Image quality evaluation method based on distance matrix
A technology of image quality evaluation and distance matrix, applied in the field of image processing, can solve problems such as increasing system cost
Inactive Publication Date: 2014-09-10
NANJING UNIV OF INFORMATION SCI & TECH
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This invention is used to evaluate color prints. It uses the color consistency of adjacent pixels of the image by human vision, and judges the quality of prints according to the pixel distance and color changes. The invention itself makes reasonable use of the characteristics of human vision, but the invention It is necessary to use a spectrometer when judging the different optical reflection characteristics, which undoubtedly increases the cost of the system, and the application limitations are more obvious, that is, the system is only suitable for evaluating the quality of static images such as printed matter
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
specific example
[0085] The standard image in this example uses the standard image library tid2008, which includes a total of 25 images with different scene characteristics, and adds Gaussian white noise with an expectation of 0 and a standard deviation of σ to each standard image, and the value of σ is based on needs Set it to an increasing value, so that multiple noisy images with different σ values can be obtained from a standard image. These images can be numbered according to the value of σ. Each standard image will get a set of noisy images, which can be obtained according to Image content is used to classify images. For example, I08, I21, I22, and I24 in the gallery can be classified as architectural images. For example, adding Gaussian white noise with an expectation of 0 and a standard deviation of σ to image I08 results in a group of images as I0801 , I0802, etc., the value of the standard deviation σ can be selected at an interval of 0.1, and it is about 10 according to actual need...
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 a distance matrix, belonging to the technical field of image processing. The image quality evaluation method disclosed by the invention comprises the following steps of: providing a distance map way from information of an image to reflect the correlation between pixels in the mage and the surrounding pixels: for the clear image, due to less interference, the correlation between pixel gray values and the neighborhood territory pixels can be different along with the different contents of the image; and for the image with large-quantity interference, the distance between the pixels and the surrounding pixels can become closer and a distance image can become blurred; and then extracting the characteristics of the distance map of the image through a distance matrix way, reflecting the quality of the image by the distribution range of the distance matrix and the position thereof and further getting quality parameters of the image. The invention further discloses an image fusion device, and real-time evaluation of the quality of the fused image can be performed by utilizing the image quality evaluation method disclosed by the invention. According to the image quality evaluation method disclosed by the invention, the standard image is not required, and the image quality of an image processing system or an imaging device can be effectively evaluated.
Description
technical field [0001] The invention relates to an image quality evaluation method, in particular to an image quality evaluation method based on a distance matrix, and belongs to the technical field of image processing. Background technique [0002] Image quality evaluation technology has always been a key technology in the field of image processing, which can be used to evaluate the effect of image processing methods, or to select appropriate image processing methods based on image quality. Most image quality assessment techniques measure image quality based on the difference between the processed image and the reference image; however, in most application areas of image quality assessment, it is difficult to obtain a standard image as a reference. Image quality to choose the appropriate image processing method. [0003] Most of the existing image quality evaluation techniques use the method of comparing with the standard reference image, but the human visual system can ju...
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
Inventor 张闯孙冬娇周勇常建华葛益娴曹鸿霞李敏
Owner NANJING UNIV OF INFORMATION SCI & TECH