CN108520512A - A kind of method and device measuring eye parameter - Google Patents
A kind of method and device measuring eye parameter Download PDFInfo
- Publication number
- CN108520512A CN108520512A CN201810252230.5A CN201810252230A CN108520512A CN 108520512 A CN108520512 A CN 108520512A CN 201810252230 A CN201810252230 A CN 201810252230A CN 108520512 A CN108520512 A CN 108520512A
- Authority
- CN
- China
- Prior art keywords
- eyelid
- eye
- endpoint
- cornea
- image
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06V40/19—Sensors therefor
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Eye Examination Apparatus (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides a kind of method and device measuring eye parameter, the method includes：Obtain the shooting image of eye；It includes shooting photo and medicine detection image to shoot image；The cornea and eyelid of eye in identification shooting photo, and according to cornea and eyelid, generate the endpoint of label cornea to eyelid correspond to endpoint between distance mark line；By mark line the first pixel number shared in shooting photo, it is determined as the first measurement result of lid retraction amount；Medicine detection image is identified, to obtain the bony structures of eye；And the part for being surrounded bony structures, it is determined as target to be split；The gray value of image of target to be split is obtained, and according to gray value of image, extracts the eye muscle being partitioned into；The second pixel number shared by eye muscle and default correspondence, determine the measurement result of eye muscle cross-sectional area.Described device executes the above method.Method and device provided in an embodiment of the present invention, being capable of objective, accurate and efficiently measurement eye parameter.
Description
Technical field
The present embodiments relate to human parameters field of measuring technique, and in particular to it is a kind of measure eye parameter method and
Device.
Background technology
With the continuous development of medical technology, the measurement of human parameters is particularly important.
The prior art also relies primarily on artificial micro-judgment to the measurement of human parameters, by taking eye as an example：Certain expert thinks
The eyeball of someone eye is more prominent, on the one hand, the conclusion is affected by the subjective factor of the expert；On the other hand, eyeball
Projecting degree, not easily pass through data quantization expression, moreover, because the importance and complexity of eye, eye parameter also compared with
Difficult accurate measurement, and measurement efficiency is low.
Therefore, drawbacks described above how is avoided, objective, accurate and efficiently measurement eye parameter becomes asking of need solving
Topic.
Invention content
In view of the problems of the existing technology, the embodiment of the present invention provides a kind of method and device measuring eye parameter.
In a first aspect, the embodiment of the present invention provides a kind of method measuring eye parameter, the method includes：
Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image；
It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates label
The endpoint of the cornea corresponds to the mark line of distance between endpoint to the eyelid；
By the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first is surveyed
Measure result；
The medicine detection image is identified, to obtain the bony structures of eye；And the portion for being surrounded the bony structures
Point, it is determined as target to be split；
The gray value of image of the target to be split is obtained, and according to described image gray value, extracts the eye muscle being partitioned into；
According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence, really
Determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is between presetted pixel number and actual physics area
Correspondence.
Second aspect, the embodiment of the present invention provide a kind of device measuring eye parameter, and described device includes：
Acquiring unit, the shooting image for obtaining eye；The shooting image includes shooting photo and medicine detection figure
Picture；
Generation unit, for identification in the shooting photo eye cornea and eyelid, and according to the cornea and described
Eyelid generates the mark line for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid；
First determination unit, for by the mark line the first pixel number shared in the shooting photo, being determined as
First measurement result of lid retraction amount；
Recognition unit, the medicine detection image for identification, to obtain the bony structures of eye；And by the sclerotin knot
The part that structure is surrounded is determined as target to be split；
Extraction unit, the gray value of image for obtaining the target to be split, and according to described image gray value, extraction
The eye muscle being partitioned into；
Second determination unit is used for second pixel number shared in the medicine detection image according to the eye muscle, with
And default correspondence, determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence be presetted pixel number with
Correspondence between actual physics area.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, including：Processor, memory and bus, wherein
The processor and the memory complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to refer to
Order is able to carry out following method：
Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image；
It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates label
The endpoint of the cornea corresponds to the mark line of distance between endpoint to the eyelid；
By the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first is surveyed
Measure result；
The medicine detection image is identified, to obtain the bony structures of eye；And the portion for being surrounded the bony structures
Point, it is determined as target to be split；
The gray value of image of the target to be split is obtained, and according to described image gray value, extracts the eye muscle being partitioned into；
According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence, really
Determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is between presetted pixel number and actual physics area
Correspondence.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, including：
The non-transient computer readable storage medium stores computer instruction, and the computer instruction makes the computer
Execute following method：
Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image；
It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates label
The endpoint of the cornea corresponds to the mark line of distance between endpoint to the eyelid；
By the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first is surveyed
Measure result；
The medicine detection image is identified, to obtain the bony structures of eye；And the portion for being surrounded the bony structures
Point, it is determined as target to be split；
The gray value of image of the target to be split is obtained, and according to described image gray value, extracts the eye muscle being partitioned into；
According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence, really
Determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is between presetted pixel number and actual physics area
Correspondence.
The method and device provided in an embodiment of the present invention for measuring eye parameter shoots mark line in photo by determining
Pixel number measures lid retraction amount, and the corresponding area of pixel number by determining the eye muscle being partitioned into medicine detection image
Eye muscle cross-sectional area is measured, it being capable of objective, accurate and efficiently measurement eye parameter.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Some bright embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the method flow schematic diagram that the embodiment of the present invention measures eye parameter；
Fig. 2 (a)-(d) is respectively the process sectional drawing of measurement lid retraction amount of the embodiment of the present invention based on shooting photo；
Fig. 3 (a)-(e) is respectively the process of measurement eye muscle cross-sectional area of the embodiment of the present invention based on medicine detection image
Sectional drawing；
Fig. 4 (a)-(b) is respectively the partial enlargement mistake of measurement lid retraction amount of the embodiment of the present invention based on shooting photo
Journey sectional drawing；
Fig. 5 is the apparatus structure schematic diagram that the embodiment of the present invention measures eye parameter；
Fig. 6 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
The every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the method flow schematic diagram that the embodiment of the present invention measures eye parameter, as shown in Figure 1, the embodiment of the present invention
The method of the measurement eye parameter of offer, includes the following steps：
S1：Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image.
Specifically, device obtains the shooting image of eye；The shooting image includes shooting photo and medicine detection image.
Device can be understood as detection device, server, terminal etc., be not especially limited.Eye parameter in the embodiment of the present invention can
To include lid retraction amount and eye muscle cross-sectional area, can be used for making the imitative of human body eye according to the measurement result of eye parameter
True mode, for simulating normal eye and lesion eye, in order to aided education, experience is taught.Fig. 2 (a)-(d) is respectively
For the process sectional drawing of measurement lid retraction amount of the embodiment of the present invention based on shooting photo, (a) in Fig. 2 is the original for shooting image
Figure, shooting image can be the photos of eye；Fig. 3 (a)-(e) is respectively survey of the embodiment of the present invention based on medicine detection image
The process sectional drawing of eye muscle cross-sectional area is measured, (a) in Fig. 3 is the artwork of medicine detection image, and medicine detection image can be eye
The CT testing result figures in portion.
S2：It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates mark
Remember that the endpoint of the cornea corresponds to the mark line of distance between endpoint to the eyelid.
Specifically, device identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eye
Eyelid generates the mark line for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid.Fast area can be passed through
Convolutional neural networks (Fast RCNN Regions with CNN features, referred to as " RCNN ") carry out the eye of eyes
Detection, to obtain cornea, such as (b) (by taking one eye as an example, another eye similarly, repeats no more) in Fig. 2, in cornea such as Fig. 2
(c) in circle shown in；The eye of eyes can be detected by depth convolutional neural networks DCNN, to obtain eye
Eyelid, such as (b) (by taking one eye as an example, another eye similarly, repeats no more) eyelid such as the circle institute in (d) in Fig. 2 in Fig. 2
Show；It should be noted that the embodiment of the present invention is not especially limited the recognition sequence of cornea and eyelid, you can first to identify angle
Film identifies eyelid again, can also first identify that eyelid identifies cornea again.Fig. 4 (a)-(b) is respectively that the embodiment of the present invention is based on shooting
The partial enlargement process sectional drawing of the measurement lid retraction amount of photo, Fig. 4 can be understood as the subsequent step of (d) in Fig. 2, such as scheme
Shown in 4, the endpoint of cornea may include upper extreme point and/or lower extreme point, i.e. in (a) in upper extreme point corresponding diagram 4 top line with
The connected part of cornea；The part that lower section line is connected with cornea in (a) in lower extreme point corresponding diagram 4；It generates and marks the angle
The endpoint of film corresponds to the mark line of distance between endpoint to the eyelid, may include：Generate the upper extreme point for marking the cornea
To the first label of distance between the eyelid upper extreme point (part that top line is connected with eyelid in (a) in corresponding diagram 4)
Line (top line in (a) in corresponding diagram 4)；And/or it generates and marks the lower extreme point of the cornea to the eyelid lower extreme point
The second mark line ((a) in corresponding diagram 4 of distance between (part that lower section line is connected with eyelid in (a) in corresponding diagram 4)
Middle lower section line), it should be noted that the first pixel number shared by the mark line in the embodiment of the present invention is along label line length
The pixel number shared by the line segment in direction is spent, does not consider the pixel number shared by mark line radial direction.
S3：By the mark line the first pixel number shared in the shooting photo, it is determined as the of lid retraction amount
One measurement result.
Specifically, the mark line the first pixel number shared in the shooting photo is determined as eyelid and moved back by device
First measurement result of contracting amount.Corresponding first pixel number of top line in first measurement result corresponding diagram 4 in (a) and/or
Corresponding first pixel number of lower section line.To which the measurement result of lid retraction amount is quantified as pixel number, consequently facilitating measuring
Lid retraction amount.The technical solution corresponds to the method 1 of Fig. 4 (a), and for advantage for convenience of operating, disadvantage is the people if to be detected
Eyes protrusion or strabismus etc., measurement result is not accurate enough.
S4：The medicine detection image is identified, to obtain the bony structures of eye；And surrounded the bony structures
Part is determined as target to be split.
Specifically, device identifies the medicine detection image, to obtain the bony structures of eye；And by the bony structures
The part surrounded is determined as target to be split.White portion in (b) in Fig. 3 in circle indicates the sclerotin knot of one eye
Structure, (c) corresponding target to be split in Fig. 3, which may include eye muscle and optic nerve.
S5：The gray value of image of the target to be split is obtained, and according to described image gray value, extracts the eye being partitioned into
Flesh.
Specifically, device obtains the gray value of image of the target to be split, and according to described image gray value, extraction point
The eye muscle cut out.Further, according to described image gray value, extracting the eye muscle being partitioned into can be specific as follows：It will be greater than pre-
If the part corresponding to the gray value of image of gray threshold is as target to be extracted；It is regarded described in being rejected from the target to be extracted
Nerve, to extract the eye muscle being partitioned into.Default gray threshold can be independently arranged according to actual conditions.Target to be extracted corresponds to
(d) in Fig. 3, the eye muscle being partitioned into correspond to (e) in Fig. 3, and the optic nerve of rejecting corresponds to (e) in Fig. 3 than in Fig. 3
(d) part lacked.Further, the optic nerve is rejected from the target to be extracted, it, can to extract the eye muscle being partitioned into
With specific as follows：The target to be extracted is inputted into preset model, to obtain the output of the preset model as a result, the output
As a result include the eye muscle that extraction is partitioned into；Wherein, the preset model is previously according between eye muscle sample and optic nerve sample
Position relationship training obtain.Preset model is specifically trained according to the position relationship between eye muscle sample and optic nerve sample
Method be method commonly used in the art, no longer discuss.With reference to (d) and (e) in Fig. 3, i.e., by part intermediate (d) in Fig. 3
It is determined as optic nerve, and rejects.
S6：According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence,
Determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence be presetted pixel number and actual physics area it
Between correspondence.
Specifically, device is according to the eye muscle the second pixel number shared in the medicine detection image, and it is default
Correspondence determines the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is presetted pixel number and practical object
Manage the correspondence between area.With reference to (e) in Fig. 3, i.e., by the sum of corresponding pixel in four parts in (e) in Fig. 3 pair
The sum of actual physics area answered is determined as the measurement result of eye muscle cross-sectional area.It should be noted that the embodiment of the present invention pair
Lid retraction amount and the measuring sequence of eye muscle cross-sectional area are not especially limited, you can measure eye again first to measure lid retraction amount
Flesh cross-sectional area can also first measure eye muscle cross-sectional area and measure lid retraction amount again.
The method provided in an embodiment of the present invention for measuring eye parameter, the pixel number of mark line in photo is shot by determining
Measure lid retraction amount, and the corresponding area measurement eye of pixel number by determining the eye muscle being partitioned into medicine detection image
Flesh cross-sectional area, being capable of objective, accurate and efficiently measurement eye parameter.
On the basis of the above embodiments, the target to be split further includes optic nerve；Correspondingly, described and according to described
Gray value of image extracts the eye muscle being partitioned into, including：
The part corresponding to the gray value of image of default gray threshold be will be greater than as target to be extracted.
Specifically, device will be greater than the part corresponding to the gray value of image of default gray threshold as target to be extracted.
Above-described embodiment is can refer to, is repeated no more.
The optic nerve is rejected from the target to be extracted, to extract the eye muscle being partitioned into.
Specifically, device rejects the optic nerve from the target to be extracted, to extract the eye muscle being partitioned into.It can refer to
Above-described embodiment repeats no more.
The method provided in an embodiment of the present invention for measuring eye parameter, by the gradation of image that will be greater than default gray threshold
The corresponding part of value is as target to be extracted；The optic nerve is rejected from the target to be extracted, is partitioned into extraction
Eye muscle can reasonably extract the eye muscle being partitioned into.
On the basis of the above embodiments, described to reject the optic nerve from the target to be extracted, to extract segmentation
The eye muscle gone out, including：
The target to be extracted is inputted into preset model, to obtain the output of the preset model as a result, the output is tied
Fruit includes the eye muscle that extraction is partitioned into；Wherein, the preset model is previously according between eye muscle sample and optic nerve sample
Position relationship training obtains.
Specifically, the target to be extracted is inputted preset model by device, with obtain the preset model output as a result,
The output result includes the eye muscle that extraction is partitioned into；Wherein, the preset model is previously according to eye muscle sample and optic nerve
What the position relationship training between sample obtained.Above-described embodiment is can refer to, is repeated no more.
The method provided in an embodiment of the present invention for measuring eye parameter, the eye being partitioned by preset model output extraction
Flesh is further able to reasonably extract the eye muscle being partitioned into.
On the basis of the above embodiments, the endpoint of the cornea includes upper extreme point and/or lower extreme point；Correspondingly, described
And according to the cornea and the eyelid, generate the mark for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid
Remember line, including：
Generate the first mark line for marking the upper extreme point of the cornea to distance between the eyelid upper extreme point.
Specifically, device generates the first label for marking the upper extreme point of the cornea to distance between the eyelid upper extreme point
Line.Above-described embodiment is can refer to, is repeated no more.
And/or
Generate the second mark line for marking the lower extreme point of the cornea to distance between the eyelid lower extreme point.
Specifically, device generates the second label for marking the lower extreme point of the cornea to distance between the eyelid lower extreme point
Line.Above-described embodiment is can refer to, is repeated no more.
The method provided in an embodiment of the present invention for measuring eye parameter, by generating the first mark line and/or the second label
Line more flexible can automatically measure lid retraction amount.
On the basis of the above embodiments, the method further includes：
Obtain the illumination point of the cornea.
Specifically, device obtains the illumination point of the cornea.When illumination point is shooting photo, due to reflective generated,
The direction of (b) arrow is illumination point in Fig. 4.
It determines and reflects the corresponding eyelid endpoint of light spot position with described, and light spot position and the eyelid end are reflected according to described
Point determines the second measurement result of the lid retraction amount.
Specifically, device is determined reflects the corresponding eyelid endpoint of light spot position with described, and according to it is described reflect light spot position with
The eyelid endpoint determines the second measurement result of the lid retraction amount.Eyelid endpoint may include eyelid upper extreme point and eye
Eyelid lower extreme point, the determination reflects the corresponding eyelid endpoint of light spot position with described, specific as follows：
Light spot position and the distance between the eyelid upper extreme point and the eyelid lower extreme point are reflected described in calculating separately, and will
Endpoint corresponding to small distance is determined as reflecting the corresponding eyelid endpoint of light spot position with described.I.e. calculate reflect light spot position with
Light spot position and eyelid lower extreme point distance L2 (being not shown in Fig. 4 (b)), this official holiday are reflected in the distance L1 of eyelid upper extreme point, calculating
If L2<L1, i.e., eyelid endpoint corresponding with light spot position is reflected are eyelid lower extreme point (" lower margo palpebrae " in corresponding diagram 4 (b)).
Light spot position and the eyelid endpoint are reflected according to described, determines the second measurement result of the lid retraction amount, is had
Body is as follows：
The second measurement result of the lid retraction amount is determined according to following formula：
Second measurement result=described reflects the distance between light spot position and the eyelid endpoint-a；
Wherein, a is the decimal more than 1mm, and less than 8mm, and the concrete numerical value of a can be independently arranged according to actual conditions,
It is chosen as 4mm.With reference to the example above, i.e.,：Second measurement result=L2-4mm.The technical solution corresponds to the method 2 of Fig. 4 (b),
Advantage is suitable for owner (including human eye to be detected protrusion or strabismus etc.), and disadvantage is that the illumination point of cornea is sometimes unknown
It is aobvious, it is not easy to identify.
The method provided in an embodiment of the present invention for measuring eye parameter, by reflecting light spot position and corresponding with light spot position is reflected
Eyelid endpoint, can determine the second measurement result of lid retraction amount so that more objective under given conditions, accurate and high
Effect ground measures lid retraction amount.
On the basis of the above embodiments, the eyelid endpoint includes eyelid upper extreme point and eyelid lower extreme point；Correspondingly, institute
It states and determines and reflect the corresponding eyelid endpoint of light spot position with described, including：
Light spot position and the distance between the eyelid upper extreme point and the eyelid lower extreme point are reflected described in calculating separately, and will
Endpoint corresponding to small distance is determined as reflecting the corresponding eyelid endpoint of light spot position with described.
Specifically, device calculates separately described reflect between light spot position and the eyelid upper extreme point and the eyelid lower extreme point
Distance be determined as reflecting the corresponding eyelid endpoint of light spot position with described and by the endpoint corresponding to small distance.It can refer to
Embodiment is stated, is repeated no more.
The method provided in an embodiment of the present invention for measuring eye parameter, by calculate separately it is described reflect light spot position with it is described
The distance between eyelid upper extreme point and the eyelid lower extreme point, and by the endpoint corresponding to small distance, be determined as reflecting with described
The corresponding eyelid endpoint of light spot position can rationally determine eyelid endpoint corresponding with light spot position is reflected, and ensure that measuring eyelid moves back
Contracting amount is smoothed out.
On the basis of the above embodiments, described and reflect light spot position and the eyelid endpoint according to described, determine described in
Second measurement result of lid retraction amount, including：
The second measurement result of the lid retraction amount is determined according to following formula：
Second measurement result=described reflects the distance between light spot position and the eyelid endpoint-a；
Wherein, a is the decimal more than 1mm, and less than 8mm.
Specifically, device determines the second measurement result of the lid retraction amount according to following formula：
Second measurement result=described reflects the distance between light spot position and the eyelid endpoint-a；
Wherein, a is the decimal more than 1mm, and less than 8mm.Above-described embodiment is can refer to, is repeated no more.
The method provided in an embodiment of the present invention for measuring eye parameter is further able to reasonable determination by above-mentioned formula
Second measurement result of lid retraction amount.
Fig. 5 is the apparatus structure schematic diagram that the embodiment of the present invention measures eye parameter, as shown in figure 5, the embodiment of the present invention
Provide it is a kind of measure eye parameter device, including acquiring unit 1, generation unit 2, the first determination unit 3, recognition unit 4,
Extraction unit 5 and the second determination unit 6, wherein：
Acquiring unit 1 is used to obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection figure
Picture；Generation unit 2 for identification in the shooting photo eye cornea and eyelid, and according to the cornea and the eyelid,
Generate the mark line for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid；First determination unit 3 is used for will
The mark line the first pixel number shared in the shooting photo, is determined as the first measurement result of lid retraction amount；Know
The medicine detection image for identification of other unit 4, to obtain the bony structures of eye；And surrounded the bony structures
Part is determined as target to be split；Extraction unit 5 is used to obtain the gray value of image of the target to be split, and according to described
Gray value of image extracts the eye muscle being partitioned into；Second determination unit 6 is used for according to the eye muscle in the medicine detection image
The second shared pixel number and default correspondence, determine the measurement result of eye muscle cross-sectional area；Wherein, described default pair
The correspondence that should be related between presetted pixel number and actual physics area.
Specifically, acquiring unit 1 is used to obtain the shooting image of eye；The shooting image includes shooting photo and medicine
Detection image；Generation unit 2 for identification in the shooting photo eye cornea and eyelid, and according to the cornea and described
Eyelid generates the mark line for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid；First determination unit 3 is used
In by the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first measures knot
Fruit；The medicine detection image for identification of recognition unit 4, to obtain the bony structures of eye；And by the bony structures institute
The part of encirclement is determined as target to be split；Extraction unit 5 is used to obtain the gray value of image of the target to be split, and root
According to described image gray value, the eye muscle being partitioned into is extracted；Second determination unit 6 according to the eye muscle in the medicine for detecting
The second shared pixel number and default correspondence, determine the measurement result of eye muscle cross-sectional area in image；Wherein, described
Default correspondence of the correspondence between presetted pixel number and actual physics area.
The device provided in an embodiment of the present invention for measuring eye parameter, the pixel number of mark line in photo is shot by determining
Measure lid retraction amount, and the corresponding area measurement eye of pixel number by determining the eye muscle being partitioned into medicine detection image
Flesh cross-sectional area, being capable of objective, accurate and efficiently measurement eye parameter.
The device provided in an embodiment of the present invention for measuring eye parameter specifically can be used for executing above-mentioned each method embodiment
Process flow, details are not described herein for function, is referred to the detailed description of above method embodiment.
Fig. 6 is electronic equipment entity structure schematic diagram provided in an embodiment of the present invention, as shown in fig. 6, the electronic equipment
Including：Processor (processor) 601, memory (memory) 602 and bus 603；
Wherein, the processor 601, memory 602 complete mutual communication by bus 603；
The processor 601 is used to call the program instruction in the memory 602, to execute above-mentioned each method embodiment
The method provided, such as including：Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection figure
Picture；It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates and mark the angle
The endpoint of film corresponds to the mark line of distance between endpoint to the eyelid；The mark line is shared in the shooting photo
First pixel number is determined as the first measurement result of lid retraction amount；The medicine detection image is identified, to obtain the bone of eye
Matter structure；And the part for being surrounded the bony structures, it is determined as target to be split；Obtain the image of the target to be split
Gray value, and according to described image gray value, extract the eye muscle being partitioned into；According to the eye muscle in the medicine detection image
The second shared pixel number and default correspondence, determine the measurement result of eye muscle cross-sectional area；Wherein, described default pair
The correspondence that should be related between presetted pixel number and actual physics area.
The present embodiment discloses a kind of computer program product, and the computer program product includes being stored in non-transient calculating
Computer program on machine readable storage medium storing program for executing, the computer program include program instruction, when described program instruction is calculated
When machine executes, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including：Obtain the shooting figure of eye
Picture；The shooting image includes shooting photo and medicine detection image；Identify the cornea and eyelid of eye in the shooting photo,
And according to the cornea and the eyelid, generate the mark for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid
Remember line；By the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first measures
As a result；The medicine detection image is identified, to obtain the bony structures of eye；And the part for being surrounded the bony structures,
It is determined as target to be split；The gray value of image of the target to be split is obtained, and according to described image gray value, extraction segmentation
The eye muscle gone out；According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence, really
Determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is between presetted pixel number and actual physics area
Correspondence.
The present embodiment provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Computer instruction is stored, the computer instruction makes the computer execute the method that above-mentioned each method embodiment is provided, example
Such as include：Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image；Identify the shooting
The cornea and eyelid of eye in photo, and according to the cornea and the eyelid, the endpoint of the label cornea is generated described in
Eyelid corresponds to the mark line of distance between endpoint；By the mark line the first pixel number shared in the shooting photo, really
It is set to the first measurement result of lid retraction amount；The medicine detection image is identified, to obtain the bony structures of eye；And by institute
The part that bony structures are surrounded is stated, target to be split is determined as；Obtain the gray value of image of the target to be split, and according to
Described image gray value extracts the eye muscle being partitioned into；According to the eye muscle the second picture shared in the medicine detection image
Prime number and default correspondence, determine the measurement result of eye muscle cross-sectional area；Wherein, the default correspondence is default
Correspondence between pixel number and actual physics area.
One of ordinary skill in the art will appreciate that：Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer read/write memory medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed；And storage medium above-mentioned includes：ROM, RAM, magnetic disc or light
The various media that can store program code such as disk.
The embodiments such as electronic equipment described above are only schematical, illustrate as separating component wherein described
Unit may or may not be physically separated, and the component shown as unit may or may not be object
Manage unit, you can be located at a place, or may be distributed over multiple network units.It can select according to the actual needs
Some or all of module therein is selected to achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying wound
In the case of the labour for the property made, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be expressed in the form of software products in other words, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally it should be noted that：The above various embodiments is only to illustrate the technical solution of the embodiment of the present invention rather than right
It is limited；Although the embodiment of the present invention is described in detail with reference to foregoing embodiments, the ordinary skill of this field
Personnel should understand that：It still can be with technical scheme described in the above embodiments is modified, or to which part
Or all technical features carries out equivalent replacement；And these modifications or replacements, it does not separate the essence of the corresponding technical solution
The range of each embodiment technical solution of the embodiment of the present invention.
Claims (10)
1. a kind of method measuring eye parameter, which is characterized in that including：
Obtain the shooting image of eye；The shooting image includes shooting photo and medicine detection image；
It identifies the cornea and eyelid of eye in the shooting photo, and according to the cornea and the eyelid, generates described in label
The endpoint of cornea corresponds to the mark line of distance between endpoint to the eyelid；
By the mark line the first pixel number shared in the shooting photo, be determined as lid retraction amount first measures knot
Fruit；
The medicine detection image is identified, to obtain the bony structures of eye；And the part for being surrounded the bony structures, really
It is set to target to be split；
The gray value of image of the target to be split is obtained, and according to described image gray value, extracts the eye muscle being partitioned into；
According to the eye muscle in the medicine detection image the second shared pixel number and default correspondence, determine eye
The measurement result of flesh cross-sectional area；Wherein, pair of the default correspondence between presetted pixel number and actual physics area
It should be related to.
2. according to the method described in claim 1, it is characterized in that, the target to be split further includes optic nerve；Correspondingly, institute
It states and according to described image gray value, extracts the eye muscle being partitioned into, including：
The part corresponding to the gray value of image of default gray threshold be will be greater than as target to be extracted；
The optic nerve is rejected from the target to be extracted, to extract the eye muscle being partitioned into.
3. according to the method described in claim 2, it is characterized in that, the rejecting from the target to be extracted is described to regard god
Through, to extract the eye muscle being partitioned into, including：
The target to be extracted is inputted into preset model, to obtain the output of the preset model as a result, the output result packet
Include the eye muscle that extraction is partitioned into；Wherein, the preset model is previously according to the position between eye muscle sample and optic nerve sample
Relationship training obtains.
4. method according to any one of claims 1 to 3, which is characterized in that the endpoint of the cornea include upper extreme point and/or
Lower extreme point；Correspondingly, described and according to the cornea and the eyelid, generate and mark the endpoint of the cornea to the eyelid pair
The mark line of distance between endpoint is answered, including：
Generate the first mark line for marking the upper extreme point of the cornea to distance between the eyelid upper extreme point；
And/or
Generate the second mark line for marking the lower extreme point of the cornea to distance between the eyelid lower extreme point.
5. method according to any one of claims 1 to 3, which is characterized in that the method further includes：
Obtain the illumination point of the cornea；
It determines and reflects the corresponding eyelid endpoint of light spot position with described, and light spot position and the eyelid endpoint are reflected according to described, really
Second measurement result of the fixed lid retraction amount.
6. according to the method described in claim 5, it is characterized in that, the eyelid endpoint includes eyelid upper extreme point and eyelid lower end
Point；Correspondingly, the determination reflects the corresponding eyelid endpoint of light spot position with described, including：
Light spot position and the distance between the eyelid upper extreme point and the eyelid lower extreme point are reflected described in calculating separately, and will be smaller
Apart from corresponding endpoint, it is determined as reflecting the corresponding eyelid endpoint of light spot position with described.
7. according to the method described in claim 5, it is characterized in that, described and reflect light spot position and the eyelid end according to described
Point determines the second measurement result of the lid retraction amount, including：
The second measurement result of the lid retraction amount is determined according to following formula：
Second measurement result=described reflects the distance between light spot position and the eyelid endpoint-a；
Wherein, a is the decimal more than 1mm, and less than 8mm.
8. a kind of device measuring eye parameter, which is characterized in that including：
Acquiring unit, the shooting image for obtaining eye；The shooting image includes shooting photo and medicine detection image；
Generation unit, for identification in the shooting photo eye cornea and eyelid, and according to the cornea and the eyelid,
Generate the mark line for marking the endpoint of the cornea to correspond to distance between endpoint to the eyelid；
First determination unit, for by the mark line the first pixel number shared in the shooting photo, being determined as eyelid
First measurement result of the amount of shrinking back；
Recognition unit, the medicine detection image for identification, to obtain the bony structures of eye；And by the bony structures institute
The part of encirclement is determined as target to be split；
Extraction unit, the gray value of image for obtaining the target to be split, and according to described image gray value, extraction segmentation
The eye muscle gone out；
Second determination unit is used for second pixel number shared in the medicine detection image according to the eye muscle, and pre-
If correspondence, the measurement result of eye muscle cross-sectional area is determined；Wherein, the default correspondence is presetted pixel number and reality
Correspondence between physical area.
9. a kind of electronic equipment, which is characterized in that including：Processor, memory and bus, wherein
The processor and the memory complete mutual communication by the bus；
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in claim 1 to 7 is any.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in claim 1 to 7 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252230.5A CN108520512B (en) | 2018-03-26 | 2018-03-26 | Method and device for measuring eye parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810252230.5A CN108520512B (en) | 2018-03-26 | 2018-03-26 | Method and device for measuring eye parameters |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108520512A true CN108520512A (en) | 2018-09-11 |
| CN108520512B CN108520512B (en) | 2020-11-20 |
Family
ID=63434340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810252230.5A Active CN108520512B (en) | 2018-03-26 | 2018-03-26 | Method and device for measuring eye parameters |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108520512B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246158A (en) * | 2019-07-19 | 2019-09-17 | 上海交通大学医学院附属第九人民医院 | Eye illness detection device, method, electric terminal and storage medium |
| CN110448267A (en) * | 2019-09-06 | 2019-11-15 | 重庆贝奥新视野医疗设备有限公司 | A kind of multimode eyeground dynamic imaging analysis system and its method |
| CN111839455A (en) * | 2020-08-11 | 2020-10-30 | 上海鹰瞳医疗科技有限公司 | Eye sign identification method and equipment for thyroid-associated ophthalmopathy |
| CN111938567A (en) * | 2020-07-09 | 2020-11-17 | 上海交通大学 | Deep learning-based ophthalmologic parameter measurement method, system and equipment |
| CN113116292A (en) * | 2021-04-22 | 2021-07-16 | 上海交通大学医学院附属第九人民医院 | Eye position measuring method, device, terminal and equipment based on eye appearance image |
| CN113509140A (en) * | 2021-04-25 | 2021-10-19 | 安徽敏度科技有限公司 | Human body parameter measuring system based on cornea parameter and using method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080050002A1 (en) * | 2001-11-21 | 2008-02-28 | Arnold Ben A | Display and Analysis of Medical Images Using Calibrated Pixel Values in Units of Known Properties of Reference Materials |
| US20120148130A1 (en) * | 2010-12-09 | 2012-06-14 | Canon Kabushiki Kaisha | Image processing apparatus for processing tomographic image of subject's eye, imaging system, method for processing image, and recording medium |
| CN105095885A (en) * | 2015-09-06 | 2015-11-25 | 广东小天才科技有限公司 | Human eye state detection method and detection device |
| CN104657722B (en) * | 2015-03-10 | 2017-03-08 | 吉林大学 | Eye parameter detection equipment |
| CN106997594A (en) * | 2016-01-26 | 2017-08-01 | 上海联影医疗科技有限公司 | The localization method and device of a kind of part tissue of eye |
-
2018
- 2018-03-26 CN CN201810252230.5A patent/CN108520512B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080050002A1 (en) * | 2001-11-21 | 2008-02-28 | Arnold Ben A | Display and Analysis of Medical Images Using Calibrated Pixel Values in Units of Known Properties of Reference Materials |
| US20120148130A1 (en) * | 2010-12-09 | 2012-06-14 | Canon Kabushiki Kaisha | Image processing apparatus for processing tomographic image of subject's eye, imaging system, method for processing image, and recording medium |
| CN104657722B (en) * | 2015-03-10 | 2017-03-08 | 吉林大学 | Eye parameter detection equipment |
| CN105095885A (en) * | 2015-09-06 | 2015-11-25 | 广东小天才科技有限公司 | Human eye state detection method and detection device |
| CN106997594A (en) * | 2016-01-26 | 2017-08-01 | 上海联影医疗科技有限公司 | The localization method and device of a kind of part tissue of eye |
Non-Patent Citations (3)
| Title |
|---|
| 杨军等: ""上睑下垂诊治专家共识"", 《中华医学杂志》 * |
| 赵毅凯: ""定量眼眶冠状位CT测量在甲状腺相关眼病中的应用"", 《实用放射学杂志》 * |
| 高保清: ""下睑退缩的原因和治疗"", 《眼科》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246158A (en) * | 2019-07-19 | 2019-09-17 | 上海交通大学医学院附属第九人民医院 | Eye illness detection device, method, electric terminal and storage medium |
| CN110246158B (en) * | 2019-07-19 | 2021-10-22 | 上海交通大学医学院附属第九人民医院 | Eye disease detection device, method, electronic terminal, and storage medium |
| CN110448267A (en) * | 2019-09-06 | 2019-11-15 | 重庆贝奥新视野医疗设备有限公司 | A kind of multimode eyeground dynamic imaging analysis system and its method |
| CN110448267B (en) * | 2019-09-06 | 2021-05-25 | 重庆贝奥新视野医疗设备有限公司 | Multimode fundus dynamic imaging analysis system and method |
| CN111938567A (en) * | 2020-07-09 | 2020-11-17 | 上海交通大学 | Deep learning-based ophthalmologic parameter measurement method, system and equipment |
| CN111938567B (en) * | 2020-07-09 | 2021-10-22 | 上海交通大学 | Deep learning-based ophthalmologic parameter measurement method, system and equipment |
| CN111839455A (en) * | 2020-08-11 | 2020-10-30 | 上海鹰瞳医疗科技有限公司 | Eye sign identification method and equipment for thyroid-associated ophthalmopathy |
| CN113116292A (en) * | 2021-04-22 | 2021-07-16 | 上海交通大学医学院附属第九人民医院 | Eye position measuring method, device, terminal and equipment based on eye appearance image |
| CN113509140A (en) * | 2021-04-25 | 2021-10-19 | 安徽敏度科技有限公司 | Human body parameter measuring system based on cornea parameter and using method thereof |
| CN113509140B (en) * | 2021-04-25 | 2023-09-15 | 极智视觉科技(合肥)有限公司 | Human body parameter measurement system based on cornea parameters and application method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108520512B (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520512A (en) | A kind of method and device measuring eye parameter | |
| KR102339915B1 (en) | Systems and methods for guiding a user to take a selfie | |
| CN111862044B (en) | Ultrasonic image processing method, ultrasonic image processing device, computer equipment and storage medium | |
| CN108875452A (en) | Face identification method, device, system and computer-readable medium | |
| JP2020507836A (en) | Tracking surgical items that predicted duplicate imaging | |
| CN108875485A (en) | A kind of base map input method, apparatus and system | |
| JP6842481B2 (en) | 3D quantitative analysis of the retinal layer using deep learning | |
| CN106037651B (en) | A kind of heart rate detection method and system | |
| CN107341762B (en) | Photographing processing method and device and terminal equipment | |
| CN109685713B (en) | Cosmetic simulation control method, device, computer equipment and storage medium | |
| KR102014660B1 (en) | Improved age modelling method | |
| CN108256404A (en) | Pedestrian detection method and device | |
| CN109662686A (en) | A kind of fundus flavimaculatus localization method, device, system and storage medium | |
| WO2021190656A1 (en) | Method and apparatus for localizing center of macula in fundus image, server, and storage medium | |
| CN109086723A (en) | A kind of method, apparatus and equipment of the Face datection based on transfer learning | |
| CN111028218B (en) | Fundus image quality judgment model training method, fundus image quality judgment model training device and computer equipment | |
| CN113689359B (en) | Image artifact removal model and training method and system thereof | |
| US11263494B2 (en) | Classification device, classification method, program, and information recording medium | |
| CN113658165B (en) | Cup/disc ratio determining method, device, equipment and storage medium | |
| CN106446805B (en) | A kind of eyeground shine in optic cup dividing method and system | |
| CN113920109A (en) | Medical image recognition model training method, recognition method, device and equipment | |
| CN113436070A (en) | Fundus image splicing method based on deep neural network | |
| CN107368817A (en) | Face identification method and device | |
| CN110008922A (en) | Image processing method, unit, medium for terminal device | |
| CN112861743A (en) | Palm vein image anti-counterfeiting method, device and equipment |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210720 Address after: 310018 22nd floor, building 1, 199 Yuancheng Road, Xiasha street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Patentee after: Hangzhou Zhuojian Information Technology Co.,Ltd. Address before: 100085 Haidian District, Beijing 1 High Court No. 18 building 103-86 Patentee before: BEIJING MEDP.AI INTELLIGENT TECHNOLOGY Co.,Ltd. |