CN115830722A

CN115830722A - Living body identification people and certificate comparison method

Info

Publication number: CN115830722A
Application number: CN202310135562.6A
Authority: CN
Inventors: 高河福; 朱岸青; 唐晓东
Original assignee: Guangzhou Senrui Technology Co ltd
Current assignee: Guangzhou Senrui Technology Co ltd
Priority date: 2023-02-20
Filing date: 2023-02-20
Publication date: 2023-03-21

Abstract

The application belongs to the technical field of testimony identification and discloses a living body identification testimony comparison method, which comprises the following steps: reading the certificate, and acquiring user information and a user head portrait of the certificate; acquiring a verification image shot by a camera, identifying a face image from the verification image, acquiring temperature values of a plurality of preset verification point positions in a face image area, and generating a preprocessing temperature group; comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group; calculating the standard deviation and the average value of the comparison temperature group, comparing the standard deviation and the temperature standard deviation interval of the comparison temperature group, and comparing the average value and the temperature threshold interval to generate a living body judgment result; if the living body judgment result is passed, acquiring a comparison image, and generating a testimony comparison result based on the comparison image and the user head portrait; by the method, the time for identifying the testimony of the person is shortened.

Description

Living body identification people and certificate comparison method

Technical Field

The application belongs to the technical field of testimony identification, and particularly relates to a method for identifying testimony of a witness in a living body.

Background

In the prior art, people's identity and testimony are generally recognized by using methods such as face recognition, fingerprint recognition, retina recognition and the like, wherein the people's identity and testimony recognition method with wide application range and convenience is adopted by the people's identity and testimony method, head portrait data shot by a verification object is compared with a user's head portrait on a certificate by the way of face recognition, and whether images of people and testimony are consistent or not is judged, but the existing people's identity and testimony recognition method has the following disadvantages, for example: when the verification object is determined to be the principal or not and the verification object is not a portrait, the verification object needs to be aligned with the camera frame and a series of complicated actions such as blinking, turning around and the like are performed, and a long time is often consumed in the set of process.

In view of the above-mentioned related art, the applicant believes that the conventional identification method takes too much time.

Disclosure of Invention

In order to shorten the time of testimony of a witness identification, the application provides a living body identification testimony of a witness contrast method.

The first purpose of the invention of the application is realized by adopting the following technical scheme:

a living body identification testimony comparison method comprises the following steps:

reading the certificate, and acquiring user information and a user head portrait of the certificate;

acquiring a verification image shot by a camera, identifying a face image from the verification image, acquiring temperature values of a plurality of preset verification point positions in a face image area, and generating a preprocessing temperature group;

comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group;

calculating the standard deviation and the average value of the comparison temperature group, comparing the standard deviation and the temperature standard deviation interval of the comparison temperature group, and comparing the average value and the temperature threshold interval to generate a living body judgment result;

and if the living body judgment result is that the living body passes, acquiring a comparison image, and generating a testimony comparison result based on the comparison image and the user head portrait.

Through the technical scheme, the certificate is read, the user information and the user head portrait in the certificate are obtained, the verification image is obtained through the camera, the face image is identified from the verification image, the temperature values of a plurality of preset verification point positions in the face image area are obtained, and the preprocessing temperature group is generated; comparing each pre-processing temperature value in the pre-processing temperature group with a temperature threshold value interval, setting a plurality of pre-processing temperatures exceeding the temperature threshold value interval as replacement values, facilitating the subsequent distinction of people and portraits according to the pre-processing temperature groups to generate a comparison temperature group, wherein the people are used as constant temperature animals and have the temperature adjusting capability, the body temperature of people is always different from the environmental temperature, the portraits are inorganic matters and do not have the temperature adjusting capability, the temperature of the inorganic matters approaches to the environmental temperature, the body temperature of human bodies is constant in a certain range under different environmental temperatures, the temperature threshold value interval is set according to the natural phenomenon, each pre-processing temperature value is compared with the temperature threshold value interval, and then the numerical value replacement processing is carried out to generate the comparison temperature group, so the method for screening portraits and living bodies; in practical situations, the temperature of the face of a human body, such as the forehead, the cheek, the nose, the eyes, the ears and other parts have different heat dissipation areas and different distances from the heart, and the parts have a temperature difference of 1 ℃ to 3 ℃, so that the standard deviation of the temperature values of all parts of the face of the human body fluctuates within a certain range, and an inorganic substance with a uniform surface like a portrait does not have the characteristic, so that a temperature standard deviation interval can be set according to the natural characteristic; calculating the standard deviation of the comparison temperature group, comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval, equivalently comparing the standard deviation with the standard deviation of the temperature values of all parts of the face of the human body, and obtaining a living body judgment result by combining the average value of the comparison temperature group; when the standard deviation of the comparison temperature group is in the temperature standard deviation interval and the average value of the comparison temperature group is in the temperature threshold value area, judging the living body, otherwise, judging the living body is not the living body; when the living body judgment result is passed, acquiring a comparison image, comparing the comparison image with the head portrait of the user, producing a comparison result, and judging whether the verification image is consistent with the certificate or not; compared with the traditional human evidence identification method, a series of actions of turning the head, blinking and the like of the object to be verified are omitted, the possibility that the object to be verified needs to take pictures repeatedly is reduced, and therefore the time for identifying the human evidence is shortened.

The application is further configured to: after the steps of reading the certificate and acquiring the user information and the user head portrait of the certificate, the method comprises the following steps:

comparing the ID of the user information with the ID in the frozen list;

and if the ID of the user information is not consistent with the ID in the frozen list, generating an ID comparison result as qualified, and starting to acquire a verification image.

According to the technical scheme, the frozen list is used as a list for protecting user information, when a certificate of a user is lost, the user can be applied for freezing by contacting with a certificate issuing related unit, the certificate ID of the user is placed into the frozen list by the certificate issuing related unit, the identity of the user is prevented from being falsely used by other people, before a verification image is obtained, the ID in the user information is compared with the ID of the frozen list, when the ID in the user information is consistent with one ID in the frozen list, the comparison result is failed, and the living body identification testimony comparison process is terminated; when the ID in the user information is inconsistent with any ID in the frozen list, the comparison result is passed, the user is indicated not to be in the frozen list, and a comparison image is obtained; by the method, the user information is protected to a certain extent.

The application is further configured to: comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group comprising the following steps:

analyzing the temperature information of each part of the human face based on authoritative medical literature, evaluating the distribution rule of the human face temperature, determining the lower limit value of the human body temperature and the upper limit value of the human body temperature,

obtaining a temperature threshold interval based on the lower limit value of the human body temperature and the upper limit value of the human body temperature;

and setting the temperature value outside the temperature threshold interval in the pretreatment temperature group as a replacement value to obtain a comparison temperature group.

According to the technical scheme, the interval of the lower limit value of the human body temperature and the lower limit value of the human body temperature is used as a temperature threshold interval; eliminating human factors, according to the actual environment temperature, taking the lowest temperature which can be reached by the face of the human body at the environment temperature as the lower limit value of the human body temperature, taking the highest temperature which can be reached by the face of the human body at the environment as the upper limit value of the human body temperature, comparing the temperature values in the pretreatment temperature group with the upper limit value of the human body temperature and the human body temperature value, and setting the temperature value in the pretreatment temperature group which is smaller than the lower limit value of the human body temperature or larger than the upper limit value of the human body temperature as a replacement value to obtain a comparison temperature group, thereby realizing the screening of the temperature values of the portrait photo and the living body.

The application is further configured to: the method comprises the following steps of calculating the standard deviation and the average value of a comparison temperature group, comparing the standard deviation of the comparison temperature group with a temperature standard deviation interval, comparing the average value with a temperature threshold interval, and generating a living body judgment result, wherein the method comprises the following steps:

analyzing the temperature information of each part of the human face based on authoritative medical literature, evaluating the distribution rule of the standard deviation of the temperature values of a plurality of preset verification point positions, and determining a first temperature comparison value and a second temperature comparison value;

generating a temperature standard deviation interval based on the first temperature comparison value and the second temperature comparison value;

calculating the standard deviation and the average value of the comparison temperature group;

and comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval based on the temperature standard deviation interval and the temperature threshold interval, and comparing the average value of the comparison temperature group with the temperature threshold interval to generate a living body judgment result.

According to the technical scheme, the temperature information of each part of the face of the human body is analyzed according to authoritative medical literature, the distribution rule of the standard deviations of the temperature values of the preset verification point locations is evaluated, the minimum standard deviation of the temperature values of the verification point locations is used as a first temperature comparison value, the maximum standard deviation of the temperature values of the verification point locations is used as a second temperature comparison value, and the interval between the first temperature comparison value and the second temperature comparison value is used as a temperature standard deviation interval; after the standard deviation and the average value of the comparison temperature group are calculated, comparing the standard deviation and the temperature standard deviation interval of the comparison temperature group, comparing the average value of the comparison temperature group with the temperature threshold interval, and if the standard deviation of the comparison temperature group is located in the temperature standard deviation interval and the average value of the comparison temperature group is located in the temperature threshold interval, judging that the verification object is a living body; and if the standard deviation of the comparison temperature group is outside the temperature standard deviation interval or the average value of the comparison temperature group is outside the temperature threshold interval, judging that the verification object is a non-living body.

The application is further configured to: if the living body judgment result is passed, acquiring a comparison image, and generating a testimony comparison result based on the comparison image and the user head portrait, wherein the step comprises the following steps:

after the living body judgment result is passed and a period of time is delayed, acquiring a plurality of contrast images shot by a camera and generating a contrast image group;

and performing similarity calculation on the user head portrait and the contrast image group, and outputting a testimony contrast result.

According to the technical scheme, after the verification object is judged to be a living body, software delays for a period of time, lens-oriented time of the verification object is reserved, an instruction is sent to the camera, the camera continuously shoots towards the verification object to obtain a plurality of comparison images, the comparison images generate comparison image groups, pairwise calculation is carried out between the user head portrait and each comparison image to obtain a testimony comparison result, and therefore testimony identification of the user is completed.

The application is further configured to: the step of calculating the similarity of the user head portrait and the contrast image group and outputting the testimony contrast result comprises the following steps:

the user head portrait is subjected to block division, all edge blocks of the user head portrait are removed, each comparative image is subjected to block division corresponding to the block division mode of the user head portrait, and all edge blocks of the comparative image are removed;

and carrying out similarity calculation on the user head portrait and the blocks corresponding to the comparison images pairwise, and then carrying out weighted summation to generate a testimonial similarity value.

By the technical scheme, all edge blocks of the head portrait of the user and all edge blocks of each comparison image are removed, so that background frames of the head portrait of the user and the comparison images are removed, and the possibility that the head portrait of the user and the background frames of the comparison images influence the calculation of the comparison result is reduced; and carrying out similarity calculation on the user head portrait and the blocks corresponding to each comparison image pairwise, then carrying out weighted summation to obtain a testimony similarity value, and judging whether the verification object is the user according to the testimony similarity value.

The application is further configured to: after the steps of calculating the similarity of the user head portrait and the blocks corresponding to the comparative images pairwise, performing weighted summation to generate a testimonial similarity value, the method comprises the following steps:

setting a similarity threshold;

if the certificate similarity value is larger than the similarity threshold value, judging that the verification object is the certificate user himself;

if the certificate similarity value is lower than the similarity threshold value, the certificate is judged to be the non-certificate user, the certificate ID is placed in a freezing list, and freezing information is sent to the mobile device of the user to which the certificate belongs.

According to the technical scheme, whether the verification object is the identity is judged by comparing the similarity threshold value with the testimony similarity value, if the comparison result is greater than the similarity threshold value, the identity is judged as the certificate user, and the verification object passes through all processes of testimony identification; if the comparison result is larger than the similarity threshold value, the user is judged to be a non-certificate user, the ID of the certificate is placed in a freezing list, the user to which the certificate belongs is frozen, the freezing information is sent to the mobile device of the user to which the certificate belongs, the user is prompted that the certificate of the user is frozen due to the false identity of other people, and therefore the possibility that the user is lost due to the false identity of other people is reduced.

The second invention of the present application is realized by the following technical scheme:

a live identification witness comparison system comprising:

the certificate reading module is used for reading the certificate and acquiring the user information and the user head portrait of the certificate;

the preprocessing temperature group generation module is used for acquiring a verification image, identifying a face image from the verification image, acquiring temperature values of a plurality of preset verification point positions in a face image area and generating a preprocessing temperature group;

the comparison temperature group generation module is used for comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value and generating a comparison temperature group;

the living body judgment module is used for calculating the standard deviation and the average value of the comparison temperature group, comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval, comparing the average value of the comparison temperature group with the temperature threshold interval, and generating a living body judgment result if the standard deviation of the comparison temperature group is in the temperature standard deviation interval and the average value of the comparison temperature group is in the temperature threshold interval;

and the testimony comparison module is used for acquiring a comparison image and generating a testimony comparison result based on the comparison image and the user head portrait.

Through the technical scheme, the certificate reading module reads the certificate and acquires the user information and the user head portrait in the certificate; the preprocessing temperature group generation module acquires a verification image through a camera, acquires temperature values of a plurality of preset verification point positions in a face image region from a face recognition image in the verification image, and generates a preprocessing temperature group; the comparison temperature group generation module compares each pretreatment temperature value in the pretreatment temperature group with a temperature threshold value interval, sets a plurality of pretreatment temperatures exceeding the temperature threshold value interval as replacement values, is convenient for distinguishing people and portraits according to the pretreatment temperature group subsequently, generates a comparison temperature group, because people are used as constant temperature animals and have the temperature regulation capacity, the body temperature of people is always different from the environmental temperature, portraits are inorganic substances which do not have the temperature regulation capacity, the temperature of the inorganic substances approaches to the environmental temperature, the body temperature of human bodies is constant in a certain range under different environmental temperatures, sets the temperature threshold value interval according to the natural phenomenon, compares each pretreatment temperature value with each temperature threshold value interval, and then carries out numerical value replacement processing to generate a comparison temperature group, and the method is used for screening portraits and living bodies; in practical situations, the temperature of the face of a human body, such as the forehead, the cheek, the nose, the eyes, the ears and other parts have different heat dissipation areas and different distances from the heart, and the parts have a temperature difference of 1 ℃ to 3 ℃, so that the standard deviation of the temperature values of all parts of the face of the human body fluctuates within a certain range, and an inorganic substance with a uniform surface like a portrait does not have the characteristic, so that a temperature standard deviation interval can be set according to the natural characteristic; the living body judgment module calculates the standard deviation of the comparison temperature group, compares the standard deviation of the comparison temperature group with the temperature standard deviation interval, is equivalent to comparing with the standard deviation of the temperature value of each part of the face of the human body, and obtains a living body judgment result by combining the average value of the comparison temperature group; when the standard deviation of the comparison temperature group is in the temperature standard deviation interval and the average value of the comparison temperature group is in the temperature threshold value area, judging the living body, otherwise, judging the living body is not the living body; when the living body judgment result is passed, the testimony comparison module acquires a comparison image again, compares the comparison image with the user head portrait, produces a comparison result and judges whether the verification image is consistent with the certificate or not; compared with the traditional human evidence identification method, a series of actions of turning the head, blinking and the like of the object to be verified are omitted, the possibility that the object to be verified needs to take pictures repeatedly is reduced, and therefore the time for identifying the human evidence is shortened.

The third purpose of the invention of the application is realized by adopting the following technical scheme:

a computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the above living body identification witness comparison method when executing said computer program.

The fourth purpose of the invention of the application is realized by adopting the following technical scheme:

a computer-readable storage medium, in which a computer program is stored, which, when executed by a processor, carries out the steps of the above-mentioned living body identification credential comparison method.

In summary, the present application includes at least one of the following beneficial technical effects:

1. compared with the traditional method for identifying the testimony, a series of actions such as turning around and blinking of the object to be verified are omitted, the possibility that the object to be verified takes pictures repeatedly is reduced, and therefore the time for identifying the testimony is shortened.

2. The frozen list is used as a list for protecting user information, when a certificate of a user is lost, a certificate issuing related unit can be contacted to apply for the user to freeze, the certificate ID of the user is placed into the frozen list by the certificate issuing related unit, the identity of the user is prevented from being faked by other people, before a verification image is obtained, the ID in the user information is compared with the ID of the frozen list, when the ID in the user information is consistent with one ID in the frozen list, the comparison result is failed, and the living body identification credential comparison process is terminated; when the ID in the user information is not consistent with any ID in the frozen list, the comparison result is passed, the user is indicated not to be in the frozen list, and a comparison image is obtained; by the method, the user information is protected to a certain extent.

3. The interval of the lower limit value of the human body temperature and the lower limit value of the human body temperature is used as a temperature threshold interval; eliminating human factors, according to the actual environment temperature, taking the lowest temperature which can be reached by the face of the human body at the environment temperature as the lower limit value of the human body temperature, taking the highest temperature which can be reached by the face of the human body at the environment as the upper limit value of the human body temperature, comparing the temperature values in the preprocessing temperature group with the upper limit value of the human body temperature and the human body temperature value, setting the preprocessing temperature value which is smaller than the lower limit value of the human body temperature or larger than the upper limit value of the human body temperature as a replacement value, and then carrying out increasing sequencing on the preprocessing temperature values subjected to data processing to obtain a comparison temperature group, thereby realizing the screening of the temperature values of the portrait and the living body.

Drawings

FIG. 1 is a flowchart of a method for comparing identification certificates of living bodies according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a living body identification and testimony comparison method in accordance with an embodiment of the present application, after step S10;

FIG. 3 is a flowchart of step S30 in a method for comparing identification certificates of living bodies according to an embodiment of the present application;

FIG. 4 is a flowchart of step S40 in the identification and identification of a living body authentication comparison method according to one embodiment of the present application;

fig. 5 is a flowchart in step S50 of the living body identification witness comparison method in the second embodiment of the present application;

fig. 6 is a flowchart in step S52 of the living body identification credential comparison method in the second embodiment of the present application;

FIG. 7 is a schematic block diagram of a system of a living body identification witness comparison method according to a third embodiment of the present application;

fig. 8 is a schematic diagram of an apparatus in the fourth embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to figures 1-8.

Example one

As shown in fig. 1, the present application discloses a living body identification credential comparison method, which can be used to compile a living body identification credential comparison software program, where the living body identification credential comparison software program is used to control a living body identification credential comparison device, in this embodiment, the living body identification credential comparison device includes a camera, a computer, a temperature measurement instrument, a display screen, and a credential reader, where the camera is used to shoot a verification object to obtain a comparison image, and transmit the comparison image to the computer; the temperature measuring instrument is used for measuring the temperature value of the point location of the preset verification object to obtain a preprocessing temperature group and transmitting the preprocessing temperature group to the computer; the certificate reader is used for reading the user information and the user head portrait and transmitting the user information and the user head portrait to the computer; the display screen is used for displaying whether the comparison result of the living body identification testimony passes or not; the living body identification testimony comparison method specifically comprises the following steps:

s10: and reading the certificate, and acquiring the user information and the user head portrait of the certificate.

In this embodiment, the user information includes an identification of the user, for example: name, ID, phone, etc.; the head portrait of the user serves as a reference image for witness comparison.

Specifically, the verification object for people and certificate identification needs to place the certificate on a certificate reader, the certificate reader extracts the user information and the user head portrait in the certificate, and the identification is identified according to the user information to judge whether the certificate can be normally used.

Specifically, the document reader mentioned in the present embodiment can only individually recognize one type of document, such as an identification card, a work card, an electronic social security card, and the like, and if the type of document recognized by the document reader is not within the recognition range thereof, any step of the method of the present application is not performed.

As shown in fig. 2, step S10 is followed by:

s11: and comparing the ID of the user information with the ID in the frozen list.

In this embodiment, before measuring the temperature of the verified object, it is further necessary to determine whether the ID of the certificate is in a frozen list, where the frozen list is used as a list for protecting the user information, when the certificate of the user is lost, the certificate issuing related unit may be contacted with the user issuing related unit to apply for the user to freeze, the certificate ID of the user is placed in the frozen list by the certificate issuing related unit, so as to prevent others from falsifying the identity of the user, and through comparing the ID in the user information with the ID in the preset frozen list, an ID comparison result is generated, and if the ID in the user information appears in the frozen list, it is indicated that someone steals the certificate of the user, and all steps of the method of the present invention are terminated, thereby reducing the loss of the user and playing a certain protection role for the user information.

Further, when the user information of the certificate is detected to be consistent with the ID in the frozen list, an alarm signal is sent to the user applying for freezing, and the address and the time of the frozen user certificate are prompted, so that the user can find the certificate conveniently.

S12: and if the ID of the user information is not consistent with the ID in the frozen list, generating an ID comparison result as qualified, and starting to acquire a verification image.

Specifically, the IDs in the user information are compared with all the IDs in the frozen list, and if the IDs of the user information are inconsistent with the IDs in the frozen list, the user to which the certificate belongs is a non-frozen user, the certificate can be normally used, and the next step is executed, otherwise, all the steps of the method are terminated.

S20: the method comprises the steps of obtaining a verification image shot by a camera, identifying a face image from the verification image, obtaining temperature values of a plurality of preset verification point positions in a face image area, and generating a preprocessing temperature group.

Specifically, after the certificate of the verification object is judged to be capable of being normally used, the verification object needs to be aligned to a lens of a camera, the camera shoots a verification image, the verification image is an image directly obtained by the camera, whether the verification image contains a face image or not is identified through an image identification algorithm, and if the verification image does not contain the face image, any step of the method is not executed; if the verification image comprises a face image, acquiring the forehead, the cheek, the nose, the eyes and the chin of the face image as verification point positions as temperature measuring point positions of a temperature measuring instrument; the temperature measuring instrument can be an infrared temperature measuring sensor or a thermal imager, in this example, in order to reduce cost, a plurality of infrared temperature measuring sensors are adopted, the temperature of a plurality of verification point positions is measured by the plurality of infrared temperature measuring sensors, and the plurality of infrared temperature measuring sensors transmit a plurality of measured temperature values to the computer for processing to obtain a preprocessing temperature group.

S30: and comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group.

In the present embodiment, the substitute value is used to expand the difference between the respective temperature values of the inorganic substance and living body pretreatment temperature groups, and the substitute value may be any value that facilitates expansion of the difference between the inorganic substance and living body temperature values.

Specifically, because a human being is used as a constant temperature animal and has the body temperature regulating capability, the body temperature of the human being always has the difference with the ambient temperature, while inorganic matters such as a portrait photo do not have the temperature regulating capability, the temperature of the inorganic matters approaches to the ambient temperature, the body temperature of the human body is constant in a certain range under different ambient temperatures, and according to the natural phenomenon and the temperature threshold value interval set by combining authoritative medical documents, each pre-treatment temperature value and each temperature threshold value interval are compared and then are subjected to numerical value replacement treatment to generate a comparison temperature group, so that the difference of each temperature value of the inorganic matters and the temperature value of the living body pre-treatment temperature group is enlarged.

As shown in fig. 3, step S30 includes:

s31: analyzing the temperature information of all parts of the human face based on authoritative medical literature, evaluating the distribution rule of the human face temperature, and determining the lower limit value of the human body temperature and the upper limit value of the human body temperature.

Specifically, according to the record of the temperature information of the human face in the authoritative medical literature, the temperatures of the human face, such as the forehead, the cheek, the nose, the eyes, the chin and the like, have different heat dissipation areas and different distances from the heart, the temperature difference of the parts exists between 1 ℃ and 3 ℃, under the appropriate condition, the temperature value of each part of the human face fluctuates within the range of 32 ℃ to 38 ℃, and the inorganic matter with uniform surface like portrait does not have the characteristic; and (3) evaluating the highest value and the lowest value of the human face, such as the forehead, the cheek, the nose, the eyes and the chin, by combining the temperature information of all parts of the human face in the authoritative medical literature, setting the lowest value of the human face temperature as a lower limit value of the human temperature, and setting the highest value of the human face temperature as an upper limit value of the human temperature.

S32: and obtaining a temperature threshold interval based on the lower limit value of the human body temperature and the upper limit value of the human body temperature.

Specifically, the lower limit value of the human body temperature is used as the minimum value of the temperature threshold interval, the upper limit value of the human body temperature is used as the maximum value of the temperature threshold interval, the lower limit value of the human body temperature and the upper limit value of the human body temperature jointly form the temperature threshold interval, and the temperature threshold interval is used as one of the comparison intervals for living body judgment.

S33: and setting the temperature value outside the temperature threshold interval in the pretreatment temperature group as a replacement value to obtain a comparison temperature group.

Specifically, in the present embodiment, the replacement value is set to 0, and by the processing at step S33, the distinction between portrait photograph and living body is realized, and the following list description is made:

combining with authoritative medical literature, the lower limit value of the human body temperature and the lower limit value of the human body temperature can be adjusted according to seasonal changes and actual requirements, for convenience of data processing, the lower limit temperature of the human body is set to be 32 ℃, the upper limit temperature of the human body is set to be 38 ℃, if the environmental temperature a =25 ℃, the verification object is a portrait photograph, as shown in table one:

watch 1

	Forehead temperature	Cheek temperature	Nose temperature	Eye temperature	Temperature of the jaw
						Pretreatment temperature set	25.1℃	25.5℃	26℃	25.0℃	34.5℃
Comparative temperature group	0℃	0℃	0℃	0℃	34.5℃

In particular, the chin temperature in Table I was 34.5C, mainly because the portrait was taken by the hand right at the chin of the portrait and the measured spot was right on the hand.

If the verification object is a human body, the specific processing method is as shown in table two:

watch two

	Forehead temperature	Cheek temperature	Nose temperature	Eye temperature	Temperature of the jaw
						Pretreatment temperature set	37℃	36.5℃	35.4℃	35.2℃	35℃
Comparative temperature group	37℃	36.5℃	35.4℃	35.2℃	35℃

By combining the table I and the table II, the portrait photos of the human body can be rapidly screened through the step S33.

In conclusion, through S31-S33, the difference between the living body contrast temperature set and the portrait contrast temperature set is enlarged by calculating the pretreatment temperature set.

S40: and calculating the standard deviation and the average value of the comparison temperature group, comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval, and comparing the average value with the temperature threshold interval to generate a living body judgment result.

In the present embodiment, according to the record of the information on the temperature of the face of the human body in the authoritative medical literature, the temperatures of the face of the human body, such as the forehead, the cheek, the nose, the eyes and the chin, have different heat dissipation areas and different distances from the heart, and the temperature difference exists between the parts of the face and the heart, so that the temperature standard deviation section is set as one of the living body judgment sections.

Specifically, the temperature values of the comparison temperature group are accumulated, and then the accumulated value is divided by the number of the temperature values in the comparison temperature group to obtain the temperature value of the comparison temperature group; and accumulating the temperature values of each comparison temperature group after subtracting the average value, and dividing the accumulated value by the number of the temperature values in the comparison temperature group to obtain the standard deviation of the comparison temperature group.

Specifically, when the standard deviation of the comparison temperature group is within the temperature standard deviation interval range and the comparison temperature group is within the temperature threshold interval range, the generated judgment result is the living body; when the standard deviation of the comparison temperature group is outside the range of the temperature standard deviation interval or the comparison temperature group is outside the range of the temperature threshold value interval, the generated judgment result is a non-living body; compared with the traditional human evidence identification method, a series of actions of turning the head, blinking and the like of the object to be verified are omitted, the possibility that the object to be verified needs to take pictures repeatedly is reduced, and therefore the time for identifying the human evidence is shortened.

As shown in fig. 4, the step S40 includes:

s41: analyzing the temperature information of all parts of the human face based on authoritative medical literature, evaluating the distribution rule of the standard deviation of the preset temperature values of a plurality of verification point positions, and determining a first temperature comparison value and a second temperature comparison value.

Specifically, according to records of authoritative medical literature about temperature information of the face of the human body, and by combining actual environment temperature, difference conditions of temperature values of a plurality of preset verification point positions are evaluated, a minimum temperature difference value and a maximum temperature difference value are obtained through a plurality of experiments, the minimum temperature difference value is used as a first temperature contrast value, the maximum temperature difference value is used as a second temperature contrast value, and the first temperature contrast value and the second temperature contrast value are both used for distinguishing living bodies from portraits.

S42: and generating a temperature standard deviation interval based on the first temperature contrast value and the second temperature contrast value.

Specifically, the lower temperature limit value is the minimum value of the temperature threshold interval, the upper temperature limit value is the maximum value of the temperature threshold interval, the lower temperature limit value and the upper temperature limit value together form the temperature threshold interval, and the temperature threshold interval is one of the contrast intervals for living body judgment.

S43: the standard deviation and mean of the control temperature groups were calculated.

In this embodiment, the standard deviation of the comparison temperature group represents the difference between a plurality of preset verification points of the verification object, and the average value is used as a further constraint condition for determining the living body.

Specifically, the standard deviation and the mean of the comparison temperature group are calculated as follows:

wherein,

is the number of temperature values in the comparison temperature group,

to compare a certain temperature value of a temperature group,

the average of the comparative temperature groups.

Wherein,

for optimizing the coefficients, according to the actual conditions

The setting is carried out such that,

standard deviations calculated for the comparative temperature groups.

S44: and comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval based on the temperature standard deviation interval and the temperature threshold interval, and comparing the average value of the comparison temperature group with the temperature threshold interval to generate a living body judgment result.

Specifically, the calculation steps for comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval are as follows:

t1<t<t2

if the standard deviation of the comparison temperature group is smaller than the first temperature comparison value or larger than the second temperature comparison value, the standard deviation of each verification point position of the verification object is too low or too high and does not accord with the characteristics of the body temperature of a human body, a judgment result is directly generated to be a non-living body, the fact that the living body verification does not pass is displayed on a display screen, and all steps of the method are finished; if the standard deviation of the comparison temperature group is greater than the first temperature comparison value and less than the second temperature comparison value, the average value of the comparison temperature group is required to be compared with the temperature threshold interval; the calculation steps for comparing the average value of the comparison temperature group with the temperature threshold interval are as follows:

<

<

wherein the lower limit value of the human body degree is

The upper limit value of the human body temperature is

On the basis that the standard deviation of the comparison temperature group is larger than the first temperature comparison value and smaller than the second temperature comparison value, if the average value of the comparison temperature group is larger than the lower limit temperature of the human body and smaller than the upper limit temperature of the human body, a judgment result is generated as a living body, and the passing of the living body verification is displayed on a display screen; otherwise, the generated judgment result is a non-living body, the fact that the living body verification fails is displayed on a display screen, and all steps of the method are finished.

S50: and if the living body judgment result is that the living body passes, acquiring a comparison image, and generating a testimony comparison result based on the comparison image and the user head portrait.

Specifically, after the verification object is judged to be a living body in step S40, a head portrait of the verification object is acquired as a contrast graph, the contrast image is compared with the head portrait of the user, similarity values of the contrast image and the head portrait of the user are calculated, when the similarity is higher than a certain threshold value, the testimony is judged to be consistent, the obtained testimony contrast result is pass, otherwise, the testimony contrast result is fail, preferably, the camera can acquire a plurality of contrast images, compare the plurality of contrast images with the head portrait of the user, calculate the similarity value of each contrast image and the head portrait of the user respectively, and then perform weighted accumulation on each similarity value, so that reliability of the similarity value is improved, and possibility of inaccuracy of the calculated similarity value due to the fact that a single contrast image is unclear is reduced.

Example two

On the basis of the first embodiment, as shown in fig. 5, step S50 includes:

s51: and after the living body judgment result is passed and a period of time is delayed, acquiring a plurality of contrast images shot by the camera and generating a contrast image group.

Specifically, after the verification object is judged to be a living body, after the software delays for a period of time, the software gives the verification object the time for aligning the camera lens, and then sends an instruction to the camera, so that the camera continuously shoots towards the verification object to obtain a plurality of comparison images, thereby generating a comparison image group.

S52: and performing similarity calculation on the user head portrait and the contrast image group, and outputting a testimony contrast result.

Specifically, a plurality of comparison images are generated into a comparison image group, and similarity calculation is carried out on the head portrait of the user and each pair of comparison images to obtain a testimony comparison result.

In the present embodiment, as shown in fig. 6, step S52 includes:

s521: and carrying out block division on the user head portrait, eliminating all edge blocks of the user head portrait, carrying out block division on each comparison image corresponding to the block division mode of the user head portrait, and eliminating all edge blocks of the comparison image.

Specifically, the edge blocks of the user head portrait and all the edge blocks of each comparison image are removed, so that the removal of the background frames of the user head portrait and the comparison images is realized, and the possibility that the calculation of the comparison result is influenced by the background frames of the user head portrait and the comparison images is reduced.

S522: and carrying out similarity calculation on the user head portrait and the blocks corresponding to the comparison images pairwise, and then carrying out weighted summation to generate a testimonial similarity value.

Specifically, similarity calculation is carried out on the user head portrait and the blocks corresponding to each contrast image pairwise, then the similarity values of each contrast image and the user head portrait are weighted and summed, so that a testimony similarity value is obtained, the influence of individual unclear contrast images on the testimony similarity value is reduced, and whether the verification object is the user is judged through the testimony similarity value.

S523: setting a similarity threshold;

specifically, the similarity threshold is used as a comparison value of the testimonial similarity value, the similarity threshold can be adjusted according to actual requirements, and the display threshold is used as a reference value for judging whether the comparison image is consistent with the head portrait of the user.

S524: and if the certificate similarity value is larger than the similarity threshold value, judging that the verification object is the certificate user.

Specifically, if the testimonial talent similarity value is greater than the similarity threshold, the testimonial talent user is determined to be the testimonial user himself, and the testimonial talent identification is passed.

S525: if the credential similarity value is lower than the similarity threshold value, the verification object is judged to be the non-credential user, the credential ID is placed in a freeze list, and freeze information is sent to the mobile equipment of the user to which the credential belongs.

Specifically, if the testimony similarity value is lower than the similarity threshold value, the user is judged to be a non-certificate user, the testimony identification is not passed, the ID of the certificate is placed in a freezing list, the user to which the certificate belongs is frozen, the freezing information is sent to the mobile equipment of the user to which the certificate belongs, the user is prompted that the certificate of the user is frozen due to the fact that the identity of the user is replaced by other people, and therefore the possibility that the user is lost due to the fact that the identity of the user is falsely used by other people is reduced.

EXAMPLE III

As shown in fig. 7, the present application discloses a living body identification witness comparison system for performing the steps of the above living body identification witness comparison method, which corresponds to the living body identification witness comparison method in the above embodiment.

The living body identification testimony comparison system comprises a testimony reading module, a preprocessing temperature group generating module, a comparison temperature group generating module, a living body judging module and a testimony comparison module, and the detailed description of each functional module is as follows:

the preprocessing temperature group generation module is used for acquiring a verification image, identifying a face image from the verification image, acquiring temperature values of a plurality of verification point positions preset in a face image area and generating a preprocessing temperature group;

Wherein, certificate reads the module and includes:

the user ID comparison submodule is used for comparing the ID in the user information with the ID in the frozen list;

the user ID judging submodule is used for judging whether the ID in the user information is consistent with the ID in the frozen list or not, if so, the generated ID comparison result is unqualified, and the unqualified picture is displayed on the display screen; and if the ID of the user information is inconsistent with the ID in the frozen list, judging that the ID comparison result is qualified.

Wherein, the comparison temperature group generation module comprises:

the temperature threshold interval generation submodule is used for receiving setting signals of a human body temperature lower limit value and a human body temperature lower limit value, storing the human body temperature lower limit value and the human body temperature upper limit value and generating a temperature threshold interval;

a pretreatment temperature group replacement submodule for setting the temperature value outside the temperature threshold interval in the pretreatment temperature group as a replacement value to obtain a comparison temperature group

Wherein, the living body judgment module includes:

the temperature standard deviation interval generation submodule is used for receiving a set signal of the first temperature contrast value and the second temperature contrast value of the person and generating a temperature standard deviation interval;

the comparison temperature group calculation submodule is used for calculating the standard deviation and the average value of the comparison temperature group;

and the living body judgment submodule is used for comparing the standard deviation of the comparison temperature group with the temperature standard deviation interval, and comparing the average value of the comparison temperature group with the temperature threshold interval to generate a living body judgment result.

Wherein, testimony of a witness contrast module includes:

the contrast image acquisition submodule is used for acquiring a plurality of contrast images shot by the camera and generating a contrast image group;

and the similarity calculation operator module is used for calculating the similarity of the user head portrait and the comparison image group and outputting a testimony comparison result.

The similarity operator module includes:

an image segmentation sub-module: the system comprises a user head portrait dividing module, a comparison module and a comparison module, wherein the user head portrait is divided into blocks, all edge blocks of the user head portrait are eliminated, and each comparison image is divided into blocks corresponding to the block division mode of the user head portrait, and all edge blocks of the comparison image are eliminated;

the testimony similarity value generation submodule is used for carrying out similarity calculation on the head portrait of the user and the blocks corresponding to the comparison images in pairs, and then carrying out weighted summation to generate a testimony similarity value;

the similarity threshold setting submodule is used for setting a similarity threshold;

and if the certificate similarity value is greater than the similarity threshold value, judging that the verification object is the certificate user, and finishing all the steps.

And if the credential similarity value is lower than the similarity threshold value, the verification failure sub-module judges that the verification object is a non-credential user, places the credential ID into a freeze list, and sends freeze information to the mobile equipment of the user to which the credential belongs.

For the specific definition of the living body identification credential comparison system, the definition of the living body identification credential comparison method in the above can be referred to, and details are not repeated herein; all modules in the living body identification witness comparison system can be completely or partially realized through software, hardware and a combination of the software and the hardware; the modules can be embedded in a hardware form or independent from a processor in the computer device, or can be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

Example four

Referring to fig. 8, in this embodiment, a computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the following steps when executing the computer program:

s10: reading the certificate, and acquiring user information and a user head portrait of the certificate;

s20: acquiring a verification image shot by a camera, identifying a face image from the verification image, acquiring temperature values of a plurality of preset verification point positions in a face image area, and generating a preprocessing temperature group;

s30: comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group;

s40: calculating the standard deviation and the average value of the comparison temperature group, comparing the standard deviation and the temperature standard deviation interval of the comparison temperature group, and comparing the average value and the temperature threshold interval to generate a living body judgment result;

In the present embodiment, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program realizes the following steps when executed:

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink), DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct bused dynamic RAM (DRDRAM), and bused dynamic RAM (RDRAM).

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art; the technical solutions described in the foregoing embodiments may still be modified, or some features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims

1. A method for comparing a person identification certificate of a living body, comprising:

2. The method for comparing the identification personality according to claim 1, wherein:

after the steps of reading the certificate and acquiring the user information and the user head portrait of the certificate, the method comprises the following steps:

comparing the ID of the user information with the ID in the frozen list;

3. The method for comparing the identification personality according to claim 1, wherein:

comparing the pretreatment temperature group with a preset temperature threshold interval, setting a temperature value outside the temperature threshold interval as a replacement value, and generating a comparison temperature group comprising the following steps:

analyzing temperature information of all parts of the human face based on authoritative medical literature, evaluating a distribution rule of the human face temperature, and determining a lower limit value of the human body temperature and an upper limit value of the human body temperature;

4. The method for comparing the identification personality according to claim 1, wherein:

the method comprises the following steps of calculating the standard deviation and the average value of a comparison temperature group, comparing the standard deviation of the comparison temperature group with a temperature standard deviation interval, comparing the average value of the comparison temperature group with a temperature threshold interval, and generating a living body judgment result, wherein the method comprises the following steps of:

generating a temperature standard deviation interval based on the first temperature contrast value and the second temperature contrast value;

5. The method for comparing the identification personality according to claim 1, wherein: the step of obtaining a contrast image and generating a testimony contrast result based on the contrast image and the head portrait of the user comprises the following steps:

6. The method for comparing the identification personality according to claim 5, wherein:

the step of calculating the similarity of the user head portrait and the comparison image group and outputting the testimony comparison result comprises the following steps:

7. The method for comparing the identification personality according to claim 6, wherein:

after the steps of calculating the similarity of the user head portrait and the blocks corresponding to the comparative images pairwise, performing weighted summation to generate a testimonial similarity value, the method comprises the following steps:

setting a similarity threshold;

if the credential similarity value is lower than the similarity threshold value, the verification object is judged to be the non-credential user, the credential ID is placed in a freeze list, and freeze information is sent to the mobile equipment of the user to which the credential belongs.

8. The utility model provides a living body discernment testimony of a witness contrast system which characterized in that includes:

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the living body identification witness comparison method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program which, when executed by a processor, implements the steps of the living body identification witness comparison method according to any one of claims 1 to 7.