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 PDFInfo
- 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
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 58
- 210000003733 optic disk Anatomy 0.000 title claims abstract description 54
- 230000004807 localization Effects 0.000 title claims abstract description 15
- 230000000877 morphologic effect Effects 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims description 8
- 238000005530 etching Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 4
- 230000003902 lesion Effects 0.000 abstract description 8
- 238000010191 image analysis Methods 0.000 abstract description 3
- 239000008280 blood Substances 0.000 description 5
- 210000004369 blood Anatomy 0.000 description 5
- 238000010276 construction Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 208000009857 Microaneurysm Diseases 0.000 description 2
- 241000950638 Symphysodon discus Species 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- HOQADATXFBOEGG-UHFFFAOYSA-N isofenphos Chemical compound CCOP(=S)(NC(C)C)OC1=CC=CC=C1C(=O)OC(C)C HOQADATXFBOEGG-UHFFFAOYSA-N 0.000 description 2
- 210000002189 macula lutea Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002207 retinal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 206010012601 diabetes mellitus Diseases 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 201000001119 neuropathy Diseases 0.000 description 1
- 230000007823 neuropathy Effects 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 208000033808 peripheral neuropathy Diseases 0.000 description 1
- 210000001525 retina Anatomy 0.000 description 1
- 210000003296 saliva Anatomy 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
-
- 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
- G06T2207/30101—Blood 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
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.
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)
| 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)
| 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 |
-
2018
- 2018-08-31 CN CN201811014375.8A patent/CN109101950A/en active Pending
Patent Citations (3)
| 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)
| 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 |