A Method of Image Quality Evaluation Based on Visual Saliency
An image quality evaluation and remarkable technology, applied in the field of image processing, can solve the problems of lack of subjective consistency and inaccurate subjective perception description, and achieve the effect of accurate image quality and accurate evaluation
Active Publication Date: 2021-06-11
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Wen Xin, Zhang Wanyi et al. ("Full-reference Image Quality Evaluation Algorithm Based on Visual Perception", Journal of Electronic Measurement and Instrumentation, 2016, 30(11): 1780-1789) based on the traditional image quality evaluation method, using human eyes to The image edge is extremely sensitive to the perception characteristics of the visual system, and it is proposed to use edge features to describe the difference in human subjective perception. This method only has high performance in the evaluation of a few compression algorithms, and the overall description of the subjective perception of the human eye is still not accurate enough. lack of subjective consistency
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
[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0031] The human visual perception system is more sensitive to high-frequency information, so the significant degree of changes in the spatial structure of image content caused by various disturbance factors is undoubtedly the core factor affecting the subjective perception of image quality. At present, the existing full-reference image quality evaluation methods only start from the analysis of image differences, and do not pay attention to the concept of saliency.
[0032] The flow chart of the image quality evaluation method based on visual salience in the present invention is as follows figure 1 As shown, the specific implementation method includes the following steps:
[0033] Step 1: For the original reference image and the image to be tested obtained by its distortion processing, convert it into a grayscale image I dist and I ref , Fourier tran...
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 provides an image quality evaluation method based on visual saliency, and relates to the technical field of image processing. The invention first calculates the phase consistency, and then calculates the grayscale gradient map and the gradient similarity map between the grayscale gradient maps. The gradient similarity graph is used to obtain the distribution uniformity, and the quality score is calculated, which is the quality evaluation score of the distorted image relative to the reference image. The beneficial effect of the invention is that the concept of visual saliency is introduced into the image quality evaluation, and the visual saliency of the interference in the image is described by analyzing the distribution uniformity of the interference in the image, so as to reflect the subjective influence of the interference in the image on human vision. degree, in order to more accurately evaluate the image quality.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to an image quality evaluation method. Background technique [0002] Image quality evaluation is one of the basic technologies in the field of image processing. It plays an important role in algorithm analysis and comparison and system performance evaluation. Full reference image quality evaluation is to evaluate the distorted image by comparing the difference between the distorted image and the original image. It is a method of quality evaluation, which is widely used in the fields of evaluating image coding and compression, guiding image processing algorithms, and monitoring image quality of user terminals. [0003] Wen Xin, Zhang Wanyi et al. ("Full-reference Image Quality Evaluation Algorithm Based on Visual Perception", Journal of Electronic Measurement and Instrumentation, 2016, 30(11): 1780-1789) based on the traditional image quality evaluation method, using human e...
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
CPCG06T7/0002G06T2207/10004
Inventor 王靖宇王霰禹张科姜海旭张彦华王景鹏
Owner NORTHWESTERN POLYTECHNICAL UNIV