CN110393504B

CN110393504B - Intelligent virus identification method and device

Info

Publication number: CN110393504B
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: 2022-02-15
Anticipated expiration: 2038-04-24
Also published as: CN110393504A

Abstract

The invention is suitable for the technical field of computer detection, and provides a pupil detection method and a pupil detection device, wherein the pupil detection method comprises the following steps: acquiring pupil iris images of a tested object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux; respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image; and determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model. The method comprises the steps of obtaining a reference image, a dark pupil image and a bright pupil image of a measured object in environments with different luminous fluxes, determining whether the pupil of the measured object is abnormal or not according to the area ratio by the ratio between the pupil area and the iris area in the images, ensuring the accuracy and universality of pupil detection and improving the precision of the pupil detection.

Description

Intelligent virus identification method and device

Technical Field

The invention belongs to the technical field of computer detection, and particularly relates to an intelligent virus identification method and device.

Background

The eyes are used as important information acquisition organs of the human body, and the pathological changes of a plurality of tissues and organs of the human body are reflected while external light radiation information is acquired. The pupil is dilated or contracted after being stimulated by different lights, but the sympathetic nerve and parasympathetic nerve in the oculomotor nerve control the pupil change. Once these nervous systems are compromised, their ability to control pupillary changes is lost, and it is through pupillary changes that the mechanisms underlying certain diseases can be observed. By observing and measuring the eye, not only ophthalmic diseases can be found, but also some systemic diseases can be diagnosed at an early stage.

In the prior art, the diameter and the size change of the pupil are measured, so that the evaluation of ophthalmic surgery and curative effect or the diagnosis of various diseases is realized. However, the conventional pupil measurement method is easily affected by the external environment and the conditions of the subject, and the measurement accuracy is poor, thereby causing calculation errors or inaccurate judgment.

Disclosure of Invention

In view of this, embodiments of the present invention provide an intelligent virus identification method and apparatus, so as to solve the problems in the prior art that the measurement accuracy is poor, and is easily affected by the external environment and the conditions of the subject to be measured, and the measurement accuracy is poor, which causes a calculation error or a determination misalignment.

The first aspect of the embodiment of the present invention provides an intelligent virus identification method, including:

acquiring pupil iris images of a detected object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux;

respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image;

and determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model.

A second aspect of the embodiments of the present invention provides an intelligent virus identification device, including:

the image acquisition unit is used for acquiring pupil iris images of the measured object under different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux;

a ratio calculation unit, configured to calculate a first ratio between a pupil area and an iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image, and a third ratio between the pupil area and the iris area in the bright pupil image, respectively;

and the abnormality judgment unit is used for determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model.

A third aspect of the embodiments of the present invention provides an intelligent virus identification device, including: the device comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, the memory is used for storing a computer program for supporting an apparatus to execute the method, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect.

A fourth aspect of embodiments of the present invention provides a computer-readable storage medium having stored thereon a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of the first aspect described above.

Compared with the prior art, the embodiment of the invention has the following beneficial effects: acquiring pupil iris images of a tested object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux; respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image; and determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model. The method comprises the steps of obtaining a reference image, a dark pupil image and a bright pupil image of a measured object in environments with different luminous fluxes, determining whether the pupil of the measured object is abnormal or not according to the area ratio by the ratio between the pupil area and the iris area in the images, ensuring the accuracy and universality of pupil detection and improving the precision of the pupil detection.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

FIG. 1 is a flow chart of a method for intelligent virus identification according to an embodiment of the present invention;

FIG. 2 is a schematic view of a human eye and camera provided by an embodiment of the invention;

FIG. 3 is a schematic diagram of the principles of human eye imaging provided by an embodiment of the present invention;

FIG. 4 is a diagram illustrating a camera aperture and a pupil of a human eye according to an embodiment of the present invention;

FIG. 5 is a graph illustrating the light influence on the pupil diameter according to an embodiment of the present invention;

fig. 6 is a flowchart of a method for pupil detection according to another embodiment of the present invention;

fig. 7 is a schematic view of a camera lens of a mobile phone according to an embodiment of the present invention;

fig. 8 is a schematic diagram illustrating a modification of a conventional lens barrel according to an embodiment of the present invention;

fig. 9 is a schematic view of a lens barrel according to an embodiment of the present invention;

fig. 10 is a schematic view of the lens barrel of fig. 9 mounted on a mobile phone according to an embodiment of the present invention;

fig. 11 is a schematic diagram of an image capturing apparatus according to an embodiment of the present invention;

fig. 12 is a schematic diagram illustrating a method of using an image capturing apparatus according to an embodiment of the present invention;

FIG. 13 is a schematic diagram of the pupil variation under different luminous flux conditions according to an embodiment of the present invention;

FIG. 14 is a diagram illustrating an image processing result of a reference image according to an embodiment of the present invention;

FIG. 15 is a pixel bitmap of a pupil image provided by an embodiment of the present invention;

FIG. 16 is a diagram illustrating image ratio calculation according to an embodiment of the present invention;

FIG. 17 is a schematic diagram of an apparatus for intelligent virus identification according to an embodiment of the present invention;

FIG. 18 is a schematic diagram of an apparatus for intelligent virus identification according to another embodiment of the present invention;

fig. 19 is a schematic diagram of an apparatus for intelligent drug identification according to still another embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

In order to explain the technical means of the present invention, the following description will be given by way of specific examples.

Referring to fig. 1, fig. 1 is a flowchart of a method for intelligent virus identification according to an embodiment of the present invention. The main implementation body of the method for pupil detection in this embodiment is a device with a pupil detection function, including but not limited to a computer, a tablet computer, a camera, or a terminal. The method of pupil detection as shown in fig. 1 may comprise the steps of:

s101: acquiring pupil iris images of a detected object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing the pupil iris image of the measured object at the preset luminous flux.

The eye is the most important organ in human sense and consists of the eyeball and the accessory organs of the eye. The eyeball we see consists mainly of the sclera, iris and pupil. The pupil is a small round hole at the center of the iris in the eye, the two sides of the pupil are equal in size and circle, the edge of the pupil is neat, and the pupil is a passage for light rays to enter the eye. The eye can distinguish light rays with different colors and brightness, and convert the information into nerve signals to be transmitted to the brain. The pupil acts as an aperture of the camera, and changes with the intensity of light, shrinks at bright light and diverges at dark light, typically by 2 to 8 mm.

Referring to fig. 2 and 3 together, the human eye is a camera, and in fact the camera is made according to the invention of the human eye structure. In the principle of a camera, a human eye dioptric system consisting of a cornea, an aqueous humor, a crystal and a vitreous body is equivalent to a lens of the camera, and a pupil is an automatic diaphragm of the camera.

Referring to fig. 4, the aperture controls the amount of light entering the lens, and the instantaneous aperture in the camera is constructed to completely mimic the pupil structure, so that when the light is strong, in order to protect the fundus from being burned, a person can automatically reduce the pupil to reduce the amount of light entering the eye to protect the fundus, which is the light control mechanism of the pupil.

Since the control mechanism of light on the pupil is an objective rule followed by human eyes, it is very reliable to detect the change rate of the pupil under different illumination conditions and diagnose the disease accordingly. Clinically, in addition to performing ophthalmic surgery, other diagnoses based on measuring pupil diameter can be replaced by simpler and more practical methods based on detecting changes in pupil proportion. The reaction of the pupil to light is controlled by the brain stem, and the dynamic change of the pupil can reflect the high-grade nerve activity and the physiological state thereof, and can cause damage to the brain stem when a person is poisoned or takes certain drugs. Therefore, the method for detecting whether the drug is taken or not (drug absorption) through the dynamic change of the pupil is as effective as the traditional urine test, blood test and saliva test.

In this embodiment, the pupil detection device acquires the reference image, the dark pupil image, and the bright pupil image under different lighting conditions. Wherein, the reference image is the pupil iris image of the tested object under the preset luminous flux, and is generally obtained under the indoor or outdoor direct shading condition; dark pupil images need to be acquired in environments with low luminous flux, such as at night or in dark room environments; the bright pupil image needs to be acquired in an environment where the luminous flux is high, for example, in an environment where the lamp light or sunlight is strong.

Since the ordinary video probe or the mobile phone cannot capture images under the condition of insufficient light, in the embodiment, a dark pupil image and a bright pupil image are respectively captured after light stimulation is given in a dark vision environment.

Fig. 5 is a dynamic diagram showing the change of the pupil diameter with time after light stimulation is given in the dark environment, wherein the pupil undergoes reflective contraction. Where x is the time axis and the y-axis is the pupil diameter. As can be seen, the diameter of the dark pupil is about 5.7mm before the time of the excitation of the stimulus light a, and the pupil is still in a dark pupil state during the period from the time of the excitation of the stimulus light a to the time of the excitation of the stimulus light B, i.e., during a → B, and this period is a latency period (typically, the latency period is about 0.2 seconds); the contraction phase occurs during the period from the generation of the stimulus beam B to the generation of the stimulus beam C, i.e., the period B → C, and the pupil diameter is contracted to a minimum of less than 3.5mm at the point C (usually, about 1 second after the light stimulus); over time, the pupil gradually reverts to the dark pupil state. It can be seen that the dark pupil image and the bright pupil image of the pupil to be photographed can be obtained only by photographing at the points a → B and C in the figure, or the maximum and minimum diameters of the pupil can be found from the video image of the whole period a → C.

It should be noted that, unlike the conventional pupil image capturing, the present invention does not have an accurate distance requirement when capturing the pupil image, and only needs to achieve clear capturing.

S102: and respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image.

After acquiring the pupil iris image of the measured object, identifying the pupil and the iris in the pupil iris image, and respectively calculating the pupil area and the iris area in the reference image, the dark pupil image and the bright pupil image. A first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image, and a third ratio between the pupil area and the iris area in the bright pupil image are then calculated.

By calculating the ratio between the pupil area and the iris area in each image, the relative size of the pupil in the different images can be determined. The problem that when pupil abnormity is judged by directly measuring the pupil diameter, the judgment result is inaccurate due to the influence of factors such as gender, age or race and the like is solved.

S103: and determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model.

After the first ratio, the second ratio and the third ratio are calculated, whether the pupil of the tested object is abnormal or not is determined according to the first ratio, the second ratio, the third ratio and a preset detection model.

Optionally, whether the pupil of the measured object is abnormal may be determined by a preset ratio threshold. The data samples are classified in advance to obtain ratio intervals between the pupil area and the iris area when the pupil is abnormal due to different causing factors, and the ratio interval in which the ratio between the pupil area and the iris area of the pupil iris image obtained currently is determined according to the ratio intervals, so that whether the pupil is abnormal or not is determined, and whether the measured object corresponding to the pupil iris image is normal or not can be determined.

It should be noted that the reasons for the pupil abnormality in the present embodiment may include: the subject is suffering from encephalopathy, central nervous system infectious diseases, cerebrovascular diseases, cerebral anoxia, brain tumor, craniocerebral trauma, drug poisoning, pain, fear, hyperthyroidism, congenital abnormality, drug absorption and the like, and the method is not limited herein.

According to the scheme, the pupil iris image of the tested object is acquired in the environment with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux; respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image; and determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model. The method comprises the steps of obtaining a reference image, a dark pupil image and a bright pupil image of a measured object in environments with different luminous fluxes, determining whether the pupil of the measured object is abnormal or not according to the area ratio by the ratio between the pupil area and the iris area in the images, ensuring the accuracy and universality of pupil detection and improving the precision of the pupil detection.

Referring to fig. 6, fig. 6 is a flowchart of a method for intelligent virus identification according to another embodiment of the present invention. The main implementation body of the method for pupil detection in this embodiment is a device with a pupil detection function, including but not limited to a computer, a tablet computer, a camera, or a terminal. The method of pupil detection as shown in fig. 6 may comprise the steps of:

s601: and acquiring the identity information of the measured object.

The pupil abnormality detection device can be used for detecting the gathering places of people such as frontiers, airports, stations and the like, and strict security guards are required, so that the iris pupil image of the detected object is determined to be in accordance with the identity information of the iris pupil image by acquiring the identity information of the detected object. Meanwhile, because the pupil characteristics of the human are influenced by factors such as sex, age or race, the normal pupil characteristic range of the tested object can be determined by acquiring the identity information of the human, so as to reasonably detect and judge whether the pupil is abnormal.

In the embodiment of the invention, the device for pupil detection is provided with preset client software, and the client software is used for controlling the mobile phone to execute the steps in each embodiment of the invention. Based on the client software, the pupil detection device is in communication connection with the server. According to the identity information input instruction sent by the user in the client software, the identity information of the object to be tested can be acquired.

Optionally, the device for acquiring the identity information of the object to be detected may be a mobile terminal, preferably, the mobile terminal is configured with a rear camera with more than 800 ten thousand pixels, is equipped with a flash lamp and a fingerprint acquisition device, and may be equipped with special detection software for acquiring the identity information of the object to be detected, automatically generating a detection table, acquiring a biological identity, and discriminating pupil data information. The terminal detection equipment is suitable for remote areas and field operation.

Optionally, the device for acquiring the identity information of the measured object may be a computer, and preferably, an identity card reader and a video probe are installed on the computer. The computer is also provided with detection software as the mobile terminal, and is responsible for login management of an operator, automatic generation of a detection form, license identity acquisition of a detected person, biological identity acquisition and pupil data information acquisition and judgment. The identity card reader on the computer is responsible for the discrimination of the identity of the detected person, and the video probe is responsible for the acquisition of the information of the iris and the pupil of the detected person. The terminal is suitable for detection of people gathering places such as borders, airports, stations and the like.

It should be noted that the identity information of the measured object in this embodiment includes, but is not limited to, a name, a certificate number, or a certificate image recorded with identity information.

S602: uploading the identity information to a server, and acquiring identity verification information sent by the server after the identity information is verified; the identity verification information is used for indicating whether the identity information of the tested object is legal or not.

After acquiring the identity information of the tested object, uploading the identity information to a server, and acquiring identity verification information which indicates whether the identity information of the tested object sent by the server after verifying the identity information is legal or not;

optionally, the pupil detection device controls the camera to shoot the certificate whose direction is toward the measured object, so as to shoot the certificate, and upload the certificate image containing the identity information to the server, so that the server verifies the identity information of the certificate. The documents include but are not limited to identification cards, passports, drivers licenses and other documents with unique identification marks.

Optionally, the pupil detection device obtains the text format of the identity information of the object to be tested, and then directly uploads the identity information of the object to be tested to the server. For example, the identity card number of the object to be tested is uploaded to the server, so as to verify the identity of the object to be tested corresponding to the identity card number.

After the identity information is uploaded to the server, the identity verification information of the tested object returned by the server is received, and the identity verification information is used for determining whether illegal behaviors exist in a person corresponding to the identity information.

S603: and if the identity information of the measured object is legal, acquiring pupil iris images of the measured object at different luminous fluxes respectively.

If the received authentication information returned by the server is legal, the authentication of the user to be detected is confirmed to be correct, at the moment, the identity information of the user to be detected is recorded in a pre-generated table, and a pupil image acquisition event is triggered; and if the received authentication information returned by the server is illegal, confirming that the authentication of the user to be detected fails, and triggering an identity exception handling event.

It should be noted that the reference image in this embodiment may be a pupil image acquired in a general reading illumination environment; the bright pupil image and the dark pupil image refer to pupil images respectively acquired under the environments of strong light and dark light.

Exemplarily, a mobile phone is taken as a pupil detection device, since a mobile phone camera has a few pixels different from a professional camera at an entry level except for a difference in optical characteristics of a lens, and an image processing function is even better than that of the professional camera, the embodiment utilizes the photographing and software processing capabilities of the mobile phone to realize image capturing, processing and judging of pupils.

Referring to fig. 7, 8, 9 and 10, a barrel as shown in fig. 7 is disposed between the camera lens of the mobile phone and the eyeball to be photographed, and the shape of the barrel is similar to that of the eyepiece of a telescope or a microscope. The lens is not arranged in the lens barrel, and the lens barrel does not play any optical amplification role. Firstly, the distance between the pupil to be shot and the camera lens is relatively fixed and is not too close to ensure the definition of the image; and secondly, the lens cone is covered by the lens cone, so that the artificial light source is applied more uniformly, and the possibility of measured pupil dissociation is isolated. The lens barrel of the mobile phone is a passive component, and does not need to be electrically connected with the mobile phone. When in use, the mobile phone lens is fixed in front of the mobile phone lens. Fig. 8 is one of the ways that the lens barrel of fig. 7 is modified and can be fixed on a mobile phone. The lens barrel can also be arranged in a form of fig. 9, wherein the lens barrel is composed of a lining, a window and an outer sleeve, when a common pupil image is obtained, the form can reduce the energy consumption of the mobile phone by an external light source, and fig. 10 is a schematic view of the lens barrel arranged on the mobile phone in fig. 9.

At airports, stations and border ports, identity verification and security facilities are common that are provided with access ways. The identity checking work is implemented by an identity card reader, which can judge whether a holder and a certificate are the same person or not and can know whether the holder is a pursuit person or not; the security inspection device can only detect metal parts at present, and can not effectively detect drugs, explosives and the like. Drug addicts are obviously in the category of forbidden access, but the current approaches are not applicable to such scenarios. Obviously, it is not possible to have all personnel entering the security and verification corridor perform blood or urine tests.

Referring to fig. 11, an image capturing apparatus composed of a general camera lens and an illumination device may be installed above the authentication window of the id verification channel, and only the verifier looks at the camera lens while verifying the id card, as shown in fig. 12. Because the eye socket does not need to be contacted with the camera component, the detected person has no psychological burden and does not cause disease infection. Because there is no lens cone or eyeshade fixing device, for different verifiers, the pupil image can be captured at different distances, or obtained in a dynamic state, due to different heights and standing postures. Referring to fig. 12, the pupils and lens distances of the detected people A, B and C are different. Under the control of verification and detection software, the camera is controlled to shoot pupil images of the verified person, and further analysis and judgment are carried out to judge whether the verified person belongs to a drug absorber.

It is known that when the illuminance is lower than a certain value, the common photosensitive device of the camera cannot acquire image information, so that the special night vision system adopts infrared light to provide illumination, and takes images at night by using an original capable of reading infrared signals as the photosensitive device. While the ordinary camera lens cannot acquire images in a non-light environment, for this reason, it is designed to apply stimulus light in a low or non-light environment, and control to capture a dark pupil image between the pupil latencies A, B of fig. 5 and capture a bright pupil image at point C of fig. 5. Experiments have shown that the latency period A-B is about 0.2 seconds and the C-point is about 1 second after light stimulation.

In the modes shown in fig. 11 and 12, it is easy to create dark light, strong light and normal lighting environment respectively, if the mobile phone lens barrel mode of fig. 8 is adopted, lighting environments for capturing dark pupil, bright pupil and normal pupil need to be simulated by mobile phone detection control software respectively; if the mobile phone lens barrel method of fig. 10 is adopted, it is necessary to simulate the illumination environment captured by the bright pupil and the dark pupil.

No matter the mobile phone camera flash or the video camera auxiliary lighting is controlled to be turned on or turned off by the electronic switch, when the switch is turned on, the brightness of the switch is consistent, and when the switch is turned off, the switch does not emit light. Therefore, the illumination switch can be enabled to send out pulse turn-on signals with different duty ratios to control illumination brightness.

Referring to fig. 13, fig. 13 shows the pupil state change under the environment of controlling different luminous fluxes. In the figure, T is the period of the illumination control pulse signal, where T1 is the duration of the pulse being high; t2 is the duration of the pulse low potential. If the signal T1 is completely occupied in the time T, the switch signal is constant high at the moment, which is equivalent to the switch is opened; if the signal T2 is fully occupied in the time T, the switch signal is constant low at this time, which corresponds to the switch being turned off. When t1 is t2, namely the duty ratio of the signal is 1:1, the lighting power is half of the constant high time of the control switch signal; when t1 is more than t2, the luminous flux becomes strong and the luminous intensity is higher, namely brighter; when t2 > t1, the luminous flux tends to be weak, and the luminous intensity is lower, i.e., darker. Therefore, by setting a plurality of Application Programming Interfaces (APIs) with different duty ratios and a delay length of t, each API represents different luminous fluxes, and corresponding pupil images are captured under different luminous flux environments.

Referring to fig. 14, fig. 14 shows that the human face reference image obtained by a general camera or a mobile phone is processed by conventional computer image processing processes such as brightness, contrast, exposure, hue saturation, hue separation, and threshold, and finally an image convenient for recognition is generated.

S604: and respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image.

Clinically, the pupil diameter of 3-4mm is judged as normal pupil, if the pupil diameter is less than 2mm, the pupil is contracted, and if the pupil diameter is more than 5mm, the pupil is dilated. In the pupil diameter determination method, when the ratio of the bright pupil diameter (small pupil) of the pupil to the normal pupil diameter is less than 2/4, the pupil is narrowed; mydriasis is expressed as the ratio of dark pupil diameter (large pupil) to normal pupil diameter > 5/3:

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

Narrowing the diameter of the pupil: ratio BP of bright pupil diameter to normal pupil diameter_D/NP_D<2/4；

Dilated pupil diameter: ratio of dark pupil diameter to normal pupil diameter DP_D/NP_D＞5/3；

Wherein the meanings of the letter abbreviations are respectively as follows: BP (Back propagation) of_DFor bright pupil diameter, DP_DFor dark pupil diameter; NP_DFor normal pupil diameter.

Since the embodiment can perform the discrimination under the condition of acquiring the dynamic pupil image, only the data of the pupil is not enough to realize the accurate discrimination under some special conditions (such as the pupils which lose the response to the light stimulus due to pathological or physiological reasons), a new data is introduced: ratio of pupil area to iris area. Pupil images obtained after photographing under different illumination environments are processed to obtain a pixel bitmap as shown in fig. 15. On the basis of the pixel map, the areas of different pupils can be easily calculated, and then the relationship among the different pupils is analyzed and judged. Clinically, the pupil is detected or measured by taking the diameter as a standard, and in the invention, a standard sample disc is not available, and the diameter cannot be calculated due to the fact that the pupil distance is not constant. However, since the characteristic of the pupil is circular, a method using the diameter as the pupil determination criterion can be expressed by determining the pupil area. According to the pupil area and the iris area in the pupil iris image acquired under the environment with different luminous fluxes, the ratios between the pupil area and the iris area in the reference image, the dark pupil image and the bright pupil image are respectively calculated, and the ratios are respectively used as a first ratio, a second ratio and a third ratio.

S605: and if the second ratio is larger than the first ratio or the third ratio is smaller than the first ratio, judging that the pupil of the measured object is abnormal.

Referring also to fig. 16, when the pupil loses its response to the light stimulus, it may be in a dilated state or in a miotic state. E.g. BP only_D/NP_DOr DP_D/NP_DThe parameter cannot know which state the pupil is in all the time, and further influences the judgment of the pupil. The relative relation between the iris and the iris can determine the state of the iris. In the present invention, since there is no pupil diameter data, the pupil state is determined by calculating the pupil area, and the area can be expressed again as:

reference image area: 2.78>NP_A＞1/4；

Pupil area reduction: ratio BP of bright pupil area to pupil area in reference image_A/NP_A<1/4；

Divergent large pupil area: ratio DP of dark pupil area to pupil area in the reference image_A/NP_A＞2.78；

Non-reference image value: ratio P of pupil area to iris area_A/I_A；

Wherein the meanings of the letter abbreviations are respectively as follows: BP (Back propagation) of_AFor expressing the bright pupil area, DP_AFor representing the dark pupil area; NP_AFor representing the pupil area in the reference image.

The above equation indicates that, in the present invention, the reference image is obtained when the ratio of the "dark pupil area to the pupil area in the reference image" is smaller than 2.78 and larger than the ratio 1/4 of the "bright pupil area to the pupil area in the reference image". If the ratio of the "bright-pupil area to the pupil area in the reference image" is less than 1/4, it is determined that the pupil is narrowed. If the ratio of the "dark pupil area to the pupil area in the reference image" is larger than>2.78, it is judged as dilated pupil. When P is present_A/I_A>>"ratio of dark pupil area to pupil area in reference image" or P_A/I_A<<When the "ratio of the bright pupil area to the pupil area in the reference image" is used, the pupil is in an abnormal state at this time. The former pupil loses its response to light stimuli, the pupil is always dilated, the latter is always contracted, and they may be caused by blindness or other abnormal reasons.

Further, step S605 may further specifically include:

determining a judgment parameter suitable for the identity of the object to be detected from a preset detection model according to the identity information of the object to be detected;

and determining whether the pupil of the tested object is abnormal or not according to the first ratio, the second ratio, the third ratio, the detection model and a judgment parameter.

The change in pupil size, in addition to being controlled by light, is related to the distance, age, sex, race, mental state, and refractive state of the fixation target. Therefore, when pupil detection is performed, the detected person is required to be in a relatively flat and quiet environment with fixed illumination intensity and is detected under the condition of a uniform fixation point. Due to the difference of the race, gender and development degree of the optic nervous system, different people have different sensitivity degrees to light, which causes the difference of the congenital pupil size among the people. If the reference image diameter of a certain person is 3mm, it is possible that the pupil diameter of 3mm is a constricted pupil for another family of people, so it is difficult and complicated to diagnose a disease by judging the size of the pupil. Since the diameter of the pupil must be measured at a known age, gender and race, a relatively accurate determination can be made.

The pupil diameter of the reference image is a statistically derived average value, and when the reference image is used for judging drug (drug absorption) pupils, the reference image is only suitable for a certain group, such as Chinese, male, young and old people. If the detection range is enlarged, a large error may be caused. As described above, since the diameter of the pupil of a person is related to the race, age, and sex, and a diameter error occurs depending on the intake distance, there are many variables in the conventional diameter measurement and determination method. The area measurement discrimination method avoids uncertain factors such as age, ingestion distance and the like, and effectively ensures the accuracy of measurement.

In the embodiment of the invention, the pupil diameter of the user is related to the age and the sex of the user, and errors are generated on the detected pupil diameter when the shooting distance is different, so that the pupil diameter of the detected object can be quickly detected whether to be abnormal or not by comparing the pixel bit ratio of the pupil image with the preset threshold value, and the pupil diameter is not required to be measured in the process, so that the influence of various factors such as the age and the shooting distance of the detected object is avoided, and the accuracy of the detection result is effectively ensured.

S606: and if the pupil of the measured object is abnormal, determining the current cause of the pupil of the measured object according to the first ratio, the second ratio, the third ratio and the detection model.

After judging whether the pupil of the tested object is abnormal or not, if the pupil of the tested object is abnormal, determining the current cause of the pupil of the tested object according to the first ratio, the second ratio, the third ratio and the detection model.

Further, step S606 may further specifically include S6061 to S6063:

s6061: and if the pupil of the measured object is abnormal, determining a first pupil characteristic corresponding to the first ratio, a second pupil characteristic corresponding to the second ratio and a third pupil characteristic corresponding to the third ratio according to the pupil characteristics corresponding to each numerical value interval in the detection model.

In the conventional determination method, the determination of the abnormal pupil is made based on limited data samples, and it is needless to say that the larger the number of samples is, the more accurate the determination is. One problem that arises, however, is how the boundaries of the sample selection should be determined. Too few samples result in reduced accuracy, and a sufficiently large number of samples consumes a lot of system resources such as time. In order to effectively solve the defects of the conventional method, the basic techniques of artificial intelligent control are adopted in the embodiment, and the basic techniques comprise methods such as a fuzzy control technique, an expert control technique and a learning control technique. And establishing a mathematical model capable of self-learning according to the past limited detection results and clinical and theoretical data.

As shown in table 1, m abnormal pupil phenomena are selected from the conventional abnormal pupil data to form an abnormal pupil set P ═ P1, P2, P3, …, and Pm }. Each pupil anomaly phenomenon is composed of different bright pupils, the ratio of the pupil area in the dark pupil to the pupil area in the reference image, and the ratio of the pupil to the iris. As in the example of table 1, m is 8, which is only one example in this embodiment, and the sizes of the elements and m values in the abnormal pupil set may be increased or decreased according to specific situations, which is not limited herein.

Table 1 test table 1

In table 1, P/IRIS (ratio of pupil to IRIS), BP/NP (ratio of pupil area in bright pupil image to pupil area in reference image) and DP/NP (ratio of pupil area in dark pupil image to pupil area in reference image) are given in advance as numerical ranges given by clinical test results and expert's findings. If the values of the elements in a given set P are:

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＝0.95-1 z₈＝0.95-1

wherein, P/IRIS is divided into (P/IRIS) min and (P/IRIS) max, the former is used for expressing the ratio of the pupil area and the IRIS area of PA/IA < < reference image; the latter is used to represent PA/IA > ratio of pupil area to iris area of the reference image. The parameters x, y, z in the table are instantaneous test results.

It should be noted that table 1 can be divided into several parts according to age group, sex, race, etc., and parameters of each part are different, and after data information of the detected person is obtained, a corresponding detection table is called to implement the judgment.

Table 1 is transformed into the schema of Table 2, where the parameter element y in Table 2 replaces BP/NP by BP/IRIS (ratio of bright pupil area to IRIS area) and element x replaces DP/NP by DP/IRIS (ratio of dark pupil area to IRIS area). Of course, the values of the elements x and y are also adjusted accordingly.

Table 2 test table 2

Illustratively, the result of calculating the parameters of the measured object at a time is:

x＝0.4；y＝0.2；z＝2.5

in comparison with table 2, the detected data values of the parameters x, y and z fall into P2, P3 and P4, where P is the cause of the abnormality, which may be P2, P3 or P4.

S6062: and determining different cause coefficients corresponding to the first pupil characteristic, the second pupil characteristic and the third pupil characteristic respectively according to different cause coefficients corresponding to the pupil characteristics in the detection model.

Firstly, a cause set is constructed, then n causes are selected (see table 1), and a limited cause set C ═ C is formed₁,C₂,C₃,…,C_nWherein the cause of the discrepancy may include the following:

C₁: atopy of atopy

C₂: cocaine poisoning

C₃: central depressant intoxication

C₄: alcoholism

C₅: blindness

…：

C_n: eye diseases

Similarly, the elements of the pupil cause set C can be added or deleted. The coefficients α, β, γ, …, η are the number of times of detection and are originally obtained and written according to expert opinions or previous sample detection results.

Illustratively, the data of the detection result of a certain time is as follows:

x＝0.4y＝0.2z＝2.5

as seen from comparison with table 2, the detected data values of the parameters x, y and z fall into P2, P3 and P4, respectively, and the causal coefficients of P2, P3 and P4 are:

α2＝2β2＝36γ2＝7…η2＝0

α3＝19β3＝2γ3＝9…η3＝0

α4＝4β4＝12γ4＝8…η4＝1

by determining the factor of the cause of the abnormality, the weights of various causes of the abnormality of the object to be measured can be determined, and the final cause of the abnormality can be determined according to the factor of the cause of the abnormality.

S6063: and determining the current cause of the pupil of the tested object according to all the cause coefficients.

After the cause-of-variation coefficients are determined, the result corresponding to the coefficient with the largest number of identification times is selected from various causes, the coefficients P2 and P3 are compared with the coefficients P4, the number of times that the cocaine poisoning corresponding to the beta 2 is identified is 36, and the cause with the largest number of identification times is as follows:

α2＝2β2＝36γ2＝7…η2＝0

α3＝19β3＝2γ3＝9…η3＝0

α4＝4β4＝12γ4＝8…η4＝1

that is, in the relationship matrix, β 2 has the highest membership coefficient, so C2 is selected as the result of this test, i.e., "cocaine poisoning". The method has the advantages that the comparison with a large amount of data is not needed every time, especially when the detection sample is mass data, a large amount of time consumption can be saved, and real-time detection and judgment can be realized.

S607: and updating the factor of the current cause of the exception according to the current cause of the exception.

After the current cause of the exception is determined, the value of the cause of the exception coefficient corresponding to the current cause of the exception is counted according to the current cause of the exception.

Once the detection result is confirmed, 1 is added to the corresponding coefficient in the cause of the variation, so that a reliable basis is added for the judgment of the detection result in the future, and the time consumption caused by data comparison of a large sample is avoided. This is the same as the human learning process.

Illustratively, after the test result is confirmed, β 2 in the table is added with "1" to obtain 37.

α2＝2β2＝37γ2＝7…η2＝0

α3＝19β3＝2γ3＝9…η3＝0

α4＝4β4＝12γ4＝8…η4＝1

The method and the device have the advantages that the foreign reason coefficient of the foreign reason is determined according to the determined number of the foreign reasons, the probability of each foreign reason can be determined, reference is further made for accurately judging the foreign reason, and the accuracy of judging the foreign reason is guaranteed.

According to the scheme, the identity information of the measured object is collected; uploading the identity information to a server, and acquiring identity verification information sent by the server after the identity information is verified; if the identity information of the measured object is legal, acquiring pupil iris images of the measured object at different luminous fluxes respectively; respectively calculating a first ratio between the pupil area and the iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image and a third ratio between the pupil area and the iris area in the bright pupil image; if the second ratio is larger than the first ratio or the third ratio is smaller than the first ratio, determining that the pupil of the measured object is abnormal; if the pupil of the tested object is abnormal, determining the current cause of the pupil of the tested object according to the first ratio, the second ratio, the third ratio and the detection model; and updating the factor of the current cause of the exception according to the current cause of the exception. The method comprises the steps of determining a judgment parameter suitable for the measured object by acquiring the identity information of the measured object, judging whether the pupil of the measured object is abnormal or not according to the pupil area and the iris area, ensuring the individuation and universality of an abnormal judgment standard, determining the cause of abnormality through the cause of abnormality coefficient, updating the cause of abnormality coefficient corresponding to the finally determined cause of abnormality, and improving the accuracy of abnormal judgment.

Referring to fig. 17, fig. 17 is a schematic view of an intelligent virus identification apparatus according to an embodiment of the present invention. The pupil detection device includes, but is not limited to, a computer, a tablet computer, a camera or a terminal. The apparatus of the present embodiment includes units for performing the steps in the embodiment corresponding to fig. 1, and please refer to fig. 1 and the related description in the embodiment corresponding to fig. 1 for details, which are not repeated herein. The pupil detection apparatus of the present embodiment includes an image acquisition unit 1701, a ratio calculation unit 1702, and an abnormality determination unit 1703.

An image acquisition unit 1701 for acquiring pupil iris images of the object to be measured at different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux;

a ratio calculation unit 1702, configured to calculate a first ratio between a pupil area and an iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image, and a third ratio between the pupil area and the iris area in the bright pupil image, respectively;

an abnormality determining unit 1703, configured to determine whether the pupil of the measured object is abnormal according to the first ratio, the second ratio, the third ratio, and a preset detection model.

Referring to fig. 18, fig. 18 is a schematic view of another intelligent virus identification device provided in the embodiment of the present invention. The pupil detection device includes, but is not limited to, a computer, a tablet computer, a camera or a terminal. The pupil detection apparatus of this embodiment includes units for performing the steps in the embodiment corresponding to fig. 6, and please refer to fig. 6 and the related description in the embodiment corresponding to fig. 6 for details, which are not repeated herein. The pupil detection device of the embodiment includes: identity information acquisition 1801, information upload unit 1802, image acquisition unit 1803, ratio calculation unit 1804, abnormality judgment unit 1805, cause determination unit 1806, and coefficient update unit 1807.

An identity information acquisition 1801 for acquiring identity information of the object to be tested;

an information uploading unit 1802, configured to upload the identity information to a server, and acquire authentication information sent by the server after the identity information is authenticated; the identity verification information is used for indicating whether the identity information of the tested object is legal or not;

an image obtaining unit 1803, configured to obtain pupil iris images of the measured object at different luminous fluxes, if the identity information of the measured object is legal; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux;

a ratio calculation unit 1804, configured to calculate a first ratio between a pupil area and an iris area in the reference image, a second ratio between the pupil area and the iris area in the dark pupil image, and a third ratio between the pupil area and the iris area in the bright pupil image, respectively;

an abnormality determining unit 1805 is configured to determine that the pupil of the measured object is abnormal if the second ratio is greater than the first ratio, or the third ratio is smaller than the first ratio.

A cause determining unit 1806, configured to determine, if the pupil of the measured object is abnormal, a current cause of the pupil of the measured object according to the first ratio, the second ratio, the third ratio, and the detection model;

a coefficient updating unit 1807, configured to update, according to the current cause of exception, a cause of exception coefficient corresponding to the current cause of exception.

Further, the abnormality determining unit 1805 may further include:

the parameter determining unit is used for determining a judgment parameter suitable for the identity of the tested object from a preset detection model according to the identity information of the tested object;

and the judging unit is used for determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio, the detection model and a judging parameter.

Further, the reason determining unit 1806 may further specifically include:

a feature determination unit, configured to determine, if a pupil of the measured object is abnormal, a first pupil feature corresponding to the first ratio, a second pupil feature corresponding to the second ratio, and a third pupil feature corresponding to the third ratio according to pupil features corresponding to each numerical value interval in the detection model;

a coefficient determining unit, configured to determine, according to a cause coefficient corresponding to each pupil feature in the detection model, a cause coefficient corresponding to each of the first pupil feature, the second pupil feature, and the third pupil feature;

and the reason judging unit is used for determining the current cause of the pupil of the measured object according to all the cause coefficients.

Further, the coefficient updating unit 1807 may further specifically include:

and the counting unit is used for counting the value of the factor of the current cause according to the current cause of the abnormality.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

Referring to fig. 19, fig. 19 is a schematic diagram of an intelligent virus identification device according to still another embodiment of the present invention. The apparatus for pupil detection in the present embodiment as shown in fig. 19 may include: a processor 1901, a memory 1902, and a computer program 1903 stored in the memory 1902 and executable on the processor 1901. The steps in the various method embodiments for pupil detection described above are implemented when the processor 1901 executes the computer program 1903. The memory 1902 is used to store computer programs, including program instructions. The processor 1901 is used to execute program instructions stored in the memory 1902. Wherein the processor 1901 is configured to call the program instruction to perform the following operations:

the processor 1901 is configured to acquire pupil and iris images of a measured object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux;

The processor 1901 is specifically configured to determine that the pupil of the measured object is abnormal if the second ratio is greater than the first ratio, or the third ratio is smaller than the first ratio.

If the pupil of the tested object is abnormal, determining the current cause of the pupil of the tested object according to the first ratio, the second ratio, the third ratio and the detection model;

and updating the factor of the current cause of the exception according to the current cause of the exception.

The processor 1901 is specifically configured to determine, if the pupil of the measured object is abnormal, a first pupil feature corresponding to the first ratio, a second pupil feature corresponding to the second ratio, and a third pupil feature corresponding to the third ratio according to the pupil features corresponding to the numerical intervals in the detection model;

determining different cause coefficients corresponding to the first pupil characteristic, the second pupil characteristic and the third pupil characteristic respectively according to different cause coefficients corresponding to the pupil characteristics in the detection model;

and determining the current cause of the pupil of the tested object according to all the cause coefficients.

The processor 1901 is specifically configured to count a value of the cause-of-variation coefficient corresponding to the current cause-of-variation according to the current cause-of-variation.

The processor 1901 is specifically configured to acquire identity information of the measured object;

uploading the identity information to a server, and acquiring identity verification information sent by the server after the identity information is verified; the identity verification information is used for indicating whether the identity information of the tested object is legal or not;

and if the identity information of the measured object is legal, acquiring pupil iris images of the measured object at different luminous fluxes respectively.

The processor 1901 is specifically configured to determine a judgment parameter suitable for the identity of the object to be tested from a preset detection model according to the identity information of the object to be tested;

It should be understood that, in the embodiment of the present invention, the Processor 1901 may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 1902 may include both read-only memory and random access memory, and provides instructions and data to the processor 1901. A portion of the memory 1902 may also include non-volatile random access memory. For example, memory 1902 may also store information for device types.

In a specific implementation, the processor 1901, the memory 1902, and the computer program 1903 described in this embodiment of the present invention may execute the implementation manners described in the first embodiment and the second embodiment of the pupil detection apparatus provided in this embodiment of the present invention, and may also execute the implementation manners of the terminal described in this embodiment of the present invention, which is not described herein again.

In another embodiment of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program comprising program instructions that when executed by a processor implement:

Further, the computer program when executed by the processor further implements:

and if the second ratio is larger than the first ratio or the third ratio is smaller than the first ratio, judging that the pupil of the measured object is abnormal.

if the pupil of the measured object is abnormal, determining a first pupil characteristic corresponding to the first ratio, a second pupil characteristic corresponding to the second ratio and a third pupil characteristic corresponding to the third ratio according to the pupil characteristics corresponding to each numerical value interval in the detection model;

and counting the value of the factor of the current cause of the abnormality according to the current cause of the abnormality.

collecting identity information of the measured object;

The computer readable storage medium may be an internal storage unit of the terminal according to any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.

Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for intelligent virus identification, which is characterized by comprising the following steps:

acquiring pupil iris images of a detected object in environments with different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux; wherein, the reference image is a pupil iris image of the measured object when the luminous flux is preset;

determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model;

if the pupil of the measured object is abnormal, determining the current cause of the pupil of the measured object according to the first ratio, the second ratio, the third ratio and the detection model, including: if the pupil of the measured object is abnormal, determining a first pupil characteristic corresponding to the first ratio, a second pupil characteristic corresponding to the second ratio and a third pupil characteristic corresponding to the third ratio according to the pupil characteristics corresponding to each numerical value interval in the detection model; determining different cause coefficients corresponding to the first pupil characteristic, the second pupil characteristic and the third pupil characteristic respectively according to different cause coefficients corresponding to the pupil characteristics in the detection model; taking the cause corresponding to the largest cause coefficient in all the cause coefficients as the current cause of the pupil of the measured object; the detection model comprises an abnormal pupil set formed by m abnormal pupil phenomena and an abnormal reason set formed by n abnormal reasons, each abnormal pupil phenomenon is formed by a numerical value interval of a ratio between a pupil area and an iris area in a reference image, a numerical value interval of a ratio between a pupil area and an iris area in a bright pupil image and a numerical value interval of a ratio between a pupil area and an iris area in a dark pupil image, each abnormal pupil phenomenon corresponds to multiple abnormal reasons, the n abnormal reasons correspond to different abnormal reason coefficients respectively, the abnormal reason coefficients are the times of corresponding to the abnormal reasons after detection and identification, and the pupil characteristics are the abnormal pupil phenomena;

2. The intelligent drug identifying method of claim 1, wherein the determining whether the pupil of the measured object is abnormal according to the first ratio, the second ratio, the third ratio and a preset detection model comprises:

3. The intelligent virus identification method according to claim 1, wherein the updating the cause-of-variation coefficient corresponding to the current cause-of-variation according to the current cause-of-variation comprises:

4. The method for intelligent drug identification according to claim 1, wherein the acquiring pupil iris images of the tested object at different luminous fluxes comprises:

collecting identity information of the measured object;

5. The intelligent drug identifying method of claim 4, wherein the determining whether the pupil of the tested object is abnormal according to the first ratio, the second ratio, the third ratio and a preset detection model comprises:

6. An intelligent drug identification device, comprising:

the image acquisition unit is used for acquiring pupil iris images of the measured object under different luminous fluxes; the pupil iris image comprises a reference image, a dark pupil image and a bright pupil image; the reference image is used for representing a pupil iris image of the measured object at a preset luminous flux; wherein, the reference image is a pupil iris image of the measured object when the luminous flux is preset;

the abnormality judgment unit is used for determining whether the pupil of the measured object is abnormal or not according to the first ratio, the second ratio, the third ratio and a preset detection model;

a cause determining unit, configured to determine, if the pupil of the measured object is abnormal, a current cause of the pupil of the measured object according to the first ratio, the second ratio, the third ratio, and the detection model;

a coefficient updating unit, configured to update, according to the current cause of exception, a cause of exception coefficient corresponding to the current cause of exception;

the reason determining unit specifically includes: a feature determination unit, configured to determine, if a pupil of the measured object is abnormal, a first pupil feature corresponding to the first ratio, a second pupil feature corresponding to the second ratio, and a third pupil feature corresponding to the third ratio according to pupil features corresponding to each numerical value interval in the detection model; a coefficient determining unit, configured to determine, according to a cause coefficient corresponding to each pupil feature in the detection model, a cause coefficient corresponding to each of the first pupil feature, the second pupil feature, and the third pupil feature; a cause judging unit, configured to use a cause corresponding to a largest cause coefficient of variation among all the cause coefficients as a current cause of variation of the pupil of the measured object; the detection model comprises an abnormal pupil set formed by m abnormal pupil phenomena and an abnormal reason set formed by n abnormal reasons, each abnormal pupil phenomenon comprises a numerical value interval of a ratio between a pupil area and an iris area in a reference image, a numerical value interval of a ratio between a pupil area and an iris area in a bright pupil image and a numerical value interval of a ratio between a pupil area and an iris area in a dark pupil image, each abnormal pupil phenomenon corresponds to multiple abnormal reasons, the n abnormal reasons correspond to different abnormal reason coefficients respectively, the abnormal reason coefficients are the times of corresponding to the abnormal reasons determined by detection, and the pupil characteristics are the abnormal pupil phenomena.

7. An apparatus for intelligent virus identification, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.