Full-reference image quality objective evaluation method based on deep feature perception reasoning
An objective evaluation method and image quality technology, applied in the field of image processing, can solve the problems of unstable evaluation and lack of subjectivity, and achieve the effect of small variation range and good stability
Active Publication Date: 2020-05-08
ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0006] The purpose of the present invention is to provide a full-reference image quality objective evaluation method based on depth feature perception reasoning to solve the problem of unstable evaluation and lack of subjectivity in existing evaluation 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
[0050] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.
[0051] In this implementation, the LIVE Release 2 image standard database provided by the image video engineering of the University of Texas at Austin is taken as an example for illustration. The LIVERelease 2 image standard database provided by the Image Video Engineering of the University of Texas at Austin stores some paired standard cases (ie, reference image and distorted image pair), and the distorted image in each case has a corresponding MOS value ( Subjective evaluation score) is known, and the MOS value is the subjective test result of the human eye.
[0052] ...
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 full-reference image quality objective evaluation method based on depth feature perception reasoning, the core of which is to combine the front-end perception characteristics, back-end processing characteristics and BP neural network of the human visual system (HVS). Based on the HVS front-end characteristics, the multi-channel significant gradient features of the image are extracted, and the secondary information decomposition processing is performed on each visual channel feature based on the HVS back-end characteristics, and the complementary evaluation algorithm is used to evaluate different decomposition contents. By constructing a BP neural network multi-channel image quality model, the multi-channel evaluation of different feature information is fused respectively. Finally, the gradient feature evaluation, the visual multi-channel gradient feature fusion evaluation, and the visual multi-channel gradient feature secondary information complementary fusion evaluation are adaptively fused together to obtain the deep feature perceptual reasoning evaluation of image quality. The method of the invention completely surpasses the levels of various evaluation indexes of various existing methods, and has better stability.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to an objective evaluation method of full-reference image quality based on depth feature perception reasoning. Background technique [0002] As a widely used signal, image plays an important role in various fields such as information acquisition, transmission and processing. At present, with the improvement of cloud computing capabilities and the rise of artificial intelligence research, various application services based on image terminal processing platforms have achieved unprecedented development. However, image signals are easily polluted, so the research on image quality evaluation is of great significance. In the field of image quality evaluation research, the objective method has become a research hotspot in this field because of its automatic and continuous efficient work mode. Among them, the research significance of full-reference image quality evaluation is parti...
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): G06T7/00G06K9/62G06N3/04
CPCG06T7/0002G06T2207/30168G06N3/045G06F18/254
Inventor 丰明坤吴茗蔚王中鹏施祥林志洁向桂山
Owner ZHEJIANG UNIVERSITY OF SCIENCE AND TECHNOLOGY