CN117649347B - Remote eye examination method and system based on ultra-wide-angle fundus imaging - Google Patents
Remote eye examination method and system based on ultra-wide-angle fundus imaging Download PDFInfo
- Publication number
- CN117649347B CN117649347B CN202410122164.5A CN202410122164A CN117649347B CN 117649347 B CN117649347 B CN 117649347B CN 202410122164 A CN202410122164 A CN 202410122164A CN 117649347 B CN117649347 B CN 117649347B
- Authority
- CN
- China
- Prior art keywords
- wide
- angle image
- pixel
- ultra
- angle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003384 imaging method Methods 0.000 title claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a remote eye examination method and system based on ultra-wide-angle fundus imaging, comprising the following steps: obtaining a wide-angle image in a Lab color space and a plurality of local windows of each pixel point, and obtaining the difference degree of the histogram equalization of each local window according to the distribution difference of the pixel values of the pixel points in the local windows before and after the histogram equalization; obtaining an adjusted pixel value of each pixel point of the wide-angle image according to the difference degree of the histogram equalization of each local window, and obtaining an adjusted wide-angle image according to the adjusted pixel value of each pixel point of the wide-angle image; the method comprises the steps of obtaining a processed ultra-wide-angle image, obtaining an enhanced ultra-wide-angle image, denoising the enhanced ultra-wide-angle image to obtain the processed ultra-wide-angle image, and assisting a doctor in eye examination. The invention enhances the ultra-wide angle image and improves the accuracy of remote eye examination.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a remote eye examination method and system based on ultra-wide-angle fundus imaging.
Background
Ultra-wide angle fundus imaging is a fundus imaging technique that can capture a wider fundus area and provide more comprehensive fundus information. By combining with the remote eye examination technology, the remote monitoring and diagnosis of the eye condition can be realized, and the method has important significance for early discovery and management of some ophthalmic diseases. And has been used more and more frequently in medical neighborhoods in recent years, so that ultra-wide-angle fundus imaging technology is also becoming more and more important.
However, in the process of acquiring the ultra-wide-angle fundus imaging, the acquisition of images is affected by eye movement, a dry environment and illumination conditions of the acquisition environment, so that the quality of the acquired ultra-wide-angle fundus image is poor, and the problem in eyes can not be accurately detected according to the ultra-wide-angle fundus image, namely the accuracy of remote eye detection is reduced.
Disclosure of Invention
The invention provides a remote eye examination method and a remote eye examination system based on ultra-wide-angle fundus imaging, which aim to solve the existing problems.
The invention discloses a remote eye examination method and a system based on ultra-wide-angle fundus imaging, which adopts the following technical scheme:
One embodiment of the present invention provides a remote eye examination method based on ultra-wide angle fundus imaging, the method comprising the steps of:
collecting an ultra-wide angle image of an eye;
Converting the ultra-wide-angle image in the RGB color space into a wide-angle image in the Lab color space, acquiring a plurality of local windows with different sizes of each pixel point in the wide-angle image, acquiring brightness histograms formed by all the pixel points in any local window, carrying out histogram equalization on the brightness histograms of any local window, and acquiring the difference degree of the histogram equalization of each local window according to the distribution difference of the pixel values of the pixel points in the local windows before and after the histogram equalization;
Obtaining an adjusted pixel value of each pixel point of the wide-angle image according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of pixel values of all pixel points of each local window of each pixel point of the wide-angle image after equalization, and obtaining an adjusted wide-angle image according to the adjusted pixel value of each pixel point of the wide-angle image;
And converting the wide-angle image after Lab color space adjustment into an enhanced ultra-wide-angle image of RGB color space, denoising the enhanced ultra-wide-angle image to obtain a processed ultra-wide-angle image, and assisting a doctor in eye examination according to the processed ultra-wide-angle image.
Further, the converting the super wide-angle image in the RGB color space into the wide-angle image in the Lab color space includes the following specific steps:
the super wide-angle image in the RGB color space is converted into an image in the XYZ color space, and then the image in the XYZ color space is converted into an image in the Lab color space, which is noted as a wide-angle image in the Lab color space.
Further, the obtaining a plurality of local windows with different sizes for each pixel point in the wide-angle image includes the following specific steps:
Constructing a wide-angle image with each pixel point as a central point, wherein the sizes of the pixels are respectively as follows 、/>/>The window is marked as a local window which is positioned at the center point of the window and corresponds to the pixel point;
wherein, Three preset parameters.
Further, the obtaining the difference degree of the histogram equalization of each local window according to the distribution difference of the pixel values of the pixel points in the local windows before and after the histogram equalization comprises the following calculation formulas:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst/>, before equalization of individual pixelsVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram before equalization of all pixels in partial windowAdjacent difference features of individual pixel values,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram after equalization of all pixel points in local windowAdjacent difference features of individual pixel values,/>Representing the number of pixel values in the luminance histogram before equalization of all pixels in each partial window of each pixel of the wide-angle image,/>Representing the number of pixel values in the luminance histogram after equalization of all pixel points in each partial window of each pixel point of the wide-angle image,/>First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window;
the horizontal axis in the luminance histogram is the pixel value of the L channel in the color space, and the vertical axis is the number of pixel points corresponding to the pixel value.
Further, the specific acquisition steps of the adjacent difference features of the pixel values are as follows:
And (3) marking the pixel value with the number of the pixel points not being 0 in the brightness histogram as a target pixel value, and marking the sum of absolute values of differences between each target pixel value and the front and rear adjacent target pixel values as adjacent difference characteristics of the pixel values.
Further, the calculation formula is as follows, according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of the pixel values of all the pixel points of each local window of each pixel point of the wide-angle image after equalization, the pixel value after adjustment of each pixel point of the wide-angle image is obtained:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window,/>First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationAverage value of pixel values of all pixel points in local window,/>Number of partial windows representing each pixel of wide-angle image,/>First/>, representing wide-angle imageAnd the pixel value after the adjustment of each pixel point.
Further, the adjusted pixel value according to each pixel point of the wide-angle image includes the following specific steps:
Pixel value adjusted according to each pixel point L channel of wide-angle image and original value in wide-angle image Channel and/>The pixel values of the channels result in an adjusted wide-angle image.
Further, the step of converting the Lab color space-adjusted wide-angle image into an enhanced super-wide-angle image of RGB color space comprises the following specific steps:
And converting the wide-angle image with the Lab color space adjusted into an enhanced ultra-wide-angle image with the RGB color space through the XYZ color space.
Further, the denoising processing is performed on the enhanced ultra-wide angle image to obtain a processed ultra-wide angle image, which comprises the following specific steps:
denoising the enhanced ultra-wide-angle image through Gaussian filtering to obtain the processed ultra-wide-angle image.
The invention also provides a remote eye examination system based on the ultra-wide angle fundus imaging, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the remote eye examination methods based on the ultra-wide angle fundus imaging when executing the computer program.
The technical scheme of the invention has the beneficial effects that: according to the method, the difference degree of histogram equalization of each local window is obtained according to the distribution difference of pixel values of pixel points in the local windows before and after the histogram equalization, the enhancement influence degree of different local windows on each pixel point is obtained, and a more accurate influence range is determined; according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of pixel values of all pixel points of each local window of each pixel point of the wide-angle image after equalization, an adjusted wide-angle image is obtained, interference of light is eliminated, and more accurate pixel values of the pixel points are obtained; the wide-angle image after Lab color space adjustment is converted into an enhanced ultra-wide-angle image of RGB color space, so that the definition of an eye image is improved; denoising the enhanced ultra-wide-angle image to obtain a processed ultra-wide-angle image, and assisting a doctor in eye examination according to the processed ultra-wide-angle image, so that the accuracy of remote eye examination is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of the steps of the remote eye examination method based on ultra-wide angle fundus imaging of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of the remote eye examination method and system based on ultra-wide angle fundus imaging according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the remote eye examination method and system based on ultra-wide-angle fundus imaging provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a remote eye examination method based on ultra-wide-angle fundus imaging according to an embodiment of the invention is shown, the method includes the following steps:
Step S001: an ultra-wide angle image of the eye is acquired.
In order to analyze the influence degree of noise interference in the ultra-wide-angle fundus imaging process, the image is enhanced according to the influence degree of noise interference, and an image containing accurate information is obtained, so that a doctor can be helped to check eyes of a patient.
Specifically, a fundus image is acquired by an ultra-wide angle fundus imaging technique, and is noted as an ultra-wide angle image of the eye. The ultra-wide angle fundus imaging technology is a well-known technology, and detailed description thereof is omitted here. Wherein the ultra-wide angle image is an image in RGB color space.
So far, the ultra-wide angle image of the eye is obtained.
Step S002: the super-wide-angle image in the RGB color space is converted into a wide-angle image in the Lab color space, a plurality of local windows with different sizes of each pixel point in the wide-angle image are obtained, a brightness histogram formed by all the pixel points in any local window is obtained, histogram equalization is carried out on the brightness histogram of any local window, and the difference degree of the histogram equalization of each local window is obtained according to the distribution difference of the pixel values of the pixel points in the local windows before and after the histogram equalization.
It should be noted that, since the interference of the above factors may be a shortage of light in the environment, and the brightness of the acquired image is greatly affected, it is necessary to convert the super wide-angle image in the RGB color space into a wide-angle image in the Lab color space, and to perform enhancement adjustment according to the affected degree of the L channel in the Lab color space.
Specifically, an ultra-wide-angle image in RGB color space is converted into an image in XYZ color space, and then the image in XYZ color space is converted into an image in Lab color space, which is noted as a wide-angle image in Lab color space. The process of converting an RGB color space image into an XYZ color space image and then converting the XYZ color space image into a Lab color space image is known in the art, and detailed descriptions thereof are omitted herein.
It should be noted that, since the interference is local in the wide-angle image, each pixel may be analyzed according to the distribution of pixel values of the pixels within the local range of each pixel, and since how large the local range of each pixel should be, several local windows may be set, and the analysis may be performed together according to the pixel distribution of the pixels in the several local windows of each pixel.
In the following analysis, the pixel values of the L channel in the Lab color space are analyzed until a new pixel value of the L channel for each pixel point is obtained.
Specifically, three parameters are presetWherein the present embodiment is described as/>To describe the example, the present embodiment is not particularly limited, wherein/>Depending on the particular implementation.
Constructing a wide-angle image with each pixel point as a central point, wherein the sizes of the pixels are respectively as follows、/>/>Is marked as a local window of the corresponding pixel point at the center point of the window.
So far, a plurality of local windows of each pixel point are obtained.
And acquiring the pixel value of each pixel point L channel in the wide-angle image, and analyzing the pixel value of the pixel point L channel only by subsequent analysis.
And obtaining a brightness histogram formed by all pixel points in any local window, and carrying out histogram equalization on the brightness histogram of any local window to obtain a brightness histogram of each local window after the histogram equalization.
And (3) marking the pixel value with the number of the pixel points not being 0 in the brightness histogram as a target pixel value, and marking the sum of absolute values of differences between each target pixel value and the front and rear adjacent target pixel values as adjacent difference characteristics of the pixel values. According to the distribution difference of pixel values of pixel points in the local windows before and after the histogram equalization, the difference degree of the histogram equalization of each local window is obtained, and the difference degree is expressed as the formula:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst/>, before equalization of individual pixelsVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram before equalization of all pixels in partial windowAdjacent difference features of individual pixel values,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram after equalization of all pixel points in local windowAdjacent difference features of individual pixel values,/>Representing the number of pixel values in the luminance histogram before equalization of all pixels in each partial window of each pixel of the wide-angle image,/>Representing the number of pixel values in the luminance histogram after equalization of all pixel points in each partial window of each pixel point of the wide-angle image,/>First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window. Wherein the difference represents the absolute value of the difference. The horizontal axis in the luminance histogram is the pixel value of the L channel in the color space, and the vertical axis is the number of pixel points corresponding to the pixel value.
Wherein,The difference of the variances of the pixel values of all the pixels in each partial window before and after the equalization of each pixel point of the wide-angle image is represented, when the difference is larger, the enhancement of the pixel point by the partial window representing the pixel point is more obvious, and when the difference is smaller, the enhancement of the pixel point by the partial window representing the pixel point is less obvious.The difference between adjacent pixels in the luminance histograms of all pixels in each local window representing each pixel before and after equalization is represented, when the difference is larger, the local window representing the pixel is more obvious in enhancing the pixel, so that details in an image are more prominent, and when the difference is smaller, the local window representing the pixel is less obvious in enhancing the pixel.
So far, the difference degree of the histogram equalization of each local window of each pixel point is obtained.
Step S003: according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of the pixel values of all the pixel points of each local window of each pixel point of the wide-angle image after equalization, obtaining the pixel value of each pixel point of the wide-angle image after adjustment, and obtaining the adjusted wide-angle image according to the pixel value of each pixel point of the wide-angle image after adjustment.
It should be noted that, the average value of the pixel values of all the pixel points in each local window of the pixel points and the difference degree of the histogram equalization of the corresponding local window are analyzed, when the difference degree of the histogram equalization of each local window is larger, the larger the duty ratio of the difference degree of the histogram equalization of all the local windows is, the larger the correction of the average value of the pixel values of all the pixel points after equalization of the local window is, so that the pixel value of the L channel of each pixel point after the wide-angle image correction can be obtained.
Specifically, according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of the pixel values of all the pixel points of each local window of each pixel point after equalization, obtaining the pixel value of each pixel point of the wide-angle image after adjustment, and using a formula to express:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window,/>First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationAverage value of pixel values of all pixel points in local window,/>Representing the number of local windows per pixel in a wide-angle image,/>First/>, representing wide-angle imageAnd the pixel value after the adjustment of each pixel point.
Wherein,The ratio of the difference degree of the histogram equalization of each local window of each pixel point in the wide-angle image in the difference degree of the histogram equalization of all the local windows is represented and is used as the weight of the average value of the pixel values of all the pixel points in each local window of each pixel point in the wide-angle image after the equalization; when the ratio is larger, the mean value of the pixel values of all the pixel points in each local window after equalization is larger, and conversely, the degree of correction is smaller.
So far, the pixel value of each pixel point L channel of the wide-angle image after adjustment is obtained.
According to the pixel value of each pixel point L channel in the wide-angle image after adjustment and the original value in the wide-angle imageChannel and/>The pixel values of the channels result in an adjusted wide-angle image.
Step S004: and converting the wide-angle image after Lab color space adjustment into an enhanced ultra-wide-angle image of RGB color space, denoising the enhanced ultra-wide-angle image to obtain a processed ultra-wide-angle image, and assisting a doctor in eye examination according to the processed ultra-wide-angle image.
Specifically, the wide-angle image after Lab color space adjustment is converted into an enhanced super-wide-angle image of RGB color space through XYZ color space. The conversion process through the XYZ color space is a well-known technology, and will not be described herein.
Thus, the enhanced ultra-wide angle image of the RGB color space is obtained.
Denoising the enhanced ultra-wide-angle image through Gaussian filtering to obtain the processed ultra-wide-angle image. Here, gaussian filtering is a well-known technique, and detailed description thereof is omitted here.
And finally, helping doctors to carry out eye examination according to the processed ultra-wide angle image.
The embodiment provides a remote eye examination system based on ultra-wide-angle fundus imaging, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes steps S001 to S004 when executing the computer program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. The remote eye examination method based on ultra-wide-angle fundus imaging is characterized by comprising the following steps of:
collecting an ultra-wide angle image of an eye;
Converting the ultra-wide-angle image in the RGB color space into a wide-angle image in the Lab color space, acquiring a plurality of local windows with different sizes of each pixel point in the wide-angle image, acquiring brightness histograms formed by all the pixel points in any local window, carrying out histogram equalization on the brightness histograms of any local window, and acquiring the difference degree of the histogram equalization of each local window according to the distribution difference of the pixel values of the pixel points in the local windows before and after the histogram equalization;
Obtaining an adjusted pixel value of each pixel point of the wide-angle image according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of pixel values of all pixel points of each local window of each pixel point of the wide-angle image after equalization, and obtaining an adjusted wide-angle image according to the adjusted pixel value of each pixel point of the wide-angle image;
Converting the wide-angle image subjected to Lab color space adjustment into an enhanced ultra-wide-angle image of RGB color space, denoising the enhanced ultra-wide-angle image to obtain a processed ultra-wide-angle image, and assisting a doctor in eye examination according to the processed ultra-wide-angle image;
According to the distribution difference of pixel values of pixel points in the local windows before and after the histogram equalization, the difference degree of the histogram equalization of each local window is obtained, and the calculation formula is as follows:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst/>, before equalization of individual pixelsVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationVariance of pixel values of all pixel points in the local window,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram before equalization of all pixels in partial windowAdjacent difference features of individual pixel values,/>First/>, representing wide-angle imageFirst pixel/>First/>, in luminance histogram after equalization of all pixel points in local windowAdjacent difference features of individual pixel values,/>Representing the number of pixel values in the luminance histogram before equalization of all pixels in each partial window of each pixel of the wide-angle image,/>Representing the number of pixel values in the luminance histogram after equalization of all pixel points in each partial window of each pixel point of the wide-angle image,/>First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window;
Wherein, the horizontal axis in the brightness histogram is the pixel value of the L channel in the color space, and the vertical axis is the number of pixel points corresponding to the pixel value;
The specific acquisition steps of the adjacent difference features of the pixel values are as follows:
Marking the pixel value with the number of the pixel points not being 0 in the brightness histogram as a target pixel value, and marking the sum of absolute values of differences between each target pixel value and the front and rear adjacent target pixel values as adjacent difference characteristics of the pixel values;
The calculation formula is as follows, wherein the calculation formula is as follows, according to the difference degree of histogram equalization of each local window of each pixel point of the wide-angle image and the average value of the pixel values of all the pixel points of each local window of each pixel point of the wide-angle image after equalization, the pixel value of each pixel point of the wide-angle image after adjustment is obtained:
In the method, in the process of the invention, First/>, representing wide-angle imageFirst pixel/>The degree of difference in the histogram equalization of the individual local windows,First/>, representing wide-angle imageFirst pixel/>The degree of difference in histogram equalization for each local window,/>First/>, representing wide-angle imageFirst pixel point after equalizationAverage value of pixel values of all pixel points in local window,/>Number of partial windows representing each pixel of wide-angle image,/>First/>, representing wide-angle imageAnd the pixel value after the adjustment of each pixel point.
2. The method for remote eye examination based on ultra-wide-angle fundus imaging according to claim 1, wherein said converting the ultra-wide-angle image in RGB color space to a wide-angle image in Lab color space comprises the following specific steps:
the super wide-angle image in the RGB color space is converted into an image in the XYZ color space, and then the image in the XYZ color space is converted into an image in the Lab color space, which is noted as a wide-angle image in the Lab color space.
3. The remote eye examination method based on ultra-wide-angle fundus imaging according to claim 1, wherein the obtaining of a plurality of local windows of different sizes for each pixel point in the wide-angle image comprises the following specific steps:
Constructing a wide-angle image with each pixel point as a central point, wherein the sizes of the pixels are respectively as follows 、/>/>The window is marked as a local window which is positioned at the center point of the window and corresponds to the pixel point;
wherein, Three preset parameters.
4. The method for remote eye examination based on ultra-wide-angle fundus imaging according to claim 1, wherein the adjusted pixel value according to each pixel point of the wide-angle image is obtained as an adjusted wide-angle image, comprising the following specific steps:
Pixel value adjusted according to each pixel point L channel of wide-angle image and original value in wide-angle image Channel and/>The pixel values of the channels result in an adjusted wide-angle image.
5. The method for remote eye examination based on ultra-wide-angle fundus imaging according to claim 1, wherein said converting the Lab color space adjusted wide-angle image into the RGB color space enhanced ultra-wide-angle image comprises the specific steps of:
And converting the wide-angle image with the Lab color space adjusted into an enhanced ultra-wide-angle image with the RGB color space through the XYZ color space.
6. The remote eye examination method based on ultra-wide-angle fundus imaging according to claim 1, wherein the denoising processing is performed on the enhanced ultra-wide-angle image to obtain a processed ultra-wide-angle image, comprising the following specific steps:
denoising the enhanced ultra-wide-angle image through Gaussian filtering to obtain the processed ultra-wide-angle image.
7. A remote eye examination system based on ultra-wide-angle fundus imaging, comprising a memory, a processor and a computer program stored in said memory and running on said processor, characterized in that said processor, when executing said computer program, carries out the steps of the remote eye examination method based on ultra-wide-angle fundus imaging as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122164.5A CN117649347B (en) | 2024-01-30 | 2024-01-30 | Remote eye examination method and system based on ultra-wide-angle fundus imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122164.5A CN117649347B (en) | 2024-01-30 | 2024-01-30 | Remote eye examination method and system based on ultra-wide-angle fundus imaging |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117649347A CN117649347A (en) | 2024-03-05 |
| CN117649347B true CN117649347B (en) | 2024-04-19 |
Family
ID=90049964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410122164.5A Active CN117649347B (en) | 2024-01-30 | 2024-01-30 | Remote eye examination method and system based on ultra-wide-angle fundus imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649347B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009010636A (en) * | 2007-06-27 | 2009-01-15 | Sony Deutsche Gmbh | Adaption histogram equalization method, and adaption histogram equalization apparatus |
| CN105447874A (en) * | 2015-12-07 | 2016-03-30 | 温州医科大学眼视光器械有限公司 | Human eye bleeding image detection apparatus |
| CN107527329A (en) * | 2017-09-19 | 2017-12-29 | 重庆邮电大学 | A kind of image defogging method based on dark channel prior and Markov random field |
| CN109035183A (en) * | 2018-08-14 | 2018-12-18 | 信利光电股份有限公司 | A kind of luminance regulating method, device and electronic equipment |
| CN110916612A (en) * | 2019-11-15 | 2020-03-27 | 南京医科大学 | Comprehensive intelligent ophthalmologic examination table and control method |
| CN112419209A (en) * | 2020-11-26 | 2021-02-26 | 华侨大学 | Image enhancement method for global histogram equalization |
| CN114972102A (en) * | 2022-06-02 | 2022-08-30 | 大连海事大学 | Underwater image enhancement method based on global variable contrast enhancement and local correction |
| CN115775210A (en) * | 2022-09-08 | 2023-03-10 | 南京瞳芯慧图医疗技术有限公司 | Wide-area fundus camera image fusion method, system and storage medium |
| CN115969308A (en) * | 2022-12-23 | 2023-04-18 | 宁乡爱尔眼科医院有限公司 | Remote eye examination system based on ultra-wide-angle eye fundus imaging |
| CN116543026A (en) * | 2023-05-12 | 2023-08-04 | 杭州电子科技大学 | Method for generating contrast network fluorescence angiography image based on multi-scale condition generation |
| CN117197064A (en) * | 2023-08-30 | 2023-12-08 | 河海大学 | Automatic non-contact eye red degree analysis method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5202749B1 (en) * | 2012-09-03 | 2013-06-05 | 正浩 小林 | Image processing method |
| US20150029204A1 (en) * | 2013-07-26 | 2015-01-29 | Shao-Yang Wang | Dynamic localized contrast enhancement method for image and computer readable medium of the same |
-
2024
- 2024-01-30 CN CN202410122164.5A patent/CN117649347B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009010636A (en) * | 2007-06-27 | 2009-01-15 | Sony Deutsche Gmbh | Adaption histogram equalization method, and adaption histogram equalization apparatus |
| CN105447874A (en) * | 2015-12-07 | 2016-03-30 | 温州医科大学眼视光器械有限公司 | Human eye bleeding image detection apparatus |
| CN107527329A (en) * | 2017-09-19 | 2017-12-29 | 重庆邮电大学 | A kind of image defogging method based on dark channel prior and Markov random field |
| CN109035183A (en) * | 2018-08-14 | 2018-12-18 | 信利光电股份有限公司 | A kind of luminance regulating method, device and electronic equipment |
| CN110916612A (en) * | 2019-11-15 | 2020-03-27 | 南京医科大学 | Comprehensive intelligent ophthalmologic examination table and control method |
| CN112419209A (en) * | 2020-11-26 | 2021-02-26 | 华侨大学 | Image enhancement method for global histogram equalization |
| CN114972102A (en) * | 2022-06-02 | 2022-08-30 | 大连海事大学 | Underwater image enhancement method based on global variable contrast enhancement and local correction |
| CN115775210A (en) * | 2022-09-08 | 2023-03-10 | 南京瞳芯慧图医疗技术有限公司 | Wide-area fundus camera image fusion method, system and storage medium |
| CN115969308A (en) * | 2022-12-23 | 2023-04-18 | 宁乡爱尔眼科医院有限公司 | Remote eye examination system based on ultra-wide-angle eye fundus imaging |
| CN116543026A (en) * | 2023-05-12 | 2023-08-04 | 杭州电子科技大学 | Method for generating contrast network fluorescence angiography image based on multi-scale condition generation |
| CN117197064A (en) * | 2023-08-30 | 2023-12-08 | 河海大学 | Automatic non-contact eye red degree analysis method |
Non-Patent Citations (3)
| Title |
|---|
| Efficient Medical Image Enhancement Technique Using Transform HSV Space and ADaptive Histogram Equalization;Satish S. et al.;《Soft computing Based Medical Image Analysis》;20180202;51-60 * |
| 基于加权CLAHE的医学内窥镜图像增强算法研究;刘鸿瑞;《万方数据》;20221008;1-63页 * |
| 基于自适应邻域灰度直方图均衡的超声内窥镜图像增强;朱其刚, 朱志强;山东科技大学学报(自然科学版);20040930(03);123-126 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117649347A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023137914A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN117474823B (en) | CT data processing system for pediatric infectious inflammation detection assistance | |
| CN107657619B (en) | A kind of low-light (level) Forest fire image dividing method | |
| CN105791709A (en) | Automatic exposure processing method and apparatus with back-light compensation | |
| Wang et al. | Low-light image joint enhancement optimization algorithm based on frame accumulation and multi-scale Retinex | |
| CN111223110B (en) | Microscopic image enhancement method and device and computer equipment | |
| CN110047059B (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN110599418B (en) | Global tone mapping method for transform domain fusion | |
| WO2021037101A1 (en) | Method, device, apparatus, and medium for image information-based ecg analysis | |
| CN117522719B (en) | Bronchoscope image auxiliary optimization system based on machine learning | |
| CN116664462B (en) | Infrared and visible light image fusion method based on MS-DSC and I_CBAM | |
| CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
| CN115760858B (en) | Deep learning-based kidney pathological section cell identification method and system | |
| CN111784686A (en) | Dynamic intelligent detection method, system and readable storage medium for endoscope bleeding area | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| CN110348326A (en) | The family health care information processing method of the identification of identity-based card and the access of more equipment | |
| CN113870369A (en) | Pathological section image staining normalization method and system | |
| CN114022880B (en) | Esophageal mucosa flatness degree quantification method, device, terminal and storage medium | |
| CN116071337A (en) | Endoscopic image quality evaluation method based on super-pixel segmentation | |
| TWI255429B (en) | Method for adjusting image acquisition parameters to optimize objection extraction | |
| CN117649347B (en) | Remote eye examination method and system based on ultra-wide-angle fundus imaging | |
| CN111881924B (en) | Dark-light vehicle illumination identification method combining illumination invariance and short-exposure illumination enhancement | |
| CN112651962A (en) | AI intelligent diagnosis system platform | |
| US20100111398A1 (en) | Method and system for detection of oral sub-mucous fibrosis using microscopic image analysis of oral biopsy samples | |
| CN113658193B (en) | Liver CT image tumor segmentation method based on information fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |