An image enhancement method based on controllable diffusion

A technology of image enhancement and diffusion equation, applied in the field of image processing, can solve problems such as visual observation pollution, achieve the effect of enhancing important details, eliminating overshoot phenomenon, and overcoming inherent shortcomings

Inactive Publication Date: 2019-03-12
SHANDONG UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, unnatural artificial artifacts (also known as overshoot) will also occur at the edge of the image during the sharpening process, causing pollution to visual observation.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An image enhancement method based on controllable diffusion
  • An image enhancement method based on controllable diffusion
  • An image enhancement method based on controllable diffusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such as Figure 7 shown.

[0050] An image enhancement method based on controllable diffusion to sharpen and enhance retinal images (original images such as figure 1 shown), including the following steps:

[0051] 1) Transform the image into the gray scale range of 0-255 through Gamma transformation;

[0052] 2) The image after the Gamma transformation is filtered by a self-similarity filter;

[0053] There is inevitably noise pollution in fundus retinal images. In order to remove noise interference and reduce the amplification of noise in the process of image sharpening and enhancement, it is necessary to perform smoothing processing on retinal images to maintain image characteristics; therefore, self-similarity filtering is adopted to image deal with;

[0054] The gray value at point p after filtering is:

[0055]

[0056] Among them, u represents the image to be processed, Ω is the definition domain of the image, and u ij Indicates the gray value of image u...

Embodiment 2

[0074] The method for sharpening and enhancing the retinal image as described in Example 1, further, step 2) During the calculation process, q is limited to a neighborhood of p. Limiting q to a neighborhood of p can reduce the computational burden and improve the computational efficiency of self-similar filtering.

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

No PUM Login to view more

Abstract

The invention relates to an image enhancement method based on controlled diffusion. Firstly, Gamma transform is applied to enhance the fundus image to a proper gray level. Secondly, the self-similarity filter is used to denoise the transformed image, especially the region of interest which needs to be extracted from the image. Finally, the proposed controllable diffusion equation method is used tofurther sharpen the image, so that the artifacts caused by over-enhancement can be avoided while the important details are highlighted.

Description

technical field [0001] The invention relates to an image enhancement method based on controllable diffusion, which belongs to the technical field of image processing. Background technique [0002] Retinal images are an effective basis for diagnosis of many ophthalmic diseases and other diseases, and the enhancement of fundus images is of great significance in the field of clinical medicine. In many cases, the retinal image will be blurred due to reasons such as uneven exposure and poor contrast of blood vessels, which will affect doctors' acquisition of information and diagnosis of diseases, which is very unfavorable to patients. Therefore, to improve the visual effect of retinal images, to enhance the quality while retaining the main features of the original image as much as possible, to facilitate the acquisition of important information for medical diagnosis. At the same time, for the subsequent processing of retinal images, it is also necessary to carry out the 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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00
CPCG06T5/002G06T5/006G06T2207/20024G06T2207/30041
Inventor 付树军刘国华王鲁王凤苓李玉亮翟林付耕
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap