002] With the development of digital image, network technology and multimedia technology, digital image has become the main carrier of information, which is processed, transmitted, stored and reconstructed in more and more applications. However, the original image signal usually contains a lot of redundancy and the image data will be mixed with various noises in the process of multi-step processing. The value of information has become a hot research topic. [0003] In the past few decades, image quality evaluation methods have made great progress, and a large number of evaluation algorithms hav...

AI Technical Summary

Problems solved by technology

These different feature extraction methods have been developed and achieved success, but there are still shortcomings: 1) Many similar algorithms are only designed for specific one or two types of noise and assume that the noise type is known, and the evaluation effect for other noises is not ideal; 2) There are also some algorithms that are performed in a certain transform such as discrete cosine transform and wavelet transform domain, which need to rely on more knowledge of the transform domain and limit the use of these algorithms in other image domains

These shortcomings will affect the accuracy of quality evaluation, and there are many limitations in practical applications.

Images