A full-reference mixed-distortion image quality assessment method based on sparse decomposition residuals
A distorted image, sparse decomposition technology, applied in the field of image processing, to achieve high accuracy, good evaluation, good correlation effect
Active Publication Date: 2021-01-26
TIANJIN UNIV
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention aims at the problem that the objective quality evaluation method based on sparse representation is only effective for single distortion types and only considers sparse coefficients for quality evaluation, and proposes a full-reference image quality evaluation method suitable for evaluating mixed distortion images
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0019]The present invention will be further explained below in conjunction with the drawings.
[0020]The present invention first performs dictionary training, and then performs image quality evaluation based on the sparse decomposition residual, and the specific methods are as follows:
[0021]The first step is to select natural images for training. Here, 10 images are selected for dictionary training. Before performing dictionary training and quality evaluation, in order to eliminate the influence of image content, the present invention first performs normalization processing on the image. In the dictionary training part, 10,000 8×8 image blocks are randomly selected from the training images as training image blocks.
[0022]The second step is to train the dictionary. Combine each image block in the training image block into a training sample set Y=[y1,y2,...,yp]∈Rn×P , Where each image block yp∈Rn×1,p=1,2,...,P contains n pixels, where n=64 and P=10000. Use the sample set as input for dic...
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
Login to View More Abstract
The invention relates to a full-reference mixed-distortion image quality evaluation method based on sparse decomposition residuals, comprising: selecting natural pictures, and selecting image blocks from them as training image block training dictionary D; obtaining sparse decomposition residual energy maps; based on sparse Decompose the residual energy map to evaluate the image distortion level, the method is as follows: calculate the similarity of local residual energy features; use the variance map obtained from the reference image as weight to obtain the local residual quality score and record it as Q rl ; Solve the global residual Gres from the local residual energy map r ; Calculate the quality score of the global residual feature; the evaluation quality score of the final residual feature is divided by the local residual quality score Q rl with the global residual quality score Q rg The two parts are combined to get the final evaluation quality score and recorded as Q r .
Description
Technical field[0001]The invention belongs to the field of image processing, in particular an objective evaluation system for planar images, and relates to a full-reference hybrid distortion image quality evaluation method.Background technique[0002]With the development of digital image processing technology, image quality evaluation technology has become a research hotspot in the field of image processing. Image quality evaluation methods can be divided into subjective evaluation and objective evaluation. The former relies on human subjective feelings to evaluate the quality of the object, while the latter uses mathematical modeling to give quantitative indicators to simulate the human visual perception mechanism to measure the quality of the image. Although subjective evaluation has high reliability, it is expensive, time-consuming, and difficult to operate. Therefore, objective evaluation methods are more concerned by scholars. According to the degree of dependence on the referenc...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00
Inventor 冯丹丹侯春萍岳广辉马彤彤刘月
Owner TIANJIN UNIV