A cross-scale image quality assessment method combining global and local features
A technology of image quality evaluation and local features, applied in image analysis, image data processing, computer parts and other directions, can solve problems such as inability to accurately simulate human visual perception and complex statistical methods
Active Publication Date: 2020-09-25
BEIJING UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
These algorithms are derived from communication theory and are relatively simple, but they cannot accurately simulate human visual perception
Existing studies have shown that human visual perception is far more complex than the simple statistical methods used in traditional image quality assessment methods
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
[0037]The technical solution of the present invention will be described in more detail below with reference to the drawings and embodiments.
[0038] This embodiment evaluates the results of the eight redirection methods in the RetargetMe database, and uses the results of the subjective evaluation as the standard for the objective evaluation.
[0039] 1) Input two images, one original image and one image to be evaluated, taking the butterfly image as an example. The SIFT feature points of the original image and the image to be evaluated are respectively extracted, and the feature points are matched and screened.
[0040] 2) Perform saliency detection on the original image. Image saliency is an important visual feature in the image, which reflects the degree to which the human eye attaches importance to certain areas of the image. The human visual system has different perceptions of different information. When evaluating the quality of an image, subjective evaluation pays more...
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 discloses a global structure and local information combined cross-scale image quality evaluation method, and relates to the technical field of image processing. On the basis of an attention mechanism in which human eye perception is from global to local, the invention provides a global structure feature and local information feature combined algorithm to carry out quality evaluationon different scales of images. The method comprises the following steps of: establishing a mapping relationship among different scales of images; carrying out research globally and locally on the basis of the mapping relationship; importing a plurality of influence factors in a global algorithm; analyzing vision disparity caused by an image in a size change process; in a local algorithm, analyzingdetail loss of the image on the basis of pixel information; and finally fusing global features and local features to obtain an image quality judgement standard. The result obtained by the objective quality evaluation method is consistent with the result obtained by a subjective evaluation method, a large number of manpower and material resources do not need to be consumed, and certain applicationvalue and reference meaning are provided.
Description
technical field [0001] The invention relates to the quality evaluation technology of images of different scales in the technical field of image processing, in particular to the research and realization of a cross-scale image quality evaluation method combining global and local features. Background technique [0002] With the rapid development of the Internet and display devices, and the personalized development of mobile terminals, there are requirements for images of different sizes. In response to this problem, a large number of image processing methods with different scales and different resolutions have emerged, which pose new challenges to image quality. Research on Image Quality Evaluation Method. [0003] Image quality assessment is an important research topic in the field of computer vision. Image quality evaluation can be divided into two types: subjective evaluation and objective evaluation. The subjective evaluation method is to use the method of user research ...
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): G06T7/00G06K9/46G06K9/62
Inventor 毋立芳闫春灿简萌刘爽徐姚文
Owner BEIJING UNIV OF TECH