CN109101950A - A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel - Google Patents

A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel Download PDF

Info

Publication number
CN109101950A
CN109101950A CN201811014375.8A CN201811014375A CN109101950A CN 109101950 A CN109101950 A CN 109101950A CN 201811014375 A CN201811014375 A CN 201811014375A CN 109101950 A CN109101950 A CN 109101950A
Authority
CN
China
Prior art keywords
blood vessel
fundus image
eye fundus
main blood
optic disk
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.)
Pending
Application number
CN201811014375.8A
Other languages
Chinese (zh)
Inventor
余轮
林嘉雯
曹新容
薛岚燕
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou Yiying Health Technology Co Ltd
Original Assignee
Fuzhou Yiying Health Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fuzhou Yiying Health Technology Co Ltd filed Critical Fuzhou Yiying Health Technology Co Ltd
Priority to CN201811014375.8A priority Critical patent/CN109101950A/en
Publication of CN109101950A publication Critical patent/CN109101950A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/18Eye characteristics, e.g. of the iris
    • G06V40/193Preprocessing; Feature extraction
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/10Segmentation; Edge detection
    • G06T7/155Segmentation; Edge detection involving morphological operators
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/25Determination of region of interest [ROI] or a volume of interest [VOI]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30041Eye; Retina; Ophthalmic
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30004Biomedical image processing
    • G06T2207/30101Blood vessel; Artery; Vein; Vascular

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Ophthalmology & Optometry (AREA)
  • Human Computer Interaction (AREA)
  • Eye Examination Apparatus (AREA)

Abstract

The present invention relates to art of image analysis, in particular to a kind of optic disk localization method and storage equipment based on the fitting of main blood vessel.A kind of optic disk localization method based on the fitting of main blood vessel, comprising steps of being pre-processed to eye fundus image to be checked;Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and the binaryzation vessel graph is corroded to obtain main blood vessel by morphological method;Parabolic Fit calculating is carried out to main blood vessel, optic disk center is positioned according to calculated result.Entire method process complexity is low, time-consuming small, practical, and i.e. convenient lesion causes optic disk outward appearance change, or there are when the interference of the light tone lesion region of some large area, will not influence positioning result, entire method is high-efficient and accuracy is high.

Description

A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel
Technical field
The present invention relates to art of image analysis, in particular to a kind of optic disk localization method and storage based on the fitting of main blood vessel Equipment.
Background technique
Retinal fundus images automatically analyze in various systemic diseases relevant with ophthalmology such as diabetes, high blood It is widely applied in the auxiliary diagnosis of pressure, kidney trouble and neuropathy.In normal colored eye fundus image, macula lutea, Central fovea, optic disk and rete vasculosum are four, the eyeground main features that can observe, and optic disk is most important on retinal fundus images One of physiological structure, its positioning has very important significance for eyeground pathological changes diagnosis tool.Simultaneously as optic disk and macular area There is fixed range in domain, and optic disk center location information can be used as priori knowledge to assist the selection of macular region, disc diameter (Papillary Diameter, PD) is used to measure the distance and size of other feature frequently as reference length, is eye fundus image One mark of registration.Therefore, the detection of optic disk is always the problem of researcher pays special attention to.
Since optic disk is usually the bright border circular areas of a yellow or white in colored eye fundus image, early stage is proposed Optic disk detection method be the method based on optic disk feature itself, i.e., using the appearance informations such as brightness, contrast, shape of optic disk As detection feature.But such method is easy error under large area lesion disturbed condition.
Since optic disk is the initiation region that blood vessel enters eye, major vessel branches confluence area, blood vessel structure is in disease Becoming in the positioning of image optic disk has more stable performance.Therefore in recent years, scholars are more likely to determine by blood vessel structure feature Position optic disk.It is then special using the vascular distribution in optic disk region usually in the blood vessel and vessel directions being extracted in eye fundus image Sign detects optic disk region automatically.Blood vessel structure feature is relatively reliable and stable, therefore the accuracy rate of such methods is higher.So And this kind of most important problems of method are vessel extraction itself is a extremely complex and time-consuming work.
Summary of the invention
For this reason, it may be necessary to a kind of optic disk localization method based on the fitting of main blood vessel be provided, to solve existing optic disk positioning skill Art the problem of either accuracy is not high or complexity is high, time-consuming big, the practicability is poor.Specific technical solution is as follows:
A kind of optic disk localization method based on the fitting of main blood vessel, comprising steps of being pre-processed to eye fundus image to be checked; Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and by morphological method to the binaryzation Vessel graph is corroded to obtain main blood vessel;Parabolic Fit calculating is carried out to main blood vessel, optic disk center is positioned according to calculated result.
Further, described " pre-processing to eye fundus image to be checked ", further comprises the steps of: to eye fundus image to be checked Carry out the normalized of green channel selection, median filtering, limited contrast enhancing and gray scale.
Further, described " binaryzation vessel graph to be extracted by Otsu algorithm to pretreated eye fundus image, and is passed through Morphological method is corroded to obtain main blood vessel to the binaryzation vessel graph ", it further comprises the steps of: to pretreated eyeground figure As calculating threshold value by Otsu algorithm, and the pixel that gray value is greater than threshold value is regarded as into blood vessel according to the following formula;
And it is tied according to 1/4 construction that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Constitutive element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
Further, described " carrying out Parabolic Fit calculating to main blood vessel ", further comprises the steps of: with the eye fundus image upper left corner For origin, horizontal direction is X-axis, and vertical direction is Y-axis, establishes coordinate system;By each pixel mapping in the main blood vessel For the coordinate of the coordinate system;As shown by the following formula, Parabolic Fit is carried out to main blood vessel according to least square method, determines and throws The parameter of object line, and parabolical vertex is calculated,
F (x)=ax2+bx+c
Further, described " optic disk " center " to be positioned according to calculated result, further comprises the steps of: and judges the vertex of a parabola Whether fall in former eye fundus image, if the vertex of a parabola is fallen in former eye fundus image, defining the vertex of a parabola is Optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, determine that the eye fundus image does not include optic disk.
To solve the above problems, additionally providing a kind of storage equipment, specific technical solution is as follows:
A kind of storage equipment, wherein being stored with instruction set, described instruction collection is for executing: carrying out to eye fundus image to be checked Pretreatment;Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and by morphological method to institute Binaryzation vessel graph is stated to be corroded to obtain main blood vessel;Parabolic Fit calculating is carried out to main blood vessel, is positioned according to calculated result Optic disk center.
Further, described instruction collection is also used to execute: described " pre-processing to eye fundus image to be checked " further includes Step: eye fundus image to be checked is carried out at green channel selection, median filtering, limited contrast's enhancing and the normalization of gray scale Reason.
Further, described instruction collection is also used to execute: described " to be mentioned to pretreated eye fundus image by Otsu algorithm Binaryzation vessel graph is taken, and the binaryzation vessel graph is corroded to obtain main blood vessel by morphological method ", it further include step It is rapid: threshold value being calculated by Otsu algorithm to pretreated eye fundus image, and gray value is greater than threshold value according to the following formula Pixel regards as blood vessel;
And it is tied according to 1/4 construction that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Constitutive element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
Further, described instruction collection is also used to execute: described " carrying out Parabolic Fit calculating to main blood vessel " further includes Step: using the eye fundus image upper left corner as origin, horizontal direction is X-axis, and vertical direction is Y-axis, establishes coordinate system;By the main blood Each pixel in pipe is mapped as the coordinate of the coordinate system;As shown by the following formula, according to least square method to main blood vessel Parabolic Fit is carried out, determines parabolical parameter, and calculate parabolical vertex,
F (x)=ax2+bx+c
Further, described instruction collection is also used to execute: described " to position optic disk " center " according to calculated result, further include step It is rapid: judge whether the vertex of a parabola falls in former eye fundus image, if the vertex of a parabola is fallen in former eye fundus image, Defining the vertex of a parabola is optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, the eye is determined Base map picture does not include optic disk.
The beneficial effects of the present invention are: because the main blood vessel in eye fundus image is similar to parabola, and parabolical vertex is general Optic disk region is all fallen within, therefore in the present invention by being pre-processed to eye fundus image, pretreated eye fundus image is passed through Otsu algorithm extracts binaryzation vessel graph, and is corroded to obtain main blood to the binaryzation vessel graph by morphological method Pipe carries out Parabolic Fit calculating to main blood vessel, positions optic disk center according to calculated result, whole process comprehensively utilizes big saliva and calculates Method and morphological method, complexity is low, time-consuming is small, practical, and i.e. convenient lesion causes optic disk outward appearance change, or there are one When the light tone lesion region interference of a little large area, positioning result will not be influenced, entire method is high-efficient and accuracy is high, and logical The eye fundus image not comprising optic disk can be determined by crossing this method.
Detailed description of the invention
Fig. 1 is a kind of flow chart of the optic disk localization method based on the fitting of main blood vessel described in specific embodiment;
Fig. 2 is eye fundus image schematic diagram described in specific embodiment;
Fig. 3 is a kind of module map for storing equipment described in specific embodiment.
Description of symbols:
300, equipment is stored.
Specific embodiment
Technology contents, construction feature, the objects and the effects for detailed description technical solution, below in conjunction with specific reality It applies example and attached drawing is cooperated to be explained in detail.
Referring to Fig. 1, doing explanation explained below to some nouns in present embodiment first:
Optic disk: full name discus nervi optici is also optic papilla, retina from macula lutea to nasal side about 3mm at have a diameter about 1.5mm, the clear pale red disc-shaped structure of boundary, referred to as discus nervi optici, abbreviation optic disk.
Otsu algorithm: also known as maximum variance between clusters, also known as: OSTU is to be proposed by Japanese scholars OTSU in 1979 A kind of pair of image carry out binaryzation highly effective algorithm.Original image is mainly divided into prospect, two images of background using threshold value. Prospect: using n1, and csum, m1 indicate the points of the prospect under present threshold value, average gray background: moment of mass uses n2, sum- Csum, m2 indicate the points of the background under present threshold value, and moment of mass, for average gray when taking optimal threshold, background should Maximum with prospect difference, key is the standard for how selecting to measure difference, and this measures the mark of difference in otsu algorithm Standard is exactly maximum between-cluster variance, and inter-class variance is indicated with sb in this program, maximum between-cluster variance fmax.
Etching operation in morphology operations: corrosion is a kind of elimination boundary point, the process for shrinking boundary internally.It can To be used to eliminate small and meaningless object.The algorithm of corrosion: it is used with each pixel of the structural element of 3x3, scan image If it is 1 that the bianry image that structural element is covered with it, which does with operation all, the pixel of result images is 1.It otherwise is 0.Knot Fruit: bianry image is made to reduce a circle.
As shown in Fig. 2, the main blood vessel in eye fundus image is similar to parabola, and parabolical vertex generally all falls within optic disk area Domain.
In the present embodiment, a kind of optic disk localization method based on the fitting of main blood vessel can be applicable to a kind of storage equipment On, in the present embodiment, a kind of storage equipment can be smart phone, tablet computer, Desktop PC, laptop, PDA etc. Deng.
In the present embodiment, a kind of specific embodiment of the optic disk localization method based on the fitting of main blood vessel is as follows:
Step S101: eye fundus image to be checked is pre-processed.Can be used such as under type: to eye fundus image to be checked into The selection of row green channel, median filtering, limited contrast enhances and the normalized of gray scale.By locating in advance to eye fundus image Reason can remove background extra in eye fundus image, effectively denoise, and be more advantageous to the progress of subsequent eye fundus image analysis.Specifically such as Under: in any one width colour eye fundus image, noise is more under blue channel, and useful information is lost substantially, two under red channel Spot is more prominent, and the information loss such as dark-coloured blood vessel, microaneurysm is more, therefore in the present embodiment to colour to be checked Eye fundus image carries out green channel selection, farthest retains, prominent optical fundus blood vessel.
To remove noise, and it can preferably retain boundary information, to the eye fundus image under green channel in present embodiment Median filtering is carried out, realizes denoising;
For the effect that can obtain better vessel extraction, the image degree of comparing denoised is enhanced.To avoid figure Occurred bright situation after image intensifying, and used limited contrast enhancement process CLAHE in present embodiment.Finally, being returned One change processing, so that the pixel value of all pixels point is all fallen between 0-1 in piece image.
Step S102: binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and passes through form Method is corroded to obtain main blood vessel to the binaryzation vessel graph.It can be used such as under type: to pretreated eyeground figure As calculating threshold value by Otsu algorithm, and the pixel that gray value is greater than threshold value is regarded as into blood vessel according to the following formula;
And it is tied according to 1/4 construction that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Constitutive element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
After obtaining main blood vessel, step S103 is executed: Parabolic Fit calculating being carried out to main blood vessel, is positioned according to calculated result Optic disk center.Can be used such as under type: using the eye fundus image upper left corner as origin, horizontal direction is X-axis, and vertical direction is Y-axis, is built Vertical coordinate system;
Each pixel in the main blood vessel is mapped as to the coordinate of the coordinate system;
As shown by the following formula, Parabolic Fit is carried out to main blood vessel according to least square method, determines parabolical parameter, And parabolical vertex is calculated,
F (x)=ax2+bx+c
Judge whether the vertex of a parabola falls in former eye fundus image, if the vertex of a parabola falls in former eye fundus image In, then defining the vertex of a parabola is optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, institute is determined Eye fundus image is stated not comprising optic disk.
Because the main blood vessel in eye fundus image is similar to parabola, and parabolical vertex generally all falls within optic disk region, therefore By pre-processing to eye fundus image in the present invention, binaryzation blood is extracted by Otsu algorithm to pretreated eye fundus image Guan Tu, and the binaryzation vessel graph is corroded to obtain main blood vessel by morphological method, parabola is carried out to main blood vessel The Fitting Calculation positions optic disk center according to calculated result, and whole process comprehensively utilizes Otsu algorithm and morphological method, complexity It is low, time-consuming small, practical, and i.e. convenient lesion causes optic disk outward appearance change, or there are the light tone diseased regions of some large area When domain is interfered, positioning result will not be influenced, entire method is high-efficient and accuracy is high, and can determine by this method and not wrap Eye fundus image containing optic disk.
Referring to Fig. 3, in the present embodiment, a kind of specific embodiment storing equipment 300 is as follows:
A kind of storage equipment 300, wherein being stored with instruction set, described instruction collection is for executing: to eye fundus image to be checked It is pre-processed;Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and passes through morphological method The binaryzation vessel graph is corroded to obtain main blood vessel;Parabolic Fit calculating is carried out to main blood vessel, according to calculated result Position optic disk center.
Further, described instruction collection is also used to execute: described " pre-processing to eye fundus image to be checked " further includes Step: eye fundus image to be checked is carried out at green channel selection, median filtering, limited contrast's enhancing and the normalization of gray scale Reason.In any one width colour eye fundus image, noise is more under blue channel, and useful information is lost substantially, two under red channel Spot is more prominent, and the information loss such as dark-coloured blood vessel, microaneurysm is more, therefore in the present embodiment to colour to be checked Eye fundus image carries out green channel selection, farthest retains, prominent optical fundus blood vessel.
To remove noise, and it can preferably retain boundary information, to the eye fundus image under green channel in present embodiment Median filtering is carried out, realizes denoising;
For the effect that can obtain better vessel extraction, the image degree of comparing denoised is enhanced.To avoid figure Occurred bright situation after image intensifying, and used limited contrast enhancement process CLAHE in present embodiment.Finally, being returned One change processing, so that the pixel value of all pixels point is all fallen between 0-1 in piece image.
Further, described instruction collection is also used to execute: described " to be mentioned to pretreated eye fundus image by Otsu algorithm Binaryzation vessel graph is taken, and the binaryzation vessel graph is corroded to obtain main blood vessel by morphological method ", it further include step It is rapid: threshold value being calculated by Otsu algorithm to pretreated eye fundus image, and gray value is greater than threshold value according to the following formula Pixel regards as blood vessel;
And it is tied according to 1/4 construction that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Constitutive element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
Further, described instruction collection is also used to execute: described " carrying out Parabolic Fit calculating to main blood vessel " further includes Step: using the eye fundus image upper left corner as origin, horizontal direction is X-axis, and vertical direction is Y-axis, establishes coordinate system;By the main blood Each pixel in pipe is mapped as the coordinate of the coordinate system;As shown by the following formula, according to least square method to main blood vessel Parabolic Fit is carried out, determines parabolical parameter, and calculate parabolical vertex,
F (x)=ax2+bx+c
Further, described instruction collection is also used to execute: described " to position optic disk " center " according to calculated result, further include step It is rapid: judge whether the vertex of a parabola falls in former eye fundus image, if the vertex of a parabola is fallen in former eye fundus image, Defining the vertex of a parabola is optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, the eye is determined Base map picture does not include optic disk.
Because the main blood vessel in eye fundus image is similar to parabola, and parabolical vertex generally all falls within optic disk region, therefore logical The instruction set crossed in storage equipment 300 executes following steps: by pre-processing to eye fundus image, to pretreated eyeground Image extracts binaryzation vessel graph by Otsu algorithm, and corrode to the binaryzation vessel graph by morphological method To main blood vessel, Parabolic Fit calculating is carried out to main blood vessel, optic disk center, whole process comprehensive utilization are positioned according to calculated result Otsu algorithm and morphological method, complexity is low, time-consuming is small, practical, and i.e. convenient lesion causes optic disk outward appearance change, or There are when the interference of the light tone lesion region of some large area, positioning result will not be influenced, high-efficient and accuracy is high, and can sentence The eye fundus image of optic disk Chu not included.
It should be noted that being not intended to limit although the various embodiments described above have been described herein Scope of patent protection of the invention.Therefore, it based on innovative idea of the invention, change that embodiment described herein is carried out and is repaired Change, or using equivalent structure or equivalent flow shift made by description of the invention and accompanying drawing content, it directly or indirectly will be with Upper technical solution is used in other related technical areas, is included within scope of patent protection of the invention.

Claims (10)

1. a kind of optic disk localization method based on the fitting of main blood vessel, which is characterized in that comprising steps of
Eye fundus image to be checked is pre-processed;
Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and by morphological method to described two Value vessel graph is corroded to obtain main blood vessel;
Parabolic Fit calculating is carried out to main blood vessel, optic disk center is positioned according to calculated result.
2. a kind of optic disk localization method based on the fitting of main blood vessel according to claim 1, which is characterized in that
Described " pre-processing to eye fundus image to be checked ", further comprises the steps of:
Eye fundus image to be checked is carried out at green channel selection, median filtering, limited contrast's enhancing and the normalization of gray scale Reason.
3. a kind of optic disk localization method based on the fitting of main blood vessel according to claim 1, which is characterized in that
It is described " binaryzation vessel graph to be extracted by Otsu algorithm to pretreated eye fundus image, and passes through morphological method pair The binaryzation vessel graph is corroded to obtain main blood vessel ", it further comprises the steps of:
Threshold value is calculated by Otsu algorithm to pretreated eye fundus image, and gray value is greater than threshold value according to the following formula Pixel regards as blood vessel;
And according to the 1/4 structural texture member that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
4. a kind of optic disk localization method based on the fitting of main blood vessel according to claim 1, which is characterized in that
Described " carrying out Parabolic Fit calculating to main blood vessel ", further comprises the steps of:
Using the eye fundus image upper left corner as origin, horizontal direction is X-axis, and vertical direction is Y-axis, establishes coordinate system;
Each pixel in the main blood vessel is mapped as to the coordinate of the coordinate system;
As shown by the following formula, Parabolic Fit is carried out to main blood vessel according to least square method, determines parabolical parameter, and count Parabolical vertex is calculated,
F (x)=ax2+bx+c
5. a kind of optic disk localization method based on the fitting of main blood vessel according to claim 4, which is characterized in that
It is described " optic disk " center " to be positioned according to calculated result, is further comprised the steps of:
Judge whether the vertex of a parabola falls in former eye fundus image, if the vertex of a parabola is fallen in former eye fundus image, Then defining the vertex of a parabola is optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, described in judgement Eye fundus image does not include optic disk.
6. a kind of storage equipment, wherein being stored with instruction set, which is characterized in that described instruction collection is for executing:
Eye fundus image to be checked is pre-processed;
Binaryzation vessel graph is extracted by Otsu algorithm to pretreated eye fundus image, and by morphological method to described two Value vessel graph is corroded to obtain main blood vessel;
Parabolic Fit calculating is carried out to main blood vessel, optic disk center is positioned according to calculated result.
7. a kind of storage equipment according to claim 6, which is characterized in that described instruction collection is also used to execute:
Described " pre-processing to eye fundus image to be checked ", further comprises the steps of:
Eye fundus image to be checked is carried out at green channel selection, median filtering, limited contrast's enhancing and the normalization of gray scale Reason.
8. a kind of storage equipment according to claim 6, which is characterized in that described instruction collection is also used to execute:
It is described " binaryzation vessel graph to be extracted by Otsu algorithm to pretreated eye fundus image, and passes through morphological method pair The binaryzation vessel graph is corroded to obtain main blood vessel ", it further comprises the steps of:
Threshold value is calculated by Otsu algorithm to pretreated eye fundus image, and gray value is greater than threshold value according to the following formula Pixel regards as blood vessel;
And according to the 1/4 structural texture member that the width of 1/8-1/5 and main blood vessel that disc diameter is picture traverse are disc diameter Element carries out etching operation to extracted blood vessel using the structural element, removes minute blood vessel, obtain main blood vessel.
9. a kind of storage equipment according to claim 6, which is characterized in that described instruction collection is also used to execute:
Described " carrying out Parabolic Fit calculating to main blood vessel ", further comprises the steps of:
Using the eye fundus image upper left corner as origin, horizontal direction is X-axis, and vertical direction is Y-axis, establishes coordinate system;
Each pixel in the main blood vessel is mapped as to the coordinate of the coordinate system;
As shown by the following formula, Parabolic Fit is carried out to main blood vessel according to least square method, determines parabolical parameter, and count Parabolical vertex is calculated,
F (x)=ax2+bx+c
10. a kind of storage equipment according to claim 9, which is characterized in that described instruction collection is also used to execute:
It is described " optic disk " center " to be positioned according to calculated result, is further comprised the steps of:
Judge whether the vertex of a parabola falls in former eye fundus image, if the vertex of a parabola is fallen in former eye fundus image, Then defining the vertex of a parabola is optic disk center;If the vertex of a parabola is not fallen in former eye fundus image, described in judgement Eye fundus image does not include optic disk.
CN201811014375.8A 2018-08-31 2018-08-31 A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel Pending CN109101950A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811014375.8A CN109101950A (en) 2018-08-31 2018-08-31 A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811014375.8A CN109101950A (en) 2018-08-31 2018-08-31 A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel

Publications (1)

Publication Number Publication Date
CN109101950A true CN109101950A (en) 2018-12-28

Family

ID=64864712

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811014375.8A Pending CN109101950A (en) 2018-08-31 2018-08-31 A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel

Country Status (1)

Country Link
CN (1) CN109101950A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110519485A (en) * 2019-09-09 2019-11-29 Oppo广东移动通信有限公司 Image processing method, device, storage medium and electronic equipment
CN111507932A (en) * 2019-01-31 2020-08-07 福州依影健康科技有限公司 High-specificity diabetic retinopathy characteristic detection method and storage equipment
CN114387209A (en) * 2021-12-03 2022-04-22 依未科技(北京)有限公司 Method, apparatus, medium, and device for fundus structural feature determination
CN114549395A (en) * 2021-12-14 2022-05-27 依未科技(北京)有限公司 Method, apparatus, medium, and device for image feature determination based on view computation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102842136A (en) * 2012-07-19 2012-12-26 湘潭大学 Optic disc projection location method synthesizing vascular distribution with video disc appearance characteristics
CN104463140A (en) * 2014-12-23 2015-03-25 天津工业大学 Colored eye fundus image optic disk automatic locating method
US20170337689A1 (en) * 2016-05-20 2017-11-23 Yung-Hui Li Method for validating segmentation of objects with arbitrary shapes

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102842136A (en) * 2012-07-19 2012-12-26 湘潭大学 Optic disc projection location method synthesizing vascular distribution with video disc appearance characteristics
CN104463140A (en) * 2014-12-23 2015-03-25 天津工业大学 Colored eye fundus image optic disk automatic locating method
US20170337689A1 (en) * 2016-05-20 2017-11-23 Yung-Hui Li Method for validating segmentation of objects with arbitrary shapes

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111507932A (en) * 2019-01-31 2020-08-07 福州依影健康科技有限公司 High-specificity diabetic retinopathy characteristic detection method and storage equipment
CN111507932B (en) * 2019-01-31 2023-05-09 福州依影健康科技有限公司 High-specificity diabetic retinopathy characteristic detection method and storage device
CN110519485A (en) * 2019-09-09 2019-11-29 Oppo广东移动通信有限公司 Image processing method, device, storage medium and electronic equipment
CN110519485B (en) * 2019-09-09 2021-08-31 Oppo广东移动通信有限公司 Image processing method, image processing device, storage medium and electronic equipment
CN114387209A (en) * 2021-12-03 2022-04-22 依未科技(北京)有限公司 Method, apparatus, medium, and device for fundus structural feature determination
CN114549395A (en) * 2021-12-14 2022-05-27 依未科技(北京)有限公司 Method, apparatus, medium, and device for image feature determination based on view computation

Similar Documents

Publication Publication Date Title
CN109101950A (en) A kind of optic disk localization method and storage equipment based on the fitting of main blood vessel
Dufour et al. Graph-based multi-surface segmentation of OCT data using trained hard and soft constraints
Delibasis et al. Automatic model-based tracing algorithm for vessel segmentation and diameter estimation
JP7333465B2 (en) Method and apparatus for discriminating artery and vein of retinal vessels
AU2021202217B2 (en) Methods and systems for ocular imaging, diagnosis and prognosis
Gui et al. Optic disc localization algorithm based on improved corner detection
JP7197708B2 (en) Preprocessing method and storage device for fundus image quantitative analysis
Kipli et al. A review on the extraction of quantitative retinal microvascular image feature
CN111507932A (en) High-specificity diabetic retinopathy characteristic detection method and storage equipment
CN107292835B (en) Method and device for automatically vectorizing retinal blood vessels of fundus image
JP2002542863A (en) Analysis of base image
CN112233789A (en) Regional feature fusion type hypertensive retinopathy classification method
CN106446805B (en) A kind of eyeground shine in optic cup dividing method and system
Khan et al. An efficient technique for retinal vessel segmentation and denoising using modified ISODATA and CLAHE
CN114937024A (en) Image evaluation method and device and computer equipment
Lu et al. Automatic macula detection from retinal images by a line operator
Mao et al. Deep learning with skip connection attention for choroid layer segmentation in oct images
Wang et al. Accurate disease detection quantification of iris based retinal images using random implication image classifier technique
CN115578783A (en) Device and method for identifying eye diseases based on eye images and related products
CN111938567B (en) Deep learning-based ophthalmologic parameter measurement method, system and equipment
Zhou et al. Computer aided diagnosis for diabetic retinopathy based on fundus image
Qomariah et al. Exudate Segmentation for Diabetic Retinopathy Using Modified FCN-8 and Dice Loss.
Hunter et al. Tram-line filtering for retinal vessel segmentation
Kumar et al. Segmentation of retinal blood vessel using generalized extreme value probability distribution function (pdf)-based matched filter approach
Khan et al. Optic disc detection and segmentation with vessel convergence and elliptical symmetry evidences

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20181228

RJ01 Rejection of invention patent application after publication