CN111488562B - Threshold determining method, device, equipment and medium based on face comparison - Google Patents
Threshold determining method, device, equipment and medium based on face comparison Download PDFInfo
- Publication number
- CN111488562B CN111488562B CN202010265167.6A CN202010265167A CN111488562B CN 111488562 B CN111488562 B CN 111488562B CN 202010265167 A CN202010265167 A CN 202010265167A CN 111488562 B CN111488562 B CN 111488562B
- Authority
- CN
- China
- Prior art keywords
- threshold
- face
- user
- preset threshold
- face comparison
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the invention provides a threshold value determining method, device, equipment and medium based on face comparison. The method comprises the following steps: acquiring a face image of a user; face comparison is carried out on the face image, and a face comparison score is obtained; when the face comparison score is not lower than a first preset threshold value, acquiring user element information of a user; and determining a third threshold according to the user element information and the second preset threshold, wherein the first preset threshold is not higher than the second preset threshold. By the embodiment of the invention, the face comparison and recognition success rate of the user can be improved, the user experience is improved, and the safety of high-sensitivity service is enhanced.
Description
Technical Field
The present invention relates to the field of face recognition technologies, and in particular, to a threshold determining method, device, equipment and computer readable storage medium based on face comparison.
Background
The face comparison technology is a core technology of the real-name service of the operator, is widely applied, and the real-name service of the operator has high safety requirements, so that the accuracy of the face comparison result is also required to a certain extent.
However, the comparison threshold used in the face comparison technology at present is generally a static parameter, and because factors such as on-site light, shooting angle, age of a user and the like are changed, the constant threshold is still used for setting an admission threshold of face comparison, so that a certain failure rate exists, and inconvenience is brought to the user for handling business.
Disclosure of Invention
The embodiment of the invention provides a threshold value determining method, device, equipment and computer readable storage medium based on face comparison, which can improve the face comparison recognition success rate of users, improve user experience and enhance the safety of high-sensitivity services.
In a first aspect, an embodiment of the present invention provides a method for determining a threshold based on face comparison, where the method includes: acquiring a face image of a user; face comparison is carried out on the face image, and a face comparison score is obtained; when the face comparison score is not lower than a first preset threshold value, acquiring user element information of a user; and determining a third threshold according to the user element information and the second preset threshold, wherein the first preset threshold is not higher than the second preset threshold.
In some implementations of the first aspect, performing face comparison on the face image to obtain a face comparison score includes: calling a preset reference image of the user according to the identity (Identity Document, ID) of the user; and carrying out face comparison based on the face image and a preset reference image to obtain a face comparison score.
In some implementations of the first aspect, determining the third threshold according to the user element information and the second preset threshold includes: calculating a weight value of each element according to the preset weight corresponding to each element in the user element information; and determining a third threshold value based on the second preset threshold value based on the weighted value of each element.
In some implementations of the first aspect, the user element information includes positive element information and/or negative element information; wherein the forward element information includes at least one of the following options: customer Level (CLV), authentication success frequency (Authentication Success Percent, ASP), user age (Customer of the year on system, CYS); the negative element information includes at least one of the following options: foreign authentication (Remote Authentication, REA), authentication failure frequency (Authentication Fail Percent, AFP), traffic sensitivity (Business sensitivity, BUS).
In some implementations of the first aspect, the method further includes: after determining the third threshold according to the user element information and the second preset threshold, the method further comprises: authenticating based on the face comparison score and a third threshold value to obtain an authentication result; and storing the authentication result and the face image as files.
In some implementations of the first aspect, the third threshold is not higher than the fifth preset threshold and not lower than the fourth preset threshold, wherein the second preset threshold is lower than the fifth preset threshold, and the fourth preset threshold is lower than the first preset threshold.
In some implementations of the first aspect, when the face alignment score is below the first preset threshold and not below the fourth preset threshold, the method further includes: acquiring a historical authentication file of a user; performing face comparison based on the face image and at least one face image in the historical authentication file to obtain at least one face comparison score; when the face comparison score with the highest score in the at least one face comparison score is higher than the face comparison score, comparing the face comparison score with a first preset threshold; and when the face comparison score with the highest score is not lower than a first preset threshold value, acquiring user element information of the user.
In a second aspect, an embodiment of the present invention provides a threshold determining device based on face comparison, where the device includes: the acquisition module is used for acquiring a face image of a user; the comparison module is used for comparing the faces of the face images to obtain face comparison score; the acquisition module is further used for acquiring user element information of the user when the face comparison score is not lower than a first preset threshold value; the determining module is used for determining a third threshold according to the user element information and the second preset threshold, wherein the first preset threshold is not higher than the second preset threshold.
In some implementations of the second aspect, the comparison module is specifically configured to: calling a preset reference image of the user according to the ID of the user; and carrying out face comparison based on the face image and a preset reference image to obtain a face comparison score.
In some implementations of the second aspect, the determining module is specifically configured to: calculating a weight value of each element according to the preset weight corresponding to each element in the user element information; and determining a third threshold value based on the second preset threshold value based on the weighted value of each element.
In some implementations of the second aspect, the user element information includes positive element information and/or negative element information; wherein the forward element information includes at least one of the following options: client level CLV, authentication success frequency ASP, user on-line age CYS; the negative element information includes at least one of the following options: remote authentication REA, authentication failure frequency AFP, service sensitivity BUS.
In some implementations of the second aspect, the apparatus further includes: the authentication module is used for authenticating the third threshold value based on the face comparison score and the third threshold value after determining the third threshold value according to the user element information and the second preset threshold value to obtain an authentication result; and storing the authentication result and the face image as files.
In some implementations of the second aspect, the third threshold is not higher than the fifth preset threshold and not lower than a fourth preset threshold, wherein the second preset threshold is lower than the fifth preset threshold and the fourth preset threshold is lower than the first preset threshold.
In some implementations of the second aspect, the obtaining module is further configured to obtain the historical authentication profile of the user when the face comparison score is below the first preset threshold and not below the fourth preset threshold; performing face comparison based on the face image and at least one face image in the historical authentication file to obtain at least one face comparison score; when the face comparison score with the highest score in the at least one face comparison score is higher than the face comparison score, comparing the face comparison score with a first preset threshold; and when the face comparison score with the highest score is not lower than a first preset threshold value, acquiring user element information of the user.
In a third aspect, an embodiment of the present invention provides a threshold determining device based on face comparison, where the device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the threshold determining method based on face alignment as described in the first aspect or any of the realizations of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer readable storage medium, where computer program instructions are stored, which when executed by a processor implement the threshold determining method based on face alignment described in the first aspect or any of the realizable modes of the first aspect.
The embodiment of the invention provides a threshold determining method, device, equipment and computer readable storage medium based on face comparison. Therefore, the recognition threshold value of the face comparison of the user in the business handling process can be adjusted in real time according to the multidimensional dynamic elements, authentication can be performed based on the threshold value, the face comparison recognition success rate of the user is further improved, user experience is improved, and the safety of high-sensitivity business is enhanced.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present invention, the drawings that are needed to be used in the embodiments of the present invention will be briefly described, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic illustration of an embodiment of the present invention an authentication system architecture schematic;
fig. 2 is a flow chart of a threshold determining method based on face comparison according to an embodiment of the present invention;
fig. 3 is a flowchart of another threshold determining method based on face comparison according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a threshold distribution provided by an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a threshold determining device based on face comparison according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a threshold determining device based on face comparison according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely configured to illustrate the invention and are not configured to limit the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the invention by showing examples of the invention.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The term "and/or" is herein merely an association relationship describing an associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone.
At present, in the face recognition process, the comparison threshold is generally a static experience parameter and cannot be dynamically adjusted according to a specific recognition process, and face comparison elements are changed under different conditions, and the continuously changed elements are adapted by using a constant admission rule, so that the comparison failure with a certain probability is caused.
In other words, the admission threshold of the face comparison is set by only relying on a single static threshold, and even if the user transacts, a certain failure rate exists, so that inconvenience is brought to the user to transact business.
In view of this, the embodiment of the invention provides a threshold determining method, device, equipment and computer readable storage medium based on face comparison, which are used for obtaining a face comparison value by obtaining a face image of a user and carrying out face comparison on the face image, when the face comparison value is not lower than a first preset threshold, obtaining user element information of the user, and determining a third threshold according to the user element information and a second preset threshold. Therefore, the recognition threshold value of the face comparison of the user in the business handling process can be adjusted in real time according to the multidimensional dynamic elements, authentication can be performed based on the threshold value, the face comparison recognition success rate of the user is further improved, user experience is improved, and the safety of high-sensitivity business is enhanced.
In some embodiments, the threshold determination method based on face alignment may be applied to an authentication system. Fig. 1 is a schematic diagram of an authentication system architecture according to an embodiment of the present invention, where as shown in fig. 1, the authentication system may include a service support system, an image acquisition module, a face comparison module, a dynamic threshold module, and a history authentication retention module. Wherein the business support system may be used to initiate a face alignment request, alternatively the business support system may be a customer relationship management (Customer relationship management, CRM) system.
The threshold determining method based on face comparison provided by the embodiment of the invention is described below with reference to the accompanying drawings.
Fig. 2 is a flow chart of a threshold determining method based on face comparison according to an embodiment of the present invention. As shown in fig. 2, the threshold determining method 100 based on face alignment may include S110 to S140.
S110, acquiring a face image of a user.
Specifically, when the user handles the business, the face image of the user can be acquired through the image acquisition device, wherein the image acquisition device can be a video camera, a mobile phone, a tablet computer and the like. In addition, the face image stored before the user transacts business, such as photos, videos and the like in the photo album, can be obtained.
S120, face comparison is carried out on the face image, and a face comparison score is obtained.
Specifically, a preset reference image of the user can be called according to the user ID, and face comparison is performed based on the face image and the preset reference image, so as to obtain a face comparison score.
As a specific example, when the service system initiates a face comparison request, the ID of the user may be obtained, and the reference image of the user stored in advance is called by the ID, so that the face image of the user and the reference image are subjected to face comparison, and a face comparison score of the user is obtained. The ID of the user may be an identification card number, a mobile phone number, or the like, for uniquely identifying the user.
S130, when the face comparison score is not lower than a first preset threshold value, acquiring user element information of the user.
Specifically, the face comparison score can be compared with a first preset threshold, and when the face comparison score is not lower than the first preset threshold, user element information of the user is obtained in real time through the ID, wherein the first preset threshold can be flexibly adjusted according to actual conditions.
The user element information may include positive element information and/or negative element information, where positive element refers to an element that has a positive influence on the authentication passing rate, and when these elements appear during service authentication, the comparison threshold may be appropriately lowered according to the corresponding weight, so as to improve the passing rate, for example, high-level clients, high-success authentication frequency, old users, and the like. The negative element is an element having negative influence on the passing rate, when the elements appear in the service authentication, the present authentication needs a stricter standard, and the comparison threshold can be properly adjusted according to the weight, so as to improve the authentication security, for example, there are different-place authentication, high failure authentication frequency, new users, high sensitivity service and the like.
In some embodiments, the forward element information may include at least one of the following options: client level CLV, authentication success frequency ASP, user in-network age CYS, the negative element information may include at least one of the following options: remote authentication REA, authentication failure frequency AFP, service sensitivity BUS. Here, each element has its corresponding preset weight, for example, CLV has a preset weight of-0.01 and rea has a preset weight of +0.03. It can be understood that the preset weight can be flexibly adjusted according to actual conditions.
And S140, determining a third threshold according to the user element information and the second preset threshold.
Specifically, the weighted value of each element may be calculated according to the preset weight corresponding to each element in the user element information, and the third threshold value may be determined based on the second preset threshold value based on the weighted value of each element. The third threshold is a threshold for admission judgment of face comparison, which is adjusted in real time, the first preset threshold is not higher than the second preset threshold, and the second preset threshold can be flexibly adjusted according to actual conditions.
As a specific example, the weighted value of each element may be calculated according to formula (1), and the third threshold value may be determined on the basis of the second preset threshold value.
Wherein, formula (1) is as follows:
third threshold = second preset threshold + CLV + ASP + CYS + REA + AFP + BUS (1)
The CLV weight is a CLV weight value, the CLV weight value is a preset weight corresponding to the CLV, the ASP weight value is an ASP weight value, the ASP weight value is an ASP corresponding preset weight value, the CYS weight value is a CYS corresponding preset weight value, the REA weight value is a REA corresponding preset weight value, the AFP weight value is an AFP corresponding preset weight value, the BUS weight value is a BUS weight value, and the BUS weight value is a BUS corresponding preset weight value.
In some embodiments, the third threshold is not higher than the fifth preset threshold and not lower than the fourth preset threshold, in other words, the third threshold has a preset range, the fifth preset threshold and the fourth preset threshold are taken as upper and lower limits, when the third threshold exceeds the fifth preset threshold, the fifth preset threshold is taken as the third threshold, when the third threshold is lower than the fourth preset threshold, the fourth preset threshold is taken as the third threshold, and the fifth preset threshold and the fourth preset threshold can be flexibly adjusted according to practical situations. Moreover, the second preset threshold is lower than the fifth preset threshold, and the fourth preset threshold is lower than the first preset threshold, that is, the fifth preset threshold > the second preset threshold > the first preset threshold > the fourth preset threshold.
According to the threshold value determining method based on face comparison, face images of users are obtained, face comparison is carried out on the face images to obtain face comparison values, when the face comparison values are not lower than a first preset threshold value, user element information of the users is obtained, and a third threshold value is determined according to the user element information and a second preset threshold value. Therefore, the recognition threshold value of the face comparison of the user in the business handling process can be adjusted in real time according to the multidimensional dynamic elements, authentication can be performed based on the threshold value, the face comparison recognition success rate of the user is further improved, user experience is improved, and the safety of high-sensitivity business is enhanced.
In some embodiments, the method may further include S150, after determining the third threshold according to the user element information and the second preset threshold, authenticating the user element information with the third threshold based on the face comparison score to obtain an authentication result, and storing the authentication result and the face image as a file.
As a specific example, the face comparison score may be compared with a third threshold, and when the face comparison score is not lower than the third threshold, the service authentication is successful, and when the face comparison score is lower than the third threshold, the service authentication is failed.
In some embodiments, the face comparison score may be compared with a first preset threshold and a fourth preset threshold, and when the face comparison score is lower than the first preset threshold and not lower than the fourth preset threshold, a historical authentication profile of the user is obtained. And carrying out face comparison on the face image and at least one face image in the historical authentication file to obtain at least one face comparison score. When the face comparison score with the highest score in the at least one face comparison score is higher than the face comparison score, comparing the face comparison score with a first preset threshold, and when the face comparison score with the highest score is not lower than the first preset threshold, acquiring user element information of the user, performing the processing from S140 to S150 to obtain an authentication result, and storing the authentication result and the face image as files.
When the face comparison score with the highest score is not higher than the face comparison score, the face comparison score is directly compared with a second preset threshold, authentication fails, and an authentication result and the face image are stored as files.
When the face comparison score with the highest score is lower than the first preset threshold, the face comparison score is directly compared with a second preset threshold, authentication fails, and an authentication result and the face image are stored as files.
As a specific example, a user's historical authentication profile may be obtained in real time, and a face image of a recent reservation may be extracted from the historical authentication profile (e.g., three times recently or three months recently) and compared with a current face image. Therefore, the face images in recent reservation are utilized for comparison, the change of the faces can be reduced as much as possible, and the accuracy of face comparison can be improved.
The method for determining the threshold value based on the face comparison according to the embodiment of the present invention is specifically described below with reference to fig. 3, where fig. 3 is a schematic flow chart of another method for determining the threshold value based on the face comparison according to the embodiment of the present invention.
The method comprises the following specific steps:
and step 1, the service initiates a face comparison request.
Specifically, the service system initiates a face comparison request, transmits in a unique ID of the user, performs face comparison based on the face image of the user, obtains a face comparison score, that is, a current face comparison score, and then executes step 2.
And 2, judging a score threshold value.
Fig. 4 is a schematic diagram of a threshold distribution provided in an embodiment of the present invention, where, as shown in fig. 4, the threshold may include four reference values and a dynamic value, and the threshold is an upper threshold, a reference threshold, a dynamic trigger threshold and a threshold in order from high to low, and the dynamic threshold varies within the upper threshold and the threshold. Here, the fifth preset threshold is an upper limit threshold, the second preset threshold is a reference threshold, the first preset threshold is a dynamic trigger threshold, the fourth preset threshold is a threshold, and the third threshold is a dynamic threshold. The upper limit threshold is the upper limit of the dynamic threshold, no matter how the calculated dynamic threshold changes, the upper limit cannot be exceeded, and when the face comparison score is not lower than the threshold, the dynamic threshold is not required to be adjusted to pass authentication directly. The baseline threshold is the initial default state, i.e., initial value, of the dynamic threshold. And when the face comparison score is not lower than the dynamic trigger threshold, the dynamic threshold is adjusted on the basis of the reference threshold according to the weighted calculation of the positive element and the negative element. The threshold value is the lower limit of the dynamic threshold value, when the face comparison score is not lower than the threshold value, the comparison of the historical authentication files is carried out, the highest value of the comparison is obtained and is used for threshold judgment, and when the face comparison score is lower than the threshold value, the dynamic threshold value is not required to be adjusted, and authentication is directly carried out without passing. The dynamic threshold is a threshold which is adjusted in real time and used for admission judgment of face comparison, and can be subjected to weighting calculation according to positive and negative factors and adjusted in real time on the basis of the reference threshold.
The table 1 is a threshold value range table, and as shown in the table 1, the upper limit threshold value, the dynamic threshold value, the reference threshold value, the dynamic trigger threshold value and the threshold value can be flexibly adjusted in a preset range on the basis of the upper limit threshold value > the reference threshold value > the dynamic trigger threshold value > the threshold value.
TABLE 1
| Threshold type | Suggesting value | Remarks |
| Upper threshold value | 90±5 | Fine tuning |
| Dynamic threshold | Dynamic change | |
| Reference threshold value | 80±5 | Can be finely adjusted, and is higher than the dynamic trigger threshold and lower than the upper limit threshold |
| Dynamic trigger threshold | 75±5 | Can be finely tuned, the threshold value is higher than the threshold value and lower than the reference threshold value |
| Threshold value of threshold | 70±5 | Is fine-tuning and is lower than a dynamic trigger threshold |
As a specific example, the face comparison score may be compared with an upper threshold and a threshold. And when the face comparison score is not lower than the upper threshold, the step 3 is directly executed without adjusting the dynamic threshold. And when the face comparison score is lower than the threshold value, the step 4 is directly executed without adjusting the dynamic threshold value. And when the face comparison score is lower than the upper threshold and not lower than the threshold, executing step 6.
And step 3, passing the authentication, ending the authentication process, and executing step 5.
And step 4, the authentication is not passed, the authentication process is ended, and step 5 is executed.
And 5, archiving the authentication result and the photo.
Specifically, the current authentication result and the face image in the step 1 may be recorded for the next authentication procedure call.
And 6, dynamically triggering threshold judgment.
Specifically, the face comparison score may be compared with the dynamic trigger threshold, and when the face comparison score is not lower than the dynamic trigger threshold, step 7 is executed. When the face alignment score is below the dynamic trigger threshold, step 10 is performed.
Step 7 is executed to acquire the element information.
Specifically, the user element information of the user including CLV, ASP, CYS, REA, AFP, BUS and the like can be acquired by the ID of the user, and then step 8 is performed.
And 8, calculating element weights and adjusting dynamic thresholds.
Specifically, the weighted value of each element may be calculated according to formula (2), the dynamic threshold is adjusted based on the reference threshold, and it is determined whether the dynamic threshold range is exceeded, the upper limit and the lower limit of the dynamic threshold range are respectively an upper limit threshold and a threshold, if the dynamic threshold range is exceeded, the upper limit or the lower limit of the range is used as the final dynamic threshold, that is, the final dynamic threshold is determined according to formula (3), and then step 9 is performed.
Wherein, formula (2) is as follows:
original dynamic threshold = reference threshold + CLV + ASP + CYS + REA + AFP + BUS (2)
The CLV weight is a CLV weight value, the CLV weight value is a preset weight corresponding to the CLV, the ASP weight value is an ASP weight value, the ASP weight value is an ASP corresponding preset weight value, the CYS weight value is a CYS corresponding preset weight value, the REA weight value is a REA corresponding preset weight value, the AFP weight value is an AFP corresponding preset weight value, the BUS weight value is a BUS weight value, and the BUS weight value is a BUS corresponding preset weight value.
As a specific example, the preset weights of the elements may be as shown in table 2.
TABLE 2
| Element(s) | Element type | Preset weight |
| CLV | Forward direction | -0.01 |
| ASP | Forward direction | -0.02 |
| CYS | Forward direction | -0.01 |
| REA | Negative going | +0.03 |
| AFP | Negative going | +0.02 |
| BUS | Negative going | +0.05 |
Equation (3) is shown below:
dynamic threshold=max (threshold, MIN (upper threshold, original dynamic threshold)) (3)
And 9, comparing the scores with a dynamic threshold.
Specifically, the face comparison score may be compared with the dynamic threshold, and when the face comparison score is not lower than the dynamic threshold, step 3 is performed. When the face comparison score is lower than the dynamic threshold, step 4 is performed.
Step 10, a recent history file is acquired, and then step 11 is executed.
And 11, comparing the historical photos and obtaining the highest comparison score.
Specifically, the face image of the recent reservation is extracted based on the history reservation and compared with the current face image, the face comparison score with the highest score, namely the highest historical face comparison score is extracted, and then step 12 is executed.
Step 12, judging whether the current face comparison score is not lower than the historical highest face comparison score, and executing step 13 when the current face comparison score is not lower than the historical highest face comparison score. And when the current face comparison score is lower than the historical highest face comparison score, judging the threshold value by using the historical highest face comparison score, and executing the step 2.
And step 13, directly comparing the reference threshold value with the current face comparison score, and executing the step 5 if the authentication is not passed.
Fig. 5 is a schematic structural diagram of a threshold determining device based on face comparison according to an embodiment of the present invention, and as shown in fig. 5, the threshold determining device 200 based on face comparison may include: an acquisition module 210, a comparison module 220, and a determination module 230.
The acquiring module 210 is configured to acquire a face image of a user. The comparison module 220 is used for comparing the faces of the face images to obtain a face comparison score. The obtaining module 210 is further configured to obtain user element information of the user when the face comparison score is not lower than a first preset threshold. The determining module 230 is configured to determine a third threshold according to the user element information and the second preset threshold, where the first preset threshold is not higher than the second preset threshold.
In some embodiments, the comparison module 220 is specifically configured to: calling a preset reference image of the user according to the ID of the user; and carrying out face comparison based on the face image and a preset reference image to obtain a face comparison score.
In some embodiments, the determining module 230 is specifically configured to: and calculating a weighted value of each element according to the preset weight corresponding to each element in the user element information, and determining a third threshold value based on the weighted value of each element and the second preset threshold value.
In some embodiments, the user element information includes positive element information and/or negative element information. Wherein the forward element information includes at least one of the following options: CLV, ASP, CYS, the negative element information includes at least one of the following: REA, AFP, BUS.
In some embodiments, the apparatus 200 further comprises: and the authentication module is used for authenticating the user element information and the second preset threshold value based on the face comparison score and the third threshold value after determining the third threshold value according to the user element information and the second preset threshold value to obtain an authentication result, and storing the authentication result and the face image as files.
In some embodiments, the third threshold is not higher than the fifth preset threshold and not lower than a fourth preset threshold, wherein the second preset threshold is lower than the fifth preset threshold and the fourth preset threshold is lower than the first preset threshold.
In some embodiments, the obtaining module 210 is further configured to obtain the historical authentication profile of the user when the face comparison score is below the first preset threshold and not below the fourth preset threshold. And carrying out face comparison on the basis of the face image and at least one face image in the historical authentication file to obtain at least one face comparison score. And when the face comparison score with the highest score in the at least one face comparison score is higher than the face comparison score, comparing the face comparison score with a first preset threshold. And when the face comparison score with the highest score is not lower than a first preset threshold value, acquiring user element information of the user.
According to the threshold determining device based on face comparison, face comparison is carried out on the face image by obtaining the face image of the user, the face comparison score is obtained, when the face comparison score is not lower than the first preset threshold, user element information of the user is obtained, and a third threshold is determined according to the user element information and the second preset threshold. Therefore, the recognition threshold value of the face comparison of the user in the business handling process can be adjusted in real time according to the multidimensional dynamic elements, authentication can be performed based on the threshold value, the face comparison recognition success rate of the user is further improved, user experience is improved, and the safety of high-sensitivity business is enhanced.
It may be appreciated that the threshold determining device 200 based on face alignment according to the embodiment of the present invention may correspond to the execution body of the threshold determining method based on face alignment in fig. 2 according to the embodiment of the present invention, and specific details of the operation and/or functions of each module/unit of the threshold determining device 200 based on face alignment may be referred to the description of corresponding parts in the threshold determining method based on face alignment in fig. 2 according to the embodiment of the present invention, which is not repeated herein for brevity.
Fig. 6 is a schematic hardware structure of a threshold determining device based on face comparison according to an embodiment of the present invention.
As shown in fig. 6, the threshold determining device 300 based on face alignment in the present embodiment includes an input device 301, an input interface 302, a central processor 303, a memory 304, an output interface 305, and an output device 306. The input interface 302, the central processing unit 303, the memory 304, and the output interface 305 are connected to each other through a bus 310, and the input device 301 and the output device 306 are connected to the bus 310 through the input interface 302 and the output interface 305, respectively, and further connected to other components of the threshold determining device 300 based on face comparison.
Specifically, the input device 301 receives input information from the outside, and transmits the input information to the central processor 303 through the input interface 302; the central processor 303 processes the input information based on computer executable instructions stored in the memory 304 to generate output information, temporarily or permanently stores the output information in the memory 304, and then transmits the output information to the output device 306 through the output interface 305; the output device 306 outputs the output information to the outside of the threshold determination device 300 based on the face alignment for use by the user.
In one embodiment, the threshold determining device 300 shown in fig. 6 based on face alignment includes: a memory 304 for storing a program; and a processor 303, configured to execute a program stored in the memory, so as to perform the threshold determining method based on face alignment provided in the embodiment shown in fig. 2.
Embodiments of the present invention also provide a computer readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by the processor, implement the face alignment based threshold determination method provided by the embodiment shown in fig. 2.
It should be understood that the invention is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor Memory devices, read-Only Memory (ROM), flash Memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
In the foregoing, only the specific embodiments of the present invention are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present invention is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and they should be included in the scope of the present invention.
Claims (9)
1. A method for determining a threshold based on face comparison, the method comprising:
acquiring a face image of a user;
performing face comparison on the face image to obtain a face comparison score;
when the face comparison score is not lower than a first preset threshold value, user element information of the user is obtained, the user element information comprises positive element information and/or negative element information, the positive element is an element positively influencing the authentication passing rate, when the element appears in service authentication, the comparison threshold value can be properly regulated down according to corresponding weight, the negative element is an element negatively influencing the passing rate, when the element appears in service authentication, the user element information indicates that the authentication needs stricter standard, and the comparison threshold value can be properly regulated up according to weight;
determining a third threshold according to the user element information and a second preset threshold, wherein the first preset threshold is not higher than the second preset threshold, and the third threshold is an adjusted threshold for admission judgment of face comparison;
the determining a third threshold according to the user element information and a second preset threshold includes:
calculating a weighted value of each element according to the preset weight corresponding to each element in the user element information;
and determining the third threshold value on the basis of the second preset threshold value based on the weighted value of each element.
2. The method of claim 1, wherein the performing face comparison on the face image to obtain a face comparison score comprises:
calling a preset reference image of the user according to the identity ID of the user;
and carrying out face comparison on the basis of the face image and the preset reference image to obtain the face comparison score.
3. The method of claim 1, wherein the forward element information includes at least one of the following: client level CLV, authentication success frequency ASP, user on-line age CYS;
the negative element information includes at least one of the following options: remote authentication REA, authentication failure frequency AFP, service sensitivity BUS.
4. The method of claim 1, wherein after determining a third threshold based on the user element information and a second preset threshold, the method further comprises:
authenticating based on the face comparison score and the third threshold value to obtain an authentication result;
and storing the authentication result and the face image as files.
5. The method of claim 1, wherein the third threshold is not higher than a fifth preset threshold and not lower than a fourth preset threshold, wherein the second preset threshold is lower than the fifth preset threshold and the fourth preset threshold is lower than the first preset threshold.
6. The method of claim 5, wherein when the face alignment score is below the first preset threshold and not below a fourth preset threshold, the method further comprises:
acquiring a history authentication file of the user;
performing face comparison based on the face image and at least one face image in the history authentication file to obtain at least one face comparison score;
when the face comparison score with the highest score in the at least one face comparison score is higher than the face comparison score, comparing the face comparison score with the first preset threshold;
and when the face comparison score with the highest score is not lower than the first preset threshold, acquiring the user element information of the user.
7. A threshold determining device based on face comparison, the device comprising:
the acquisition module is used for acquiring a face image of a user;
the comparison module is used for comparing the faces of the face images to obtain face comparison scores;
the acquisition module is further configured to acquire user element information of the user when the face comparison score is not lower than a first preset threshold, where the user element information includes positive element information and/or negative element information, the positive element is an element that has a positive influence on the authentication passing rate, when the elements occur during service authentication, the comparison threshold can be properly adjusted down according to corresponding weights, the negative element is an element that has a negative influence on the passing rate, when the elements occur during service authentication, it indicates that the authentication needs stricter criteria, and the comparison threshold can be properly adjusted up according to the weights;
the determining module is used for determining a third threshold according to the user element information and a second preset threshold, wherein the first preset threshold is not higher than the second preset threshold, and the third threshold is an adjusted threshold for admission judgment of face comparison;
the determining module is specifically configured to:
calculating a weighted value of each element according to the preset weight corresponding to each element in the user element information;
and determining the third threshold value on the basis of the second preset threshold value based on the weighted value of each element.
8. A threshold determination device based on face alignment, the device comprising: a processor and a memory storing computer program instructions;
the processor, when executing the computer program instructions, implements a face alignment based threshold determination method as claimed in any one of claims 1-6.
9. A computer readable storage medium, wherein computer program instructions are stored on the computer readable storage medium, which when executed by a processor, implement the face alignment based threshold determination method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265167.6A CN111488562B (en) | 2020-04-07 | 2020-04-07 | Threshold determining method, device, equipment and medium based on face comparison |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265167.6A CN111488562B (en) | 2020-04-07 | 2020-04-07 | Threshold determining method, device, equipment and medium based on face comparison |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111488562A CN111488562A (en) | 2020-08-04 |
| CN111488562B true CN111488562B (en) | 2023-07-18 |
Family
ID=71791549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010265167.6A Active CN111488562B (en) | 2020-04-07 | 2020-04-07 | Threshold determining method, device, equipment and medium based on face comparison |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111488562B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104901823B (en) * | 2014-03-04 | 2018-09-25 | ***通信集团北京有限公司 | A kind of alarm threshold generation method, service feature index monitoring method and device |
| CN106295672B (en) * | 2015-06-12 | 2019-10-29 | 中移信息技术有限公司 | A kind of face identification method and device |
| CN110443098A (en) * | 2018-05-04 | 2019-11-12 | 北京京东尚科信息技术有限公司 | Authentication system, method, apparatus and computer readable storage medium |
| CN109241868A (en) * | 2018-08-16 | 2019-01-18 | 平安科技（深圳）有限公司 | Face identification method, device, computer equipment and storage medium |
| CN109508705B (en) * | 2018-12-29 | 2020-09-08 | 河北三川科技有限公司 | Dynamic threshold face comparison setting method based on validity period of identity card |
-
2020
- 2020-04-07 CN CN202010265167.6A patent/CN111488562B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111488562A (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9202104B2 (en) | Biometric information correction apparatus, biometric information correction method and computer-readable recording medium for biometric information correction | |
| KR101767454B1 (en) | Method and apparatus of fraud detection for analyzing behavior pattern | |
| US10097687B2 (en) | Nuisance call detection device and method | |
| US11283796B2 (en) | Systems and methods for real-time detection of compromised authentication credentials | |
| US10586030B2 (en) | Method and device for fingerprint authentication | |
| EP1839274A1 (en) | System and method for tracking individuals | |
| CN109829859B (en) | Image processing method and terminal equipment | |
| CN112818885B (en) | Face recognition method, device, equipment and storage medium | |
| CN109905393B (en) | E-commerce login method based on cloud security | |
| EP3644232B1 (en) | Method and device for classifying samples to be assessed | |
| CN110532746B (en) | Face checking method, device, server and readable storage medium | |
| EP3890312B1 (en) | Distributed image analysis method and system, and storage medium | |
| US20150227530A1 (en) | Address Book Ranking Method and Apparatus | |
| CN111488562B (en) | Threshold determining method, device, equipment and medium based on face comparison | |
| US10936706B2 (en) | Biometric authentication | |
| CN112325934B (en) | Wisdom cable channel real-time supervision device | |
| CN117609992A (en) | Data disclosure detection method, device and storage medium | |
| CN111178347B (en) | Ambiguity detection method, ambiguity detection device, ambiguity detection equipment and ambiguity detection storage medium for certificate image | |
| CN113051601A (en) | Sensitive data identification method, device, equipment and medium | |
| CN108235228B (en) | Safety verification method and device | |
| KR101763761B1 (en) | Method of identifying shape of iris and device for identifying iris | |
| CN111160066B (en) | Face recognition method, device, equipment and medium | |
| CN112883946A (en) | Adaptive threshold value selection method and face recognition method | |
| US11698953B2 (en) | Biometric fraud detection system and method | |
| US20150095993A1 (en) | Method and apparatus for preventing theft of personal identity |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |