Full-reference mixed distortion image quality evaluating method based on texture and cartoon sparse expression
A technology of distorted images and reference images, applied in the field of image processing, to achieve the effects of good evaluation, high accuracy and good correlation
Active Publication Date: 2017-12-15
TIANJIN UNIV
View PDF8 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention proposes a full-reference image quality evaluation method suitable for evaluating mixed-distortion images, aiming at the problem that the objective quality evaluation method based on sparse representation is only effective for a single distortion type
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
[0016] The present invention will be further elaborated below in conjunction with the accompanying drawings.
[0017] The present invention first trains the texture cartoon dictionary, and then performs image quality evaluation based on the texture cartoon sparse representation respectively, and the specific method is as follows:
[0018] In the first step, natural images with obvious cartoon and texture features are selected to train the cartoon dictionary and the texture dictionary respectively. The number of natural images used to train the cartoon and texture dictionaries in the present invention are 80 and 100 respectively. Such as figure 1 As shown, the top four images are texture images, which contain many grain details, while the bottom four images are cartoon images, in which the rest is smooth except for some edges.
[0019] In the second step, the texture and cartoon dictionaries are trained. Before performing dictionary training and quality evaluation, in order ...
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 evaluating method based on texture and cartoon sparse expression. The method includes the steps of selecting nature images with obvious cartoon and obvious texture characteristics as training images to train a cartoon dictionary and a texture dictionary to obtain the texture dictionary and the cartoon dictionary, obtaining a texture and cartoon sparse coefficient, respectively constructing sparse characteristic vectors of the two parts, evaluating the distortion level of image blocks by using the similarity between the sparse characteristic vectors of the two parts including reference image block and a distortion image block by taking amplitude and phase information into consideration, using image block variance as the weight value of an image block, respectively solving the texture sparse characteristic and the cartoon sparse characteristic image quality as Qtex and Qcar, and compositing the quality scores of the two parts Qtex and Qcar to obtain the final sparse characteristic evaluation score Qs.
Description
technical field [0001] The invention belongs to the field of image processing, in particular to an objective evaluation system for plane images, and relates to a full-reference mixed-distortion image quality evaluation method based on sparse representation. Background technique [0002] Image quality evaluation methods can be divided into two categories: subjective evaluation and objective evaluation. The former uses people to directly score the image quality, while the latter uses methods such as system modeling and statistical calculations to complete the evaluation of image quality. Although subjective evaluation has high reliability, it is expensive, time-consuming, and difficult to operate. Therefore, objective evaluation methods have attracted more attention from scholars. According to the degree of dependence on reference images, objective evaluation can be divided into full-reference, semi-reference and no-reference objective evaluation methods. [0003] The simple...
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 Applications(China)
IPC IPC(8): G06T7/00G06T7/40
CPCG06T7/0002G06T7/40G06T2207/20081
Inventor 冯丹丹侯春萍岳广辉马彤彤刘月
Owner TIANJIN UNIV