CN110393504A

CN110393504A - A kind of method and device of pupil detection

Info

Publication number: CN110393504A
Application number: CN201810371837.5A
Authority: CN
Inventors: 高峰; 高金铎
Original assignee: Individual
Current assignee: Individual
Priority date: 2018-04-24
Filing date: 2018-04-24
Publication date: 2019-11-01
Anticipated expiration: 2038-04-24
Also published as: CN110393504B

Abstract

The present invention is suitable for computer control and detection technique field, provides a kind of method and device of pupil detection, comprising: by the pupil iris image in the environment of different luminous fluxes, obtaining measurand；The pupil iris image includes benchmark image, dark pupil image and bright pupil image；The benchmark image is used to indicate the pupil iris image of the measurand in default luminous flux；Calculate separately the first ratio between the pupil area in the benchmark image and iris area, the second ratio between the pupil area and iris area in the dark pupil image and the third ratio between pupil area and iris area in the bright pupil image；According to first ratio, second ratio, the third ratio and default detection model, determine whether the pupil of the measurand is abnormal.Benchmark image, dark pupil image and the bright pupil image of the measurand in environment by obtaining different luminous fluxes, and the ratio in these images between pupil area and iris area, ratio determines whether the pupil of measurand is abnormal according to area, the accuracy and universality that ensure that pupil detection, improve the precision of pupil detection.

Description

A kind of method and device of pupil detection

Technical field

The invention belongs to computer control and detection technique field more particularly to a kind of method and devices of pupil detection.

Background technique

The eyes acquisition of information organ important as human body also reflects human body while obtaining ambient light radiation information The lesion situation of multiple tissues and organ.Pupil is expanding or shrinking of occurring after stimulation by different illumination, but controls pupil What hole changed is the sympathetic nerve and parasympathetic nerve in oculomotor nerve.Once these nervous systems are impaired, control pupil becomes The ability of change also just loses, this is also exactly based on pupil variation it can be observed that certain pathogenetic mechanism of disease.By to eye The observation and measurement of eyeball are not only it can be found that ophthalmology disease, it might even be possible to early diagnose to some systemic diseases.

For the prior art by measuring to pupil diameter and its size variation, ophthalmologic operation and curative effect are commented in realization Estimate, or the diagnosis to various diseases.But existing pupillometry mode is easy by external environment and measured's condition It influences, measurement accuracy is poor, and causes to calculate error or determine misalignment.

Summary of the invention

In view of this, the embodiment of the invention provides a kind of method and device of pupil detection, to solve in the prior art Measurement accuracy is poor, be easy influenced by external environment and measured's condition, measurement accuracy is poor, and cause calculate error or Person determines the problem of misalignment.

The first aspect of the embodiment of the present invention provides a kind of method of pupil detection, comprising:

In the environment of different luminous fluxes, the pupil iris image of measurand is obtained；The pupil iris image includes Benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating the measurand in default luminous flux Pupil iris image；

Calculate separately the first ratio, the dark pupil image between the pupil area in the benchmark image and iris area In pupil area and iris area between the second ratio and the bright pupil image in pupil area and iris area it Between third ratio；

According to first ratio, second ratio, the third ratio and default detection model, the quilt is determined Whether the pupil for surveying object is abnormal.

The second aspect of the embodiment of the present invention provides a kind of device of pupil detection, comprising:

Image acquisition unit, the pupil iris image of measurand when for obtaining different luminous fluxes；The pupil iris Image includes benchmark image, dark pupil image and bright pupil image；Described in the benchmark image is used to indicate in default luminous flux The pupil iris image of measurand；

Ratio calculation unit, for calculating separately first between the pupil area in the benchmark image and iris area The pupil in the second ratio and the bright pupil image between pupil area and iris area in ratio, the dark pupil image Third ratio between area and iris area；

Abnormal deciding means, for according to first ratio, second ratio, the third ratio and default inspection Model is surveyed, determines whether the pupil of the measurand is abnormal.

The third aspect of the embodiment of the present invention provides a kind of device of pupil detection, comprising: processor, input equipment, Output equipment and memory, the processor, input equipment, output equipment and memory are connected with each other, wherein the memory For storing the computer program for supporting device to execute the above method, the computer program includes program instruction, the processing Device is configured for calling described program instruction, the method for executing above-mentioned first aspect.

The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer storage medium It is stored with computer program, the computer program includes program instruction, and described program instruction makes institute when being executed by a processor State the method that processor executes above-mentioned first aspect.

Existing beneficial effect is the embodiment of the present invention compared with prior art: by the environment of different luminous fluxes, Obtain the pupil iris image of measurand；The pupil iris image includes benchmark image, dark pupil image and bright pupil image； The benchmark image is used to indicate the pupil iris image of the measurand in default luminous flux；Calculate separately the benchmark The first ratio between pupil area in image and iris area, the pupil area in the dark pupil image and iris area it Between the second ratio and pupil area and iris area in the bright pupil image between third ratio；According to described first Ratio, second ratio, the third ratio and default detection model determine whether the pupil of the measurand is different Often.Benchmark image, dark pupil image and the bright pupil image of the measurand in environment by obtaining different luminous fluxes, and these Ratio in image between pupil area and iris area, ratio determines whether the pupil of measurand is abnormal, protects according to area The accuracy and universality for having demonstrate,proved pupil detection, improve the precision of pupil detection.

Detailed description of the invention

It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these Attached drawing obtains other attached drawings.

Fig. 1 is a kind of flow chart of the method for pupil detection that one embodiment of the invention provides；

Fig. 2 is the schematic diagram of the human eye that one embodiment of the invention provides and camera；

Fig. 3 is the schematic diagram for the human eye image-forming principle that one embodiment of the invention provides；

Fig. 4 is the schematic diagram of the camera aperture that one embodiment of the invention provides and pupil of human；

Fig. 5 is the pupil diameter light influence curve figure that one embodiment of the invention provides；

Fig. 6 be another embodiment of the present invention provides a kind of pupil detection method flow chart；

Fig. 7 is the mobile phone camera camera lens schematic diagram that one embodiment of the invention provides；

Fig. 8 is traditional lens barrel transformation schematic diagram that one embodiment of the invention provides；

Fig. 9 is the lens barrel organigram that one embodiment of the invention provides；

Figure 10 is the schematic diagram that the lens barrel for Fig. 9 that one embodiment of the invention provides is mounted on mobile phone；

Figure 11 is a kind of schematic diagram for image-pickup device that one embodiment of the invention provides；

Figure 12 is the schematic diagram of the application method for the image-pickup device that one embodiment of the invention provides；

Figure 13 is variation schematic diagram of the pupil of one embodiment of the invention offer under the conditions of different luminous fluxes；

Figure 14 is the processing result image schematic diagram for the benchmark image that one embodiment of the invention provides；

Figure 15 is the bitmap of pixels for the pupil image that one embodiment of the invention provides；

Figure 16 is the schematic diagram that the image ratio that one embodiment of the invention provides calculates；

Figure 17 is a kind of schematic diagram of the device for pupil detection that one embodiment of the invention provides；

Figure 18 be another embodiment of the present invention provides a kind of pupil detection device schematic diagram；

Figure 19 is a kind of schematic diagram of the device for pupil detection that yet another embodiment of the invention provides.

Specific embodiment

In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity The detailed description of road and method, in case unnecessary details interferes description of the invention.

In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.

It is a kind of flow chart of the method for pupil detection that one embodiment of the invention provides referring to Fig. 1, Fig. 1.The present embodiment The executing subject of the method for middle pupil detection is the device with pupil detection function, including but not limited to computer, plate electricity The devices such as brain, camera or terminal.The method of pupil detection as shown in Figure 1 may comprise steps of:

S101: in the environment of different luminous fluxes, the pupil iris image of measurand is obtained；The pupil iris image Including benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating described tested in default luminous flux The pupil iris image of object.

Eyes are most important organs in human sensory, are made of the accessory organ of eyeball and eye.We have seen that eyeball Mainly it is made of sclera, iris and pupil.Pupil is the small sircle hole at iris center in eyes, and two sides etc. are big, waits circles, edge is whole Together, the channel of eyes is entered for light.Eyes can distinguish the light of different color and brightness, and these information are transformed into mind Through signal, brain is sent to.The effect of pupil and the aperture of camera be it is the same, pupil can with the variation of intensity of illumination and Variation is reduced at light, is dissipated greatly at half-light, is generally fluctuated between 2 to 8 millimeters.

Referring to Figure 2 together and shown in Fig. 3, the eyes of people are exactly a camera, and in fact camera is exactly according to people The construction invention production of eye.In camera principle, the human eye dioptric system that is made of cornea, aqueous humor, crystal and vitreum It is equivalent to the camera lens of camera, pupil is exactly the auto iris of camera.

Referring to Figure 4 together shown in, aperture be control enter camera lens light number, instantaneous aperture in camera Construction is entirely to imitate pupil alignment, and when strong illumination, for protection, eyeground is unlikely is burnt, people can reduce automatically pupil with It reduces light-inletting quantity and protects eyeground, here it is the photocontrol mechanism of pupil.

Since control mechanism of the light to pupil is the objective law that human eye follows, so pupil under detection different illumination conditions Change rate, and it is very reliable for diagnosing the illness accordingly.Clinically, other than implementing ophthalmologic operation, other are based on surveying The diagnosis for measuring pupil diameter can be using the simpler and more practical method substitution based on detection pupil ratio variation.Pupil pair The reaction of light is controlled by brain stem, and the dynamic change of pupil can reflect higher nervous activity and its physiological status, when in people Poison is sucked and can cause to damage to brain stem after certain drugs.Therefore it is detected whether by the dynamic change to pupil to suck poison Product (drug abuse) are same effective with the inspection of traditional urine examination, blood examination and saliva.

In the present embodiment, through pupil detector under different illumination conditions, obtain benchmark image, dark pupil image and Bright pupil image.Wherein, benchmark image is the pupil iris image of the measurand in default luminous flux, generally indoor or outdoors It is protected from light under the conditions of direct projection and obtains；Dark pupil image needs obtain in the lower environment of luminous flux, such as in night or dark room conditions Lower acquirement；Bright pupil image needs obtain in the higher environment of luminous flux, such as under light or the stronger environment of sunlight It obtains.

Since ordinary video probe or mobile phone can not absorb image under the conditions of illumination is insufficient, so the present embodiment is adopted With under scotopia environment, after giving light stimulus, dark pupil image and bright pupil image are absorbed respectively.

It please together as shown in connection with fig. 5, is after giving light stimulus under scotopia environment, the pupil that reflex contraction occurs for pupil is straight The dynamic schematic diagram that diameter changes over time.Wherein x is time shaft, and y-axis is pupil diameter.In figure as it can be seen that when issuing stimulates light A Before, dark pupil diameter is 5.7mm or so, is issuing stimulation light A to during issuing stimulation light B, i.e. during A → B, pupil is still protected It holds as dark pupil state, is incubation period during this (usual incubation period is about 0.2 second)；The laser c phase is pierced to sending issuing stimulation light B Between, i.e. during B → C, become the contraction phase, in C point (usually 1 second or so after light stimulus), pupil diameter is retracted to most It is small less than 3.5mm；Over time, pupil is gradually restored to dark pupil state.As it can be seen that only need to be A → B sections and C in figure Point intake can get the video figure during the dark pupil image and bright pupil image of pupil shot, or the entire A → C of intake Minimum and maximum diameter as can also therefrom find pupil.

It should be noted that the present invention has no essence when pupil image is absorbed unlike obtaining from traditional pupil image True required distance, as long as reaching clear intake.

S102: the first ratio between the pupil area in the benchmark image and iris area, described dark is calculated separately The pupil area and iris in the second ratio and the bright pupil image between pupil area in pupil image and iris area Third ratio between area.

After getting the pupil iris image of measurand, the pupil and iris in the pupil iris image are identified, And calculate separately benchmark image, dark pupil image and pupil area and iris area in bright pupil image.Calculating benchmark figure later The first ratio between pupil area and iris area as in, the between pupil area and iris area in dark pupil image Third ratio between two ratios and the pupil area in bright pupil image and iris area.

By calculating the ratio between the pupil area and iris area in each image, pupil in different images can be determined Relative size.Directly measurement pupil diameter is avoided come when carrying out dyscoria judgement, due to gender, age or ethnic group etc. The influence of factor, and make the problem of judging result inaccuracy.

S103: it according to first ratio, second ratio, the third ratio and default detection model, determines Whether the pupil of the measurand is abnormal.

After the size for calculating the first ratio, the second ratio, third ratio, according to the first ratio, the second ratio, Three ratios and default detection model determine whether the pupil of measurand is abnormal.

Optionally, can judge whether the pupil of measurand is abnormal by preset fractional threshold.By in advance will Data sample is sorted out, and ratio when dyscoria caused by the different different factors of cause between pupil area and iris area is obtained It is worth section, the pupil area of the pupil iris image currently got according to these ratio interval judgements and the ratio of iris area It in which ratio section, and then determines whether the pupil is abnormal, and can determine that quilt corresponding to the pupil iris image Whether normal survey object.

It should be noted that the reason of dyscoria in the present embodiment may include: measurand occur cerebral lesion, in Pivot nervous system infectious diseases, cerebrovascular disease, cerebral anoxia, brain tumor, craniocerebral trauma, drug poisoning, pain, fear, first shape Gland hyperfunction, birth defect and drug abuse etc., herein without limitation.

Above scheme, by the pupil iris image in the environment of different luminous fluxes, obtaining measurand；The pupil Iris image includes benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating in default luminous flux The pupil iris image of the measurand；Calculate separately between the pupil area in the benchmark image and iris area The pupil in the second ratio and the bright pupil image between pupil area and iris area in one ratio, the dark pupil image Third ratio between hole area and iris area；According to first ratio, second ratio, the third ratio and Default detection model determines whether the pupil of the measurand is abnormal.It is tested in environment by obtaining different luminous fluxes The benchmark image of object, dark pupil image and bright pupil image, and the ratio in these images between pupil area and iris area, Ratio determines whether the pupil of measurand is abnormal, ensure that the accuracy and universality of pupil detection, improves according to area The precision of pupil detection.

Referring to Fig. 6, Fig. 6 be another embodiment of the present invention provides a kind of pupil detection method flow chart.This implementation The executing subject of the method for pupil detection is the device with pupil detection function, including but not limited to computer, plate in example The devices such as computer, camera or terminal.The method of pupil detection as shown in FIG. 6 may comprise steps of:

S601: the identity information of the measurand is acquired.

Since the device of dyscoria detection can be used for the detection on the gathering of people such as border, airport, station ground, and need herein Stringent security guard is wanted, therefore, by obtaining the identity information of measurand, to determine the rainbow of accessed measurand Film pupil image and its identity information are consistent.Simultaneously as the pupil feature of the mankind by its gender, age or race etc. because The influence of element can determine the normal pupil characteristic range of the measurand, to its pupil by obtaining its identity information Whether exception is reasonably detected and is judged.

In the embodiment of the present invention, preset client software is installed in the device of pupil detection, client software is used for Control the step in each embodiment of the mobile phone execution present invention.Based on above-mentioned client software, the device of pupil detection and service Device communication is connected.The identity information input instruction issued in client software according to user, can collect measurand Identity information.

Optionally, the device for acquiring the identity information of measurand can be mobile terminal, it is preferred that the mobile terminal is matched The rear camera of 8,000,000 pixels or more is set, is furnished with flash lamp and fingerprint acquisition device, and it is soft to install special detection Part is responsible for the identity information of acquisition measurand, automatically generates detection table, biometric identity acquisition and the differentiation of pupil data information Work.Such terminal detection device is suitble to outlying district and field work.

Optionally, the device for acquiring the identity information of measurand can be computer well, is preferably somebody's turn to do, installs in calculating There are identity card reader and video probe.The computer and mobile terminal are also provided with inspection software, which is responsible for operation Login management, detection the automatically generating of table, the acquisition of the license identity-acquiring of detected person, biometric identity and the pupil data of person The acquisition of information differentiates work.Identity card reader on computer is responsible for the examination of detected person's identity, and video probe is responsible for The iris of detected person and the acquisition of pupil information.This Terminal Type is suitable for the inspection on the gathering of people ground such as border, airport, station It surveys.

It should be noted that the identity information of the measurand in the present embodiment include but is not limited to name, certificate number or Person records the certificate image etc. for having identity information.

S602: being uploaded to server for the identity information, and obtain the server verify the identity information it The authentication information sent afterwards；The authentication information is for indicating whether the identity information of the measurand is legal.

After collecting the identity information of measurand, identity information is uploaded to server, and obtain server and exist Verify the whether legal authentication information of the identity information of the measurand sent after identity information；

Optionally, pupil detection device control certificate of the camera shooting direction towards measurand, with to certificate into After row shooting, the certificate image comprising identity information is uploaded to server so that server to the identity information of the certificate into Row verifying.Wherein, above-mentioned certificate includes but is not limited to that identity card, passport, the pass and driver's license etc. have unique identities mark The certificate of knowledge.

Optionally, the device of pupil detection obtains the text formatting of measurand identity information, then by the body of measurand Part information is directly uploaded to server.For example, the identification card number of measurand is uploaded to server, to the identification card number institute Corresponding measurand identity is verified.

After identity information is uploaded to server, the authentication information for the measurand that server returns is received, Authentication information is for determining the corresponding people of the identity information with the presence or absence of illegal activities.

S603: if the identity information of the measurand is legal, measurand when different luminous fluxes is obtained respectively Pupil iris image.

If the authentication information for receiving server return is legal, confirm that user identity to be detected is verified correctly, this When, its identity information is recorded in pre-generated table, and trigger pupil image collection event；If receiving server return Authentication information it is illegal, then confirm that user identity to be detected verifies failure, at this point, triggering identity abnormality processing event.

It should be noted that the benchmark image in the present embodiment can be the general pupillogram read and obtained under light environment Picture；Bright pupil image and dark pupil image refer to the pupil image obtained respectively under intense light irradiation and half-light environment.

Illustratively, using mobile phone as a kind of device of pupil detection, since cell phone cameras is in addition in lens optical spy Property on have outside gap with mm professional camera special, pixel number is very nearly the same with entry-level professional camera, image processing function even win In mm professional camera special, therefore, the image capture to pupil, place are realized in photograph and software processing capability of the present embodiment using mobile phone Reason and judgement.

Referring to Figure 7 together, shown in Fig. 8, Fig. 9 and Figure 10, it is arranged in mobile phone camera camera lens and being ingested between eyeball One tubular article as shown in Figure 7, shape and telescope or microscopical eyepiece are alike.Without eyeglass in lens barrel, does not rise and appoint What optical amplifier effect.Its purpose has two, first is that shot pupil and camera lens is made to be unlikely to too close apart from relatively fixed, To guarantee the clarity of image；Two shrouding come lens barrel whereby, apply more uniform when artificial light sources, while also having completely cut off tested The free possibility of pupil.Mobile phone lens barrel is passive component, is not required to have any connection electrically with mobile phone.Need to only it try when use Before being fixed in mobile lens.Fig. 8 is one of which side that is improved to Fig. 7 lens barrel and being fixed on mobile phone Formula.Lens barrel can also be arranged to Fig. 9 form, wherein lens barrel is made of liner, window and housing, and this form is obtaining commonly When pupil image, mobile phone energy consumption can be reduced by external light source, Figure 10 is the schematic diagram that Fig. 9 lens barrel is mounted on mobile phone.

In airport, station and border port, the common identity verification being arranged into channel and safety inspection facility.Challenge work Work is implemented by identity card reader, it can differentiate whether licensee and certificate are same people, while also it can be seen that this is accredited Whether person is chasing personnel；Safety check apparatus can only detect metal parts at present, can not also give effective inspection to drugs, explosive etc. Out.Drug addict is clearly to belong to be prohibited from entering channel scope, but means can not also be applied to such scene at present.It is aobvious and easy What is seen is, it is impossible to allow it is all enter safety checks, verifying channel personnel carry out blood examination or urine examination.

Also referring to shown in Figure 11, the image-pickup device for adding lighting device to form by ordinary camera camera lens, it can It is installed on above the verifying window in identity verification channel, while examining identity card to shine, only authenticatee is needed to watch camera lens attentively Head, such as Figure 12.Because contacting without human eye socket of the eye with camera parts, not only detected person will not cause without psychological burden Disease infects.It, can be because of height, stance etc. no for different verifiers due to there is no the fixed device of lens barrel, goggle type Together, so that the intake of pupil image is realized under entirely different distance, it can also say and get in dynamic state. Also referring to shown in Figure 12, the pupil and distance of camera lens of detected person A, B and C are different.In verifying, the behaviour of inspection software Under control, control pick-up lens implements the intake of pupil image to the personnel that are verified, and further analyzes, judges whether to belong to drugs Smoker.

It is known that common camera sensor devices are can not to obtain image information when illuminance is lower than certain value , therefore special night vision system provides illumination using infraluminescence, the original part of infrared signal can be read as sensor devices by using Realize the intake of nighttime image.And common photographic film can not obtain image under no light environment, for this purpose, devising Under low or no light environment, apply stimulation illumination, and control and absorb dark pupil image between pupil incubation period A, B of Fig. 5, and The C point of Fig. 5 absorbs bright pupil image.Experiment shows that the time of incubation period A-B is about 0.2 second, and C point is about 1 second after light stimulus.

In the mode shown in Figure 11, Figure 12, half-light, strong light and normal illumination environment are built respectively and is relatively easy to, It needs to be detected control software if according to Fig. 8 mobile phone lens barrel mode by mobile phone and simulates the dark pupil of intake, bright pupil and common respectively The light environment of pupil；According to the mobile phone lens barrel mode of Figure 10, then need to simulate the light environment of bright pupil and the intake of dark pupil.

Either mobile phone camera flash lamp or video camera floor light, be all controlled by electronic switch its open or It closes, its brightness is remained the same from beginning to end after switching opening, is not shone then after closing.So light switch can be enabled to issue duty Than different pulse open signal, the brightness of illumination is controlled.

The pupil status situation of change controlled under different luminous flux environment is illustrated also referring to Figure 13, Figure 13.T in figure For Lighting control pulse signal cycle, it is the high potential duration that wherein t1, which is pulse,；T2 is the pulse low potential duration.If It is occupied completely by signal t1 in T time, then switching signal is permanent high at this time, is equivalent to switch and opens；If completely by believing in T time Number t2 is occupied, then switching signal perseverance is low at this time, is equivalent to switch and is closed.As t1=t2, i.e., when signal dutyfactor is 1:1, shine Bright power is half when control switch signal constant is high；As t1 > t2, luminous flux tends to become strong, and luminous intensity is higher, i.e., brighter；When When t2 > t1, luminous flux tends to become weak, and luminous intensity is lower, i.e., darker.So by the way that multiple and different duty ratios, delay length is arranged For the application programming interface (Application Programming Interface, API) of t, each difference API table shows Different luminous fluxes absorbs corresponding pupil image in the environment of different luminous fluxes respectively.

It is the face benchmark image obtained through general camera or mobile phone also referring to Figure 14, Figure 14, by the bright of routine The conventional computers image processing process such as degree, contrast, exposure, hue saturation, tone separation, threshold value, have ultimately produced just In the image of identification.

S604: the first ratio between the pupil area in the benchmark image and iris area, described dark is calculated separately The pupil area and iris in the second ratio and the bright pupil image between pupil area in pupil image and iris area Third ratio between area.

It clinically, is that 3-4mm is determined as normal pupil by pupil diameter, if pupil diameter < 2mm is to reduce pupil, pupil Diameter > 5mm is mydriasis.In pupil diameter decision procedure, the bright pupil pupil diameter (microcoria) and normal pupil of pupil To reduce pupil when diameter ratio < 2/4；It is pupil when dark the ratio between Core- diameter (big pupil) and normal pupil diameter > 5/3 Dissipate big, statement are as follows:

Normal pupil diameter: NP_D=3.5mm ± 0.5mm；

Reduce pupil diameter: the ratio between bright pupil and normal pupil diameter BP_D/NP_D<2/4；

Dissipate big pupil diameter: dark the ratio between pupil and normal pupil diameter DP_D/NP_D> 5/3；

Wherein the meaning of letter abbreviations is respectively as follows: BP_DFor indicating bright pupil pupil diameter, DP_DFor indicating that dark Core- is straight Diameter；NP_DFor indicating normal pupil diameter.

Since the present embodiment can implement differentiation under conditions of obtaining pupil dynamic image, under certain special states The data that (such as because pathology or some photic stimulis of physiological reason lose the pupil of reaction) only has pupil are also not enough to realize accurately Differentiate, therefore introduce a new data: pupil area and iris area ratio.Under the different light environments got after taking pictures Pupil image, obtain bitmap of pixels as shown in figure 15 after processing.On the basis of this pixel map, it is easy to calculate difference The area of pupil, and then analyze and determine out different interpupillary relationships.It clinically, is all with straight to the detection of pupil or measurement Diameter is as standard, in the present invention, has not both had master sample disk, also due to intake interpupillary distance is indefinite, therefore can not Calculating is made to diameter.But due to pupil be characterized in it is circular, can also be with therefore using diameter as the method for pupil criterion It is indicated by the judgement of pupil area.According to the pupil in pupil iris image accessed in the environment of different luminous fluxes Area and iris area calculate separately in benchmark image, dark pupil image and bright pupil image between pupil area and iris area Ratio, and using these ratios as the first ratio, the second ratio and third ratio.

S605: if second ratio is greater than first ratio or the third ratio is less than first ratio When, then determine the dyscoria of the measurand.

Also referring to shown in Figure 16, when pupil loses the reaction of photic stimuli, it may be in always and dissipate big state Or it is in diminution pupil status always.Such as only has BP_D/NP_DOr DP_D/NP_DParameter is can not to learn that current pupil is to locate always In any state, and then influence whether the differentiation to it.By the relativeness of it and iris, it can assert which kind of it is in State.There is no pupil diameter data in the present invention, therefore use pupil area computational discrimination in the differentiation to pupil status, It is expressed as example with above-mentioned, can be stated again with area are as follows:

Benchmark image area: 2.78 > NP_A> 1/4；

Reduce pupil area: the ratio between pupil area in bright pupil pupil area and benchmark image BP_A/NP_A<1/4；

Dissipate big pupil area: the ratio between pupil area in dark Core- area and benchmark image DP_A/NP_A> 2.78；

Non-reference image value: pupil area and iris area ratio P_A/I_A；

Wherein the meaning of letter abbreviations is respectively as follows: BP_AFor indicating bright pupil pupil area, DP_AFor indicating dark Core- face Product；NP_AFor indicating the pupil area in benchmark image.

Above formula shows that in the present invention the ratio of " dark Core- area and the ratio between the pupil area in benchmark image " is small In 2.78, and while being greater than the ratio 1/4 of " the ratio between the pupil area in bright pupil pupil area and benchmark image " is benchmark image.If The ratio of " the ratio between the pupil area in bright pupil pupil area and benchmark image " is then judged to reducing pupil less than 1/4.As " secretly The ratio of the ratio between pupil area in Core- area and benchmark image " is greater than > 2.78, then is judged to dissipating big pupil.Work as P_A/I_A> > " the ratio between the pupil area in dark Core- area and benchmark image " or P_A/I_AIn < < " bright pupil pupil area and benchmark image When the ratio between pupil area ", pupil is in abnormality at this time.The former pupil loses the reaction of photic stimuli, and pupil is in always Big shape is dissipated, the latter is in diminution shape always, they may be that blindness or other improper reasons cause.

Further, step S605 can also be specifically included:

According to the identity information of the measurand, determination is suitble to the measurand identity from default detection model Judge parameter；

According to first ratio, second ratio, the third ratio, the detection model and judge parameter, Determine whether the pupil of the measurand is abnormal.

The variation of pupil size, in addition to the control of light, also with the distance of fixation object, age, gender, ethnic group, spirit State is related to refractive status.So when carrying out pupil detection, it is desirable that detected person is in relatively flat and quiet, fixed-illumination In the environment of intensity, and measured under conditions of unified blinkpunkt.Due to ethnic group, gender and optic nerve systematic growth degree Difference, so that different crowds is different to the sensitivity of light, this has resulted in the difference of congenital pupil size between them.Such as Someone benchmark image diameter is 3mm, this pupil diameter of possible 3mm belongs to diminution pupil, institute in addition some kind clansman To be relatively difficult and many and diverse by differentiating pupil size degree to diagnose the illness.Because have to the age, gender known to and The diameter of pupil is measured in the case where ethnic group, can make relatively accurate judgement.

Clinically the pupil diameter of so-called benchmark image is that statistics obtains mean values, carries out drug (drug abuse) using it When pupil judges, it is appropriate only for a certain types of populations, such as meets the Hans, male, person between twenty and fifty's prerequisite.If expanding detection Range, it is possible to cause biggish error.As previously mentioned, the pupil diameter because of people is related to ethnic group, age, gender, intake away from From difference can also generate diameter error, therefore measured using conventional diameter and sentence method for distinguishing there are numerous uncertainties.And Area measurement method of discrimination avoids because of non-determined factors such as age, intake distances, is effectively guaranteed the accuracy of measurement.

Since the pupil diameter of user is related to its age, gender, and when shooting distance difference, the pupil detected is straight Diameter can also generate error, therefore, in the embodiment of the present invention, be carried out based on the pixel digit ratio of pupil image with preset threshold Size comparison, whether the pupil that can quickly detect measurand is abnormal, due to being not necessarily to measure pupil diameter during this, The influence by many factors such as the age of measurand and shooting distances is avoided, testing result is effectively guaranteed Accuracy.

S606: if the dyscoria of the measurand, according to first ratio, second ratio, described Three ratios and the detection model determine the different reason of currently cause of the pupil of the measurand.

Whether it is abnormal after the meeting in the pupil for judging measurand, if the dyscoria of measurand, according to first Ratio, the second ratio, third ratio and detection model determine the different reason of currently cause of the pupil of measurand.

Further, step S606 can also specifically include S6061~S6063:

S6061: if the dyscoria of the measurand, according to the corresponding pupil of numerical intervals each in the detection model Hole characteristic determines corresponding first pupil feature of first ratio, corresponding second pupil feature of second ratio and institute State the corresponding third pupil feature of third ratio.

In traditional determination method, the judgement of abnormal pupillary is dependent on limited data sample and makes, unquestionably Be that sample size is bigger, determine it is more accurate.But one problem of bring is, how the boundary of samples selection should determine.Sample This quantity causes accuracy to decline very little, and sample size is sufficiently large the system resources such as to take a substantial amount of time.Effectively to solve The deficiency of conventional method, the basic technology that the present embodiment uses artificial intelligence control includes fuzzy control technology, Multimode Control The methods of technology, learning control techniques.According to previous limited testing result and clinic and gross data, establishing voluntarily to learn Mathematical model.

Also referring to shown in table 1, according to existing abnormal pupillary data, m kind abnormal pupillary phenomenon is selected, is constituted abnormal Pupil set P={ P1, P2, P3 ..., Pm }.Every kind of dyscoria phenomenon is by pupil area and benchmark in different bright pupils, dark pupil The ratio of ratio, pupil and iris in image between pupil area is constituted.As in the example illustrated in table 1, m has chosen 8, this is this reality An example in example is applied, the size of the element and m value in abnormal pupillary set can be increased or decreased as the case may be, this Place is without limitation.

Table 1 detects table 1

In table 1, P/IRIS (ratio of pupil and iris), BP/NP (pupil in pupil area and benchmark image in bright pupil image Hole area ratio) and DP/NP (pupil area ratio in pupil area and benchmark image in dark pupil image) be all in advance given Numberical range, these ranges are assert by clinical detection result and expert to be provided.If each element value difference in given set P Are as follows:

x₁=0-0.15 y₁=0.95-1 z₁=0.95-1

x₂=0.15-0.25 y₂=0.13-0.2 z₂=5-6.5

x₃=0.25-0.4 y₃=0.2-0.25 z₃=2-2.5

x₄=0.4-0.5 y₄=0.25-0.3 z₄=2.5-3

x₅=0.5-0.6 y₅=0.3-0.35 z₅=3-3.5

x₆=0.6-0.7 y₆=0.35-0.4 z₆=3.5-4

x₇=0.75-0.8 y₇=0.4-0.95 z₇=2.5-3.5

x₈=0.8-1 y₈=0.95-1z₈=0.95-1

Wherein, P/IRIS points are (P/IRIS) min and (P/IRIS) max, the former is for indicating PA/IA < <benchmark image Pupil area and iris area ratio；The latter is for indicating PA/IA > > benchmark image pupil area and iris area ratio.Table Middle parameter x, y, z is instant testing result.

It should be noted that table 1 can be divided into several pieces according to age bracket, sex, race, every part of parameter is different, when After the data information for learning detected personnel, recalls corresponding detection table and implement to differentiate.

Table 1 is transformed to the mode of table 2, param elements y is by BP/IRIS (bright pupil area and iris area ratio) in table 2 Instead of BP/NP, element x is by DP/IRIS (dark pupil area and iris area ratio) instead of DP/NP.Certainly, element x, y Value will also make corresponding adjustment.

Table 2 detects table 2

Illustratively, certain parametric results for calculating measurand are as follows:

X=0.4；Y=0.2；Z=2.5

It contrasts and finds out with table 2, parameter x, y, z detection data value is respectively fallen among P2, P3 and P4, and p here is exactly Different reason is caused, illustrates that the reason of measurand pupil is abnormal may be P2, P3 or P4.

S6062: different reason coefficient is caused according to pupil feature each in the detection model is corresponding, determines first pupil Feature, second pupil feature and the corresponding different reason coefficient of cause of the third pupil feature.

Building causes different reason gather first, then n kind is taken to cause different reason (being shown in Table 1), constitutes the limited different reason collection of cause Close C={ C₁,C₂,C₃,…,C_n, wherein causing different reason may include following reason:

C₁: atropinism

C₂: cocaine poisoning

C₃: central depressant poisoning

C₄: alcoholism

C₅: blindness

...:

C_n: eye diseases

Similarly, pupil causes the element of different reason gather C can also factually additions and deletions.Wherein, factor alpha, β, γ ..., η be detection recognize Fixed number, these parameters are original to be obtained and is written according to expert opinion or previous pattern detection result.

Illustratively, certain testing result data are as follows:

X=0.4y=0.2z=2.5

It contrasts and finds out with table 2, parameter x, y, z detection data value is respectively fallen among P2, P3 and P4, and P2, P3, P4 couple The different reason coefficient of the cause answered is respectively as follows:

α 2=2 β 2=36 γ 2=7 ... η 2=0

α 3=19 β 3=2 γ 3=9 ... η 3=0

α 4=4 β 4=12 γ 4=8 ... η 4=1

By determining the abnormal corresponding different reason coefficient of cause, the various causes for causing measurand to be abnormal can be determined The weight of different reason, and then the different reason of final cause can be determined according to the different reason coefficient of cause.

S6063: according to the different reason of currently cause of all pupils for causing different reason coefficient to determine the measurand.

It after the different reason coefficient of cause has been determined, is caused in different reasons various, chooses and assert that the most coefficient institute of number is right The number that as a result, each coefficients comparison of P2, P3 and P4, " cocaine poisoning " is identified corresponding to β 2 that is answering is 36 times, belongs to and assert The most reason of number, as follows:

α 2=2 β 2=36 γ 2=7 ... η 2=0

α 3=19 β 3=2 γ 3=9 ... η 3=0

α 4=4 β 4=12 γ 4=8 ... η 4=1

That is, in this relational matrix, the ownership coefficient highest of β 2, therefore selected C2 is this testing result, i.e., " can block Because of poisoning ".The benefit of this mode is to go to compare with a large amount of data every time, especially when detection sample is mass data When can save a large amount of time loss, can be realized real-time detection differentiation.

S607: currently causing different reason according to described, updates and currently causes different reason is corresponding to cause different reason coefficient with described.

After determination currently causes different reason, according to different reason is currently caused, to currently causing, different reason is corresponding to cause different reason The value of coefficient is counted.

After testing result is identified, cause corresponding coefficient in different reason that will add " 1 ", for sentencing for testing result from now on Surely reliable foundation is increased, time loss caused by the comparing of large sample is eliminated.The learning process of this and people is The same.

Illustratively, after this time testing result is identified, just by the β 2 in table in parameter plus " 1 ", become 37.

α 2=2 β 2=37 γ 2=7 ... η 2=0

α 3=19 β 3=2 γ 3=9 ... η 3=0

α 4=4 β 4=12 γ 4=8 ... η 4=1

By determining the different reason coefficient of cause for causing different reason, can determine according to the predetermined number for causing different reason Each probability size for causing different reason to occur, and then cause different reason to do to refer to for accurate judgement, guarantee to cause different reason judgement Accuracy.

Above scheme, by the identity information for acquiring the measurand；The identity information is uploaded to server, and Obtain the authentication information that the server is sent after verifying the identity information；If the identity of the measurand is believed It is legal to cease, then obtains the pupil iris image of measurand when different luminous fluxes respectively；Calculate separately the benchmark image In pupil area and iris area between the first ratio, between pupil area and iris area in the dark pupil image Third ratio between second ratio and pupil area and iris area in the bright pupil image；If second ratio is big When first ratio or the third ratio are less than first ratio, then determine that the pupil of the measurand is different Often；If the dyscoria of the measurand, according to first ratio, second ratio, the third ratio and The detection model determines the different reason of currently cause of the pupil of the measurand；Currently cause different reason according to described, update with It is described currently to cause different reason is corresponding to cause different reason coefficient.Identity information by obtaining measurand, which determines, is suitable for tested pair The judgement parameter of elephant, and determine whether the pupil of measurand is abnormal, ensure that exception is sentenced according to pupil area and iris area Quasi- personalization and universality are calibrated, causes different reason by causing different reason coefficient to determine, and update the finally determining different reason of cause The different reason coefficient of corresponding cause, improves the accuracy judged extremely.

It is a kind of schematic diagram of the device of pupil detection provided in an embodiment of the present invention referring to Figure 17, Figure 17.Pupil detection Device include but is not limited to the devices such as computer, tablet computer, camera or terminal.The device of the present embodiment includes each Unit is used to execute each step in the corresponding embodiment of Fig. 1, referring specifically to the correlation in the corresponding embodiment of Fig. 1 and Fig. 1 Description, does not repeat herein.The device of the pupil detection of the present embodiment includes image acquisition unit 1701, ratio calculation unit 1702 And abnormal deciding means 1703.

Image acquisition unit 1701, the pupil iris image of measurand when for obtaining different luminous fluxes；The pupil Iris image includes benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating in default luminous flux The pupil iris image of the measurand；

Ratio calculation unit 1702, for calculating separately between the pupil area in the benchmark image and iris area In the second ratio and the bright pupil image between pupil area and iris area in first ratio, the dark pupil image Third ratio between pupil area and iris area；

Abnormal deciding means 1703, for according to first ratio, second ratio, the third ratio and pre- If detection model, determine whether the pupil of the measurand is abnormal.

It is the schematic diagram of the device of another pupil detection provided in an embodiment of the present invention referring to Figure 18, Figure 18.Pupil inspection The device of survey includes but is not limited to the devices such as computer, tablet computer, camera or terminal.The pupil detection of the present embodiment The each unit that device includes is used to execute each step in the corresponding embodiment of Fig. 6, referring specifically to the corresponding reality of Fig. 6 and Fig. 6 The associated description in example is applied, is not repeated herein.The device of the pupil detection of the present embodiment includes: identity information acquisition 1801, letter It ceases uploading unit 1802, image acquisition unit 1803, ratio calculation unit 1804, abnormal deciding means 1805, reason and determines list Member 1806 and coefficient update unit 1807.

Identity information acquisition 1801 acquires the identity information of the measurand for unit；

Information uploading unit 1802 for the identity information to be uploaded to server, and obtains the server and is testing Demonstrate,prove the authentication information sent after the identity information；The authentication information is used to indicate the body of the measurand Whether part information is legal；

Image acquisition unit 1803, if the identity information for the measurand is legal, obtain respectively do not share the same light it is logical The pupil iris image of measurand when amount；The pupil iris image includes benchmark image, dark pupil image and bright pupil Image；The benchmark image is used to indicate the pupil iris image of the measurand in default luminous flux；

Ratio calculation unit 1804, for calculating separately between the pupil area in the benchmark image and iris area In the second ratio and the bright pupil image between pupil area and iris area in first ratio, the dark pupil image Third ratio between pupil area and iris area；

Abnormal deciding means 1805, if being greater than first ratio or the third ratio for second ratio When less than first ratio, then the dyscoria of the measurand is determined.

Reason determination unit 1806, if the dyscoria for the measurand, according to first ratio, described Second ratio, the third ratio and the detection model determine the different reason of currently cause of the pupil of the measurand；

Coefficient update unit 1807 updates for currently causing different reason according to described and currently causes different reason corresponding with described The different reason coefficient of cause.

Further, abnormal deciding means 1805 can also specifically include:

Parameter determination unit determines from default detection model and is suitble to for the identity information according to the measurand The judgement parameter of the measurand identity；

Judging unit, for according to first ratio, second ratio, the third ratio, the detection model And judge parameter, determine whether the pupil of the measurand is abnormal.

Further, reason determination unit 1806 can also specifically include:

Characteristics determining unit, if the dyscoria for the measurand, according to numerical value each in the detection model The corresponding pupil feature in section determines corresponding first pupil feature of first ratio, corresponding second pupil of second ratio Hole characteristic and the corresponding third pupil feature of the third ratio；

Factor determination unit is determined for causing different reason coefficient according to pupil feature each in the detection model is corresponding First pupil feature, second pupil feature and the corresponding different reason coefficient of cause of the third pupil feature；

Reason judging unit, for according to the current of all pupils for causing different reason coefficient to determine the measurand Cause different reason.

Further, coefficient update unit 1807 can also specifically include:

Counting unit currently causes different reason is corresponding to cause different reason system for currently causing different reason according to described to described Several values are counted.

It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit It is fixed.

It is a kind of schematic diagram of the device for pupil detection that yet another embodiment of the invention provides referring to Figure 19, Figure 19.Such as figure The device of pupil detection in the present embodiment shown in 19 may include: that processor 1901, memory 1902 and being stored in is deposited In reservoir 1902 and the computer program 1903 that can be run on processor 1901.Processor 1901 executes computer program 1903 Step in the above-mentioned each embodiment of the method for pupil detection of Shi Shixian.Memory 1902 is used to store computer program, The computer program includes program instruction.Processor 1901 is used to execute the program instruction of the storage of memory 1902.Wherein, locate Reason device 1901 is configured for that described program instruction execution or less is called to operate:

Processor 1901 is used in the environment of different luminous fluxes, obtains the pupil iris image of measurand；The pupil Hole iris image includes benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating in default luminous flux The pupil iris image of Shi Suoshu measurand；

If processor 1901 is specifically used for, second ratio is greater than first ratio or the third ratio is less than When first ratio, then the dyscoria of the measurand is determined.

If the dyscoria of the measurand, according to first ratio, second ratio, the third ratio And the detection model, determine the different reason of currently cause of the pupil of the measurand；

Different reason is currently caused according to described, updates and currently causes different reason is corresponding to cause different reason coefficient with described.

If processor 1901 is specifically used for the dyscoria of the measurand, according to numerical value each in the detection model The corresponding pupil feature in section determines corresponding first pupil feature of first ratio, corresponding second pupil of second ratio Hole characteristic and the corresponding third pupil feature of the third ratio；

Cause different reason coefficient according to pupil feature each in the detection model is corresponding, determine first pupil feature, Second pupil feature and the corresponding different reason coefficient of cause of the third pupil feature；

According to the different reason of currently cause of all pupils for causing different reason coefficient to determine the measurand.

Processor 1901 is specifically used for currently causing different reason according to described, currently causes different reason is corresponding to cause different original to described Because the value of coefficient is counted.

Processor 1901 is specifically used for acquiring the identity information of the measurand；

The identity information is uploaded to server, and obtains the server and is sent after verifying the identity information Authentication information；The authentication information is for indicating whether the identity information of the measurand is legal；

If the identity information of the measurand is legal, the pupil of measurand when different luminous fluxes is obtained respectively Iris image.

Processor 1901 is specifically used for the identity information according to the measurand, determines and is suitble to from default detection model The judgement parameter of the measurand identity；

It should be appreciated that in embodiments of the present invention, alleged processor 1901 can be central processing unit (Central Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic Device, discrete gate or transistor logic, discrete hardware components etc..General processor can be microprocessor or this at Reason device is also possible to any conventional processor etc..

The memory 1902 may include read-only memory and random access memory, and provide instruction to processor 1901 And data.The a part of of memory 1902 can also include nonvolatile RAM.For example, memory 1902 may be used also With the information of storage device type.

In the specific implementation, processor 1901 described in the embodiment of the present invention, memory 1902, computer program 1903 Realization described in the first embodiment and second embodiment of the device of pupil detection provided in an embodiment of the present invention can be performed The implementation of terminal described in the embodiment of the present invention also can be performed in mode, and details are not described herein.

A kind of computer readable storage medium, the computer-readable storage medium are provided in another embodiment of the invention Matter is stored with computer program, and the computer program includes program instruction, and described program instructs realization when being executed by processor:

Further, it is also realized when the computer program is executed by processor:

If second ratio is greater than first ratio or the third ratio less than first ratio, Determine the dyscoria of the measurand.

If the dyscoria of the measurand, according to the corresponding pupil feature of numerical intervals each in the detection model Determine corresponding first pupil feature of first ratio, corresponding second pupil feature of second ratio and the third The corresponding third pupil feature of ratio；

Different reason is currently caused according to described, currently causes the corresponding value for causing different reason coefficient of different reason to count to described Number.

Acquire the identity information of the measurand；

The computer readable storage medium can be the internal storage unit of terminal described in aforementioned any embodiment, example Such as the hard disk or memory of terminal.The computer readable storage medium is also possible to the External memory equipment of the terminal, such as The plug-in type hard disk being equipped in the terminal, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, the computer readable storage medium can also be wrapped both The internal storage unit for including the terminal also includes External memory equipment.The computer readable storage medium is described for storing Other programs and data needed for computer program and the terminal.The computer readable storage medium can be also used for temporarily Ground stores the data that has exported or will export.

Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not It is considered as beyond the scope of this invention.

It is apparent to those skilled in the art that for convenience of description and succinctly, the end of foregoing description The specific work process at end and unit, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.

In several embodiments provided herein, it should be understood that disclosed terminal and method can pass through it Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied Another system is closed or is desirably integrated into, or some features can be ignored or not executed.In addition, shown or discussed phase Mutually between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication of device or unit Connection is also possible to electricity, mechanical or other form connections.

If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words It embodies, which is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, server or the network equipment etc.) executes the complete of each embodiment the method for the present invention Portion or part steps.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. are various can store journey The medium of sequence code.

The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right It is required that protection scope subject to.

Claims

1. a kind of method of pupil detection characterized by comprising

In the environment of different luminous fluxes, the pupil iris image of measurand is obtained；The pupil iris image includes benchmark Image, dark pupil image and bright pupil image；The benchmark image is used to indicate the pupil of the measurand in default luminous flux Hole iris image；

Calculate separately the first ratio between the pupil area in the benchmark image and iris area, in the dark pupil image Between the second ratio between pupil area and iris area and pupil area and iris area in the bright pupil image Third ratio；

According to first ratio, second ratio, the third ratio and default detection model, described tested pair is determined Whether the pupil of elephant is abnormal.

2. the method for pupil detection as described in claim 1, which is characterized in that it is described according to first ratio, described Two ratios, the third ratio and default detection model determine whether the pupil of the measurand is abnormal, comprising:

3. the method for pupil detection as claimed in claim 1 or 2, which is characterized in that it is described according to first ratio, it is described Second ratio, the third ratio and default detection model determine that the pupil of the measurand whether after exception, also wraps It includes:

If the dyscoria of the measurand, according to first ratio, second ratio, the third ratio and The detection model determines the different reason of currently cause of the pupil of the measurand；

4. the method for pupil detection as claimed in claim 3, which is characterized in that if the pupil of the measurand is different Often, then it is determined described tested according to first ratio, second ratio, the third ratio and the detection model The different reason of currently cause of the pupil of object, comprising:

If the dyscoria of the measurand, determined according to the corresponding pupil feature of numerical intervals each in the detection model Corresponding first pupil feature of first ratio, corresponding second pupil feature of second ratio and the third ratio Corresponding third pupil feature；

Different reason coefficient is caused according to pupil feature each in the detection model is corresponding, determines first pupil feature, described Second pupil feature and the corresponding different reason coefficient of cause of the third pupil feature；

5. the method for pupil detection as claimed in claim 3, which is characterized in that it is described currently to cause different reason according to described, more Newly currently cause different reason is corresponding to cause different reason coefficient with described, comprising:

Different reason is currently caused according to described, currently causes the corresponding value for causing different reason coefficient of different reason to count to described.

6. the method for pupil detection as described in claim 1, which is characterized in that the measurand when acquisition different luminous fluxes Pupil iris image, comprising:

Acquire the identity information of the measurand；

The identity information is uploaded to server, and obtains the body that the server is sent after verifying the identity information Part verification information；The authentication information is for indicating whether the identity information of the measurand is legal；

If the identity information of the measurand is legal, the pupil iris of measurand when different luminous fluxes is obtained respectively Image.

7. the method for pupil detection as claimed in claim 6, which is characterized in that it is described according to first ratio, described Two ratios, the third ratio and default detection model determine whether the pupil of the measurand is abnormal, comprising:

According to the identity information of the measurand, the judgement for being suitble to the measurand identity is determined from default detection model Parameter；

According to first ratio, second ratio, the third ratio, the detection model and judge parameter, determines Whether the pupil of the measurand is abnormal.

8. a kind of device of pupil detection characterized by comprising

Image acquisition unit, the pupil iris image of measurand when for obtaining different luminous fluxes；The pupil iris image Including benchmark image, dark pupil image and bright pupil image；The benchmark image is for indicating described tested in default luminous flux The pupil iris image of object；

Ratio calculation unit, for calculating separately the first ratio between the pupil area in the benchmark image and iris area The pupil plane in the second ratio and the bright pupil image between pupil area and iris area in value, the dark pupil image Third ratio between long-pending and iris area；

Abnormal deciding means, for according to first ratio, second ratio, the third ratio and default detection mould Type determines whether the pupil of the measurand is abnormal.

9. a kind of device of pupil detection, including memory, processor and storage are in the memory and can be at the place The computer program run on reason device, which is characterized in that realized when the processor executes the computer program as right is wanted The step of seeking any one of 1 to 7 the method.

10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists In when the computer program is executed by processor the step of any one of such as claim 1 to 7 of realization the method.