Image quality evaluation method based on visual characteristics of human eyes
A technology for image quality evaluation and human vision, which is applied in the field of computer vision research, can solve the problems that the image cannot be consistent with the subjective and objective, and the accuracy of the evaluation effect is reduced, and achieve the effect of avoiding errors, simple calculation, and low complexity
Active Publication Date: 2017-09-15
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] A single image feature information extraction will often result in a decrease in the accuracy of the evaluation effect, and some images cannot achieve consistent subjective and objective results
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
[0033] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0034] Aiming at the inconsistency of subjective and objective evaluations which are common nowadays, the present invention proposes an image quality evaluation method based on human visual characteristics, which not only overcomes the shortcoming of low accuracy of single-scale evaluation, but also is more in line with human visual characteristics. At the same time, the method of the present invention has low complexity and small amount of calculation.
[0035] Such as figure 1 Shown are the detailed steps of the present invention:
[0036] 1. First input the image that needs to be evaluated for quality, and then generate the saliency image of the original image. The remarkable characteristics of the image can imitate the human visual observation process and satisfy the visual characteristics of the human eye.
[0037] The generation method of ...
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 an image quality evaluation method based on visual characteristics of the human eyes, which can perform objective evaluation on an effect of image processing in the absence of a reference frame. The image quality evaluation method comprises the steps of firstly generating a saliency image of an input image, then performing scale division on the original image and the saliency image, extracting features of the original image on each scale, weighting the features of the original image by using a weighting strategy of the saliency image which highlights a region of interest of the human eyes so as to acquire quality factors of difference scales, and finally performing weighted averaging on the quality factors of the scales so as to acquire a final image quality evaluation index. The image quality evaluation method gives sufficient consideration to the visual characteristics of the human eyes, thereby being capable of evaluating the image quality more effectively and more accurately.
Description
technical field [0001] The invention relates to an image quality evaluation method based on human visual characteristics, which is suitable for image quality evaluation without a reference frame, and belongs to the field of computer vision research. Background technique [0002] The continuous development of image processing technology has promoted the in-depth research and application of image quality evaluation methods. Image quality evaluation methods generally evaluate the effect of an image to judge the quality of image processing algorithms. [0003] Image quality evaluation methods are generally divided into two ways: subjective evaluation and objective evaluation. Subjective evaluation is mainly divided into subjective evaluation based on color perception and subjective evaluation based on preference, which is a qualitative evaluation method. The ITU recommended the double-stimulus continuous quality scale method, the double-stimulus damage scale method, and the sin...
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): G06K9/00G06K9/40G06K9/46G06T7/37
CPCG06T7/37G06T2207/20052G06T2207/30168G06V40/193G06V10/443G06V10/30G06V10/464
Inventor 唐贵进张诗林宝栋刘小花崔子冠刘峰
Owner NANJING UNIV OF POSTS & TELECOMM