CN110555330A - image surface signing method and device, computer equipment and storage medium - Google Patents
image surface signing method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110555330A CN110555330A CN201810539006.4A CN201810539006A CN110555330A CN 110555330 A CN110555330 A CN 110555330A CN 201810539006 A CN201810539006 A CN 201810539006A CN 110555330 A CN110555330 A CN 110555330A
- Authority
- CN
- China
- Prior art keywords
- user
- image
- face
- label
- living body
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Abstract
the embodiment of the invention provides an image surface signing method, an image surface signing device, computer equipment and a storage medium, wherein the method comprises the following steps: determining a personal image associated with identity identification information input by a user, then acquiring a user face sign image acquired by a user side, determining whether the user face sign image is a living body image, and whether the user face sign image is matched with the personal image, if the user face sign image is the living body image and the user face sign image is matched with the personal image, performing voice processing according to the user face sign image, and determining whether the user reads face sign guide texts according to voice processing results. The image surface-signing method provided by the embodiment of the invention can not only save labor cost and improve approval efficiency, but also improve the surface-signing security level.
Description
Technical Field
The embodiment of the invention relates to the technical field of finance, in particular to an image surface signing method, an image surface signing device, computer equipment and a storage medium.
background
When a user applies for financial services such as financial credit, educational credit and the like to a service institution, the service institution can verify the valid certificate information and identity of the user through the video surface label.
In the prior art, a video surface label is usually guided by a service organization staff to record a video at an equipment terminal and uploaded to an organization auditing system, the organization auditing system distributes surface label auditors for users, the surface label auditors approve the surface label of the users for auditing, or the organization auditing system audits the action and identity information of the users according to the video.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the video surface label in the prior art depends on manual examination by a surface label examiner, and has the defects of high manpower success and low efficiency, or simple examination content and low safety level.
Disclosure of Invention
the image surface-signing method, the image surface-signing device, the computer equipment and the storage medium, provided by the invention, not only can save the labor cost and improve the approval efficiency, but also can improve the surface-signing security level.
In a first aspect, an embodiment of the present invention provides an image surface labeling method, where the method includes:
determining a personal image associated with the identity information input by the user;
Acquiring a user face sign image acquired by a user side, and determining whether the user face sign image is a living body image and whether the user face sign image is matched with a personal image;
And if the user face label image is a living body image and the user face label image is matched with the personal image, performing voice processing according to the user face label image, and determining whether the user reads the face label guide text according to a voice processing result.
in a second aspect, an embodiment of the present invention further provides an image surface labeling apparatus, where the apparatus includes:
The basic image determining module is used for determining the personal image related to the identity information input by the user;
The system comprises a face signature image verification module, a face signature image verification module and a face signature image verification module, wherein the face signature image verification module is used for acquiring a user face signature image acquired by a user side and determining whether the user face signature image is a living body image and whether the user face signature image is matched with a personal image;
And the surface label voice verification module is used for carrying out voice processing according to the user surface label image and determining whether the user reads the surface label guide text according to a voice processing result if the user surface label image is a living body image and the user surface label image is matched with the personal image.
in a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
One or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement an image facetagging method as described above.
in a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the image surface labeling method as described above.
The embodiment of the invention provides an image surface signing method, which comprises the steps of firstly determining a personal image related to identity identification information input by a user, then obtaining a user surface signing image acquired by a user side, determining whether the user surface signing image is a living body image or not, and whether the user surface signing image is matched with the personal image or not, if the user surface signing image is the living body image and the user surface signing image is matched with the personal image, carrying out voice processing according to the user surface signing image, and determining whether a user reads surface signing guide texts according to voice processing results. The image surface-signing method provided by the embodiment of the invention can not only save labor cost and improve approval efficiency, but also improve the surface-signing security level.
drawings
Fig. 1 is a schematic flowchart of an image surface-signing method according to an embodiment of the present invention;
Fig. 2 is a schematic flowchart of an image surface-signing method according to a second embodiment of the present invention;
Fig. 3 is a schematic structural diagram of an image surface labeling apparatus according to a third embodiment of the present invention;
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
the present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the operations (or steps) as a sequential process, many of the operations can be performed in parallel, concurrently or simultaneously. In addition, the order of the operations may be re-arranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.
Example one
Fig. 1 is a flowchart of an image countersigning method according to an embodiment of the present invention, where the embodiment of the present invention is applicable to countersigning scenes of internet financial and bank insurance institutions, the method may be implemented by an image countersigning device, which may be implemented in a software and/or hardware manner, the device may be integrated in any image countersigning terminal having a network communication function, and the terminal may be a server, such as a server for performing countersigning on an image, or a mobile terminal. As shown in fig. 1, an embodiment of the present invention provides an image countersigning method, which may include:
Step 101, determining a personal image associated with the identification information input by the user.
In the embodiment of the invention, when the user performs the face-to-face signing, the identity information input by the user can be received according to the face-to-face request of the user. The identification may be a certificate for verifying the identity of the user, for example, the identification may include an identification card, a temporary residence card, a house notebook, a driving license, a passport, a certificate letter, a permanent residence card, a health card, etc., and the identification may include a name, an address, a place of birth, and a date of birth. In addition, with the continuous development of the technology, the identity identification mode can also be an anti-counterfeiting identification, a bar code, a magnetic stripe or an IC chip. Further, the identification may be a fingerprint, iris, voice, DNA, or the like.
in the embodiment of the present invention, the public trust network (e.g., public security network, etc.) and most of the registered accounts may store the identification information of the user, and the stored user identification information may be generally associated with a plurality of personal images of the user. Optionally, after the identity information input by the user is obtained, the image of the person can be obtained by calling the public communication network interface according to the identity information input by the user; alternatively, the head portrait of the registered user associated with the identification information is used as the principal image. For example, the public letter network may store identification information of each user and a user image corresponding to each user identification information, most of the registered accounts (e.g., mailbox registered accounts) may include identification information input when the user registers an account and a corresponding personal avatar, and the image of the person may be obtained by calling the public letter network interface according to the identification information input by the user; alternatively, the head portrait of the registered user associated with the identification information is used as the principal image. It should be noted that the number of principal images in the principal image associated with the identification information input by the user may be determined to be more than one.
102, acquiring a user face sign image acquired by a user side, and determining whether the user face sign image is a living body image and whether the user face sign image is matched with the image of the user.
in the embodiment of the invention, when the user performs the face signing, the image of the user in the face signing process can be acquired through the acquisition equipment arranged at the user terminal. When the user terminal acquires the face label image of the user, the user face label image acquired by the user terminal can be directly acquired, and whether the acquired user face label image is a living body image or not is determined. Illustratively, after a user face-to-face label image is acquired, facial feature information in the user face-to-face label image is extracted, the facial feature information is matched with preset facial feature information, if a corresponding matching value is reached, a living body detection instruction is randomly called, corresponding living body operation is carried out on the living body detection instruction according to a user to obtain living body detection information, then matching is carried out according to the living body detection information and the preset living body information, and when the living body detection information is matched with the preset living body information, the living body detection is successful, and the fact that the user face-to-face label image is the living body image is indicated. Optionally, whether the collected user face label image is a living body image or not may be detected by a living body detection method, specifically, a monocular living body detection model may be trained according to a large amount of image sample data, and whether the user face label image collected by the user side is a living body image or not may be judged by the trained living body detection model. In determining whether the user facing sign image is a living body image, it may also be determined whether the user facing sign image matches the principal image. Whether the principal image and the user facing image are the same person can be determined by determining whether the user facing image and the principal image match. In the embodiment of the invention, the identity image associated with the identity identification information in the public trust network is used for carrying out two-factor consistency check, and the user portrait is constructed by using the internet mass search data in combination with the factors such as the position information based on the position service, the user network environment and the like, so that the users of the multiple head and the black birth can be identified.
It should be noted that steps 101 and 102 in the embodiment of the present invention may occur simultaneously; step 101 may precede step 102.
On the basis of the foregoing embodiment, an optional manner may be provided, and optionally, acquiring a user face-tag image acquired by a user side, and determining whether the user face-tag image is a living body image, and whether the user face-tag image matches with the image of the person may include:
acquiring a first face sign picture of a user in a view-finding frame of a camera of a user end; if the preset living body detection model is adopted to determine that the first face sign picture of the user is the living body picture, controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user face sign video collected by the user side; intercepting a user face label video to obtain a user second face label picture; and matching the second face signature picture of the user with the image of the user by adopting a preset living body picture comparison model.
In the embodiment of the invention, a user can set an image acquisition device (such as a camera), and the camera can acquire a picture of the user in the face-to-face signing process in a camera view frame of the user terminal as a first face-to-face signed picture. After the first face-to-face picture is acquired, the image face-to-face device can determine whether the first face-to-face picture of the user is a living body picture or not through a preset living body detection model. And if the preset living body detection model is adopted to determine that the first face sign picture of the user is the living body picture, controlling the user side to start video input and guiding the user to read the guide text aloud to obtain the user face sign video collected by the user side. The guidance text can be a section of text displayed to the user through the client, and the user is guided to read aloud according to the provided text, so that video data and corresponding voice data of the user reading guidance text can be obtained. And if the preset living body detection model is adopted to determine that the first face label picture of the user is not the living body picture, returning to the initial step of image face label to perform face label renewal. After the user facing-signing video is obtained, the image facing-signing device can randomly intercept the user facing-signing video to obtain a second facing-signing picture of the user contained in the user facing-signing video. For example, any frame of image in the user facing sign video is randomly intercepted, and the intercepted image is used as the second facing sign picture of the user.
It should be noted that, the step of intercepting the user facebook video to obtain the second facebook picture of the user may be to randomly intercept the second facebook picture included in the user facebook video from the obtained user facebook video after obtaining the user facebook video, or may be to randomly intercept the second facebook picture in the process of reading the guide text at the user side; the second surface label picture can comprise one or more sheets. Optionally, in the process of controlling the user side to start video entry and guiding the user to read the guide text aloud, the live photo when the user reads the guide text aloud is captured as the second facial-signature picture according to a random time point. The interval of the random time points and the number of times of the second face-to-be-captured face can be set according to actual requirements, for example, three random time points can be set, and the three times of face-to-be-captured faces are captured randomly, so that a second face-to-be-captured image is obtained; in addition, the interval between the three random time points is at least two seconds.
After the second facial signature picture is intercepted, the image facial signature device can match the second facial signature picture of the user with the image of the user by adopting a preset living body picture comparison model. The preset living body image comparison model can be obtained by training a large amount of image sample data in a deep learning mode. Illustratively, a pre-trained living body picture model is adopted to compare the second facial signature picture with a person image obtained by determining the person image associated with the identity information input by the user one by one, and whether the living body in the user facial signature image is the user is determined according to the comparison result. The method for face-signing the user has the advantages that massive image data are applied to the establishment of the user face-signing image, meanwhile, the frame extraction is carried out on the user face-signing video to obtain the captured image, and the captured image is compared with the image of the user in the public security network and other registered accounts of other applications, so that the accuracy of user detection is improved in multiple dimensions.
on the basis of the foregoing embodiment, another optional manner may also be provided, and optionally, acquiring a user face-tag image acquired by a user side, and determining whether the user face-tag image is a living body image, and whether the user face-tag image is matched with the image of the person may include: controlling a user side to start video input and guiding a user to read a guide text aloud to obtain a user face label video collected by the user side; intercepting a user face label video to obtain a user face label picture; and if the preset living body detection model is adopted to determine that the user face signing picture is the living body picture, matching the user face signing picture with the image of the user by adopting the preset living body picture comparison model. In the embodiment of the invention, the comparison of the face-to-face pictures is added once in the first mode relative to the second mode. The first comparison of the face-to-face pictures in the first mode can make preparations before the detection of the later living body pictures and the recording of the face-to-face video of the user, for example, the recording function of the camera is not started before the first comparison of the face-to-face pictures is successful, and the recording function of the camera is started when the first comparison of the face-to-face pictures determines that the first face-to-face pictures are the living body pictures. The first approach also has the benefits of: the method can well guide the user to adapt to the face-to-sign process, when the first face-to-sign picture comparison is not carried out, the interception can be directly carried out, and the subsequent face-to-sign process does not need to be carried out continuously.
and 103, if the user facing sign image is a living body image and the user facing sign image is matched with the image of the user, performing voice processing according to the user facing sign image, and determining whether the user reads the facing sign guide text according to a voice processing result.
In the embodiment of the invention, if the user face-sign image is a living body image and the user face-sign image is matched with the personal image, voice processing is carried out according to the user face-sign image, and whether the user reads the face-sign guide text or not is determined according to a voice processing result. And if the user face-labeling image is not the living body image and/or the user face-labeling image is not matched with the self image, stopping face-labeling and not performing the subsequent face-labeling process. After step 103, the data factors acquired in each step in the surface labeling process may be input into a preset risk control strategy model, and the approval result of the image surface labeling may be output through the risk control strategy model. The whole surface signing process does not need manual participation, and good beneficial effects are achieved, for example, the user information verification capability is stronger, the accuracy of a living body detection and face comparison model is higher, the voice recognition speed is higher, the efficiency of a video surface signing process is higher, and the labor cost is lower.
In this embodiment of the present invention, optionally, performing voice processing according to the user face-label image, and determining whether the user reads the face-label guidance text according to a result of the voice processing may include: performing voice recognition on the user surface label image by adopting a voice recognition model to obtain a user surface label text; it is determined whether the user facebook text matches the speakable facebook guide text. In the embodiment of the invention, the image surface-signing device can control the user terminal to start video input and guide the user to read the guide text aloud, so that the user surface-signing video collected by the user terminal is obtained. The user facing video may include voice data of the user reading guide text. Exemplarily, a voice recognition model is adopted to perform voice recognition on a user facing sign video, audio data are extracted from the user facing sign video, then the extracted voice data are converted into text data through a voice recognition technology, and finally the recognized actual reading text is compared with a standard guiding text which requires reading by a user through a text comparison algorithm, so that the accuracy of reading the guiding text by the user in the facing sign process is determined. Optionally, when the accuracy of the reading guiding text is calculated, other characters except the Chinese characters in the actual reading text and the standard guiding text can be removed, so that the actual reading plain text and the guiding plain text are obtained; then, both the actual reading plain text and the guide plain text can be converted into character string data in a UTF-8 format; acquiring the longest public subsequence from the character string data in the converted UTF-8 format by adopting an LCS algorithm, and recursing the left side and the right side of the public subsequence by using the LCS algorithm; and counting the lengths of all the public subsequences and calculating the actual accuracy rate of the reading text.
The embodiment of the invention provides an image surface signing method, which comprises the steps of firstly determining a personal image related to identity identification information input by a user, then obtaining a user surface signing image acquired by a user side, determining whether the user surface signing image is a living body image or not, and whether the user surface signing image is matched with the personal image or not, if the user surface signing image is the living body image and the user surface signing image is matched with the personal image, carrying out voice processing according to the user surface signing image, and determining whether a user reads a surface signing guide text or not according to a voice processing result. The image surface-signing method provided by the embodiment of the invention can not only save labor cost and improve approval efficiency, but also improve the surface-signing security level.
Example two
fig. 2 is a schematic flow chart of an image surface-signing method according to a second embodiment of the present invention, which is optimized based on the above embodiments. As shown in fig. 2, an embodiment of the present invention provides an image countersigning method, which may include:
step 201, determining the personal image associated with the identification information input by the user.
on the basis of the foregoing embodiment, optionally, determining the principal image associated with the identification information input by the user may include: calling a public trust network interface to obtain a personal image according to the identity identification information input by the user; alternatively, the head portrait of the registered user associated with the identification information is used as the principal image.
Step 202, determining credit investigation records and/or loan times of the user according to the identification information input by the user.
in the embodiment of the invention, the credit investigation report is a main information source and basis for credit assessment of the financial industry. The credit investigation is an activity that a specialized and independent third-party organization establishes a credit file for an individual or an enterprise, collects and objectively records credit information thereof according to law, provides credit information service according to law, and provides a credit information sharing platform for the specialized credit granting organization. In addition, the user can make a loan at a financial institution such as a bank, can make a small loan at other similar loan companies, and can record the corresponding loan information of the user. The identification information of each user can be associated with corresponding credit investigation record information and loan information. After the identification information of the user is input, credit investigation records and/or loan times related to the identification information can be obtained according to the identification information of the user.
and step 203, if the user is determined to belong to the credit loss personnel and/or the loan frequency is larger than the frequency threshold value according to the credit investigation record of the user, rejecting the face sign.
in the embodiment of the present invention, the credit investigation record and/or the loan number may also be used as an evaluation criterion for whether to continue the subsequent face-signing process. If the user is determined to belong to the credit loss personnel according to the credit investigation record of the user and/or the loan times are larger than the time threshold, the user is considered to be not suitable for carrying out various loan approval operations, so that the subsequent surface signing process does not need to be continued, and the surface signing can be directly rejected at the moment. The person who loses credit can be a person who enters a list of losing credit similar to the phenomenon that the loan is not overdue or the loan is paid by others. The loan frequency threshold value can be set according to the personal property record of the user, the loan amount information, whether the historical loan is overdue or not and other factors. And if the user is determined not to belong to the credit loss personnel and/or the loan times do not exceed the time threshold according to the credit investigation record of the user, continuing the subsequent process of the surface signing at the time. The credit investigation record and/or the loan times are used as the advantages of evaluating whether the subsequent surface signing process is carried out or not: the method can realize the identification of the multi-head and black-birth users, thereby improving the safety of the user facing and signing process.
And 204, if the user is determined not to belong to the credit loss person and/or the loan times do not exceed the time threshold according to the credit investigation record of the user, acquiring a user face sign image acquired by the user side, determining whether the user face sign image is a living body image, and determining whether the user face sign image is matched with the user image.
On the basis of the foregoing embodiment, optionally, acquiring a user face-sign image acquired by a user side, and determining whether the user face-sign image is a living body image, and whether the user face-sign image is matched with the image of the person may include: acquiring a first face sign picture of a user in a view-finding frame of a camera of a user end; if the preset living body detection model is adopted to determine that the first face sign picture of the user is the living body picture, controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user face sign video collected by the user side; intercepting a user face label video to obtain a user second face label picture; and matching the second face signature picture of the user with the image of the user by adopting a preset living body picture comparison model. Whether the user face-sign image is the living body image or not is determined by adopting the method, and the advantages that whether the user face-sign image is matched with the image of the user or not are as follows: whether the living body in the face signing process is the user can be determined through living body detection and face comparison, and the wind control capability of the image face signing process is improved.
on the basis of the foregoing embodiment, optionally, acquiring a user face-sign image acquired by a user side, and determining whether the user face-sign image is a living body image, and whether the user face-sign image is matched with the image of the person may include: controlling a user side to start video input and guiding a user to read a guide text aloud to obtain a user face label video collected by the user side; intercepting a user face label video to obtain a user face label picture; and if the preset living body detection model is adopted to determine that the user face signing picture is the living body picture, matching the user face signing picture with the image of the user by adopting the preset living body picture comparison model.
and step 205, if the user facing sign image is a living body image and the user facing sign image is matched with the image of the user, performing voice processing according to the user facing sign image, and determining whether the user reads the facing sign guide text according to a voice processing result.
On the basis of the above embodiment, if the user face-to-face image is not the living body image and/or the user face-to-face image does not match the person image, the image face-to-face process is directly stopped, and the subsequent face-to-face process is not continued. Optionally, performing voice processing according to the user face-label image, and determining whether the user reads the face-label guiding text according to a voice processing result, may include: performing voice recognition on the user surface label image by adopting a voice recognition model to obtain a user surface label text; it is determined whether the user facebook text matches the speakable facebook guide text. The adoption of the voice recognition mode can greatly improve the accuracy of living body recognition.
The embodiment of the invention provides an image face-to-face signing method, which is used for improving the wind control capability of a face-to-face signing process by applying living body detection, face comparison, voice recognition and black product multi-head detection in the image face-to-face signing process. By utilizing an image surface signing scheme based on big data, the identity attribute of a user is accurately identified from multiple dimensions, a user portrait is constructed, the identification of a multi-head user and a black user is realized, and therefore the safety of the user detection process is improved. By means of voice recognition and face comparison, the living body in the image face signing process is determined to be the user, risk control of the image face signing process is enhanced, the human cost of letter examination is released, and the examination and approval efficiency is improved. The image surface-signing method provided by the embodiment of the invention can not only save labor cost and improve approval efficiency, but also improve the surface-signing security level.
EXAMPLE III
fig. 3 is a schematic structural diagram of an image countersigning device according to a third embodiment of the present invention, where the image countersigning device is applicable to countersigning scenes of internet financial and bank insurance institutions, and the device executes the image countersigning method according to any one of the embodiments described above, and the device may be implemented in software and/or hardware. As shown in fig. 3, the image tagging device may include, as shown in fig. 3: a basic image determination module 301, a face-to-face image verification module 302, and a face-to-face voice verification module 303, wherein:
the basic image determining module 301 is configured to determine a principal image associated with the identification information input by the user.
The facial signature image verification module 302 is configured to obtain a user facial signature image acquired by a user side, and determine whether the user facial signature image is a living body image and whether the user facial signature image is matched with the image of the user.
And the surface label voice verification module 303 is configured to, if the user surface label image is a living body image and the user surface label image is matched with the image of the user, perform voice processing according to the user surface label image and determine whether the user reads the surface label guide text according to a voice processing result.
on the basis of the above embodiment, optionally, the basic image determining module 301 may include: the first determining unit is used for calling the public trust network interface to obtain the personal image according to the identity information input by the user; or, a second determination unit configured to take an avatar of the registered user associated with the identification information as the principal image.
On the basis of the above embodiment, optionally, the face-label image verification module 302 may include:
The first face-to-face picture acquiring unit is used for acquiring a first face-to-face picture of a user in a view-finding frame of a camera at a user end; the user face label video acquisition unit is used for controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user face label video acquired by the user side if the first face label picture of the user is determined to be the living picture by adopting a preset living body detection model; the second face-to-face picture acquiring unit is used for intercepting the user face-to-face video to obtain a user second face-to-face picture; the user face-to-face signature image verification unit is used for matching a second face-to-face signature image of the user with the image of the user by adopting a preset living body image comparison model;
On the basis of the above embodiment, optionally, the face-label image verification module 302 may include:
the user surface label video acquisition unit is used for controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user surface label video acquired by the user side; the user face-to-face picture acquiring unit is used for intercepting the user face-to-face video to obtain a user face-to-face picture; and the user face-to-face image verification unit is used for matching the user face-to-face image with the personal image by adopting a preset living body image comparison model if the preset living body detection model is adopted to determine that the user face-to-face image is the living body image.
Based on the foregoing embodiment, optionally, the surface-tag voice verification module 303 may include: the surface label text acquisition unit is used for carrying out voice recognition on the surface label image of the user by adopting a voice recognition model to obtain a surface label text of the user; and the surface label text verification unit is used for determining whether the user surface label text is matched with the reading surface label guide text.
On the basis of the above embodiment, optionally, the image tagging device may further include: a credit record determining module 304 and a credit record executing module 305, wherein:
And the credit investigation record determining module 304 is used for determining credit investigation records and/or loan times of the user according to the identification information input by the user.
and the credit investigation record execution module 305 is used for refusing the face sign if the user is determined to belong to the credit loss person according to the credit investigation record of the user and/or the loan frequency is greater than a frequency threshold value.
The image countersigning device can execute the image countersigning method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the image countersigning method.
Example four
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 412 suitable for use in implementing embodiments of the present invention. The computer device 412 shown in FIG. 4 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 412 is in the form of a general purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors 416, a system memory 428, and a bus 418 that couples the various system components (including the system memory 428 and the processors 416).
Bus 418 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
computer device 412 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 412 and includes both volatile and nonvolatile media, removable and non-removable media.
the system memory 428 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)430 and/or cache memory 432. The computer device 412 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 434 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 418 by one or more data media interfaces. Memory 428 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
a program/utility 440 having a set (at least one) of program modules 442 may be stored, for instance, in memory 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 442 generally perform the functions and/or methodologies of the described embodiments of the invention.
The computer device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, display 424, etc.), with one or more devices that enable a user to interact with the computer device 412, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 412 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 422. Also, computer device 412 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) through network adapter 420. As shown, network adapter 420 communicates with the other modules of computer device 412 over bus 418. It should be appreciated that although not shown in FIG. 4, other hardware and/or software modules may be used in conjunction with the computer device 412, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 416 executes programs stored in the system memory 428 to perform various functional applications and data processing, such as implementing an image surface-signing method provided by embodiments of the present invention, the method comprising:
Determining a personal image associated with the identity information input by the user;
Acquiring a user face sign image acquired by a user side, and determining whether the user face sign image is a living body image and whether the user face sign image is matched with a personal image;
And if the user face label image is a living body image and the user face label image is matched with the personal image, performing voice processing according to the user face label image, and determining whether the user reads the face label guide text according to a voice processing result.
EXAMPLE five
The fifth embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the image surface labeling method provided in the fifth embodiment of the present invention, where the method includes:
Determining a personal image associated with the identity information input by the user;
acquiring a user face sign image acquired by a user side, and determining whether the user face sign image is a living body image and whether the user face sign image is matched with a personal image;
And if the user face label image is a living body image and the user face label image is matched with the personal image, performing voice processing according to the user face label image, and determining whether the user reads the face label guide text according to a voice processing result.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (12)
1. an image facetagging method, the method comprising:
determining a personal image associated with the identity information input by the user;
acquiring a user face sign image acquired by a user side, and determining whether the user face sign image is a living body image and whether the user face sign image is matched with a personal image;
And if the user face label image is a living body image and the user face label image is matched with the personal image, performing voice processing according to the user face label image, and determining whether the user reads the face label guide text according to a voice processing result.
2. The method of claim 1, wherein determining the principal image associated with the identity information input by the user comprises:
Calling a public trust network interface to obtain a personal image according to the identity identification information input by the user; or, the head portrait of the registered user associated with the identification information is used as the personal image.
3. The method of claim 1, wherein the obtaining a user facing sign image collected by a user end and determining whether the user facing sign image is a living body image and whether the user facing sign image matches with a self image comprises:
acquiring a first face sign picture of a user in a view-finding frame of a camera of a user end;
If the preset living body detection model is adopted to determine that the first face sign picture of the user is the living body picture, controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user face sign video collected by the user side;
Intercepting a user face label video to obtain a user second face label picture;
Matching a second face signature picture of the user with the image of the user by adopting a preset living body picture comparison model;
Or, the acquiring a user face label image acquired by a user side, and determining whether the user face label image is a living body image, and whether the user face label image is matched with the image of the user, includes:
Controlling a user side to start video input and guiding a user to read a guide text aloud to obtain a user face label video collected by the user side;
intercepting the user surface label video to obtain a user surface label picture;
and if the preset living body detection model is adopted to determine that the user face signing picture is the living body picture, matching the user face signing picture with the image of the user by adopting the preset living body picture comparison model.
4. The method of claim 1, wherein the performing voice processing according to the user face-label image and determining whether the user reads the face-label guiding text according to the voice processing result comprises:
Performing voice recognition on the user surface label image by adopting a voice recognition model to obtain a user surface label text;
it is determined whether the user facebook text matches the speakable facebook guide text.
5. The method of claim 1, further comprising, after determining the principal image associated with the user-entered identification information:
Determining credit investigation records and/or loan times of the user according to the identity identification information input by the user;
and if the user is determined to belong to the credit loss personnel and/or the loan times are larger than the time threshold according to the credit investigation record of the user, rejecting the surface sign.
6. An image tag device, comprising:
The basic image determining module is used for determining the personal image related to the identity information input by the user;
The system comprises a face signature image verification module, a face signature image verification module and a face signature image verification module, wherein the face signature image verification module is used for acquiring a user face signature image acquired by a user side and determining whether the user face signature image is a living body image and whether the user face signature image is matched with a personal image;
and the surface label voice verification module is used for carrying out voice processing according to the user surface label image and determining whether the user reads the surface label guide text according to a voice processing result if the user surface label image is a living body image and the user surface label image is matched with the personal image.
7. The apparatus of claim 6, wherein the base image determination module comprises:
the first determining unit is used for calling the public trust network interface to obtain the personal image according to the identity information input by the user;
Or, a second determination unit configured to take an avatar of the registered user associated with the identification information as the principal image.
8. The apparatus of claim 6, wherein the face-tag image verification module comprises:
The first face-to-face picture acquiring unit is used for acquiring a first face-to-face picture of a user in a view-finding frame of a camera at a user end;
The user face label video acquisition unit is used for controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user face label video acquired by the user side if the first face label picture of the user is determined to be the living picture by adopting a preset living body detection model;
the second face-to-face picture acquiring unit is used for intercepting the user face-to-face video to obtain a user second face-to-face picture;
the user face-to-face signature image verification unit is used for matching a second face-to-face signature image of the user with the image of the user by adopting a preset living body image comparison model;
Or, the face-label image verification module comprises:
the user surface label video acquisition unit is used for controlling the user side to start video input and guiding the user to read the guide text aloud to obtain a user surface label video acquired by the user side;
The user face-to-face picture acquiring unit is used for intercepting the user face-to-face video to obtain a user face-to-face picture;
and the user face-to-face image verification unit is used for matching the user face-to-face image with the personal image by adopting a preset living body image comparison model if the preset living body detection model is adopted to determine that the user face-to-face image is the living body image.
9. the apparatus of claim 6, wherein the face-tag voice verification module comprises:
the surface label text acquisition unit is used for carrying out voice recognition on the surface label image of the user by adopting a voice recognition model to obtain a surface label text of the user;
and the surface label text verification unit is used for determining whether the user surface label text is matched with the reading surface label guide text.
10. The apparatus of claim 6, further comprising:
The credit investigation record determining module is used for determining credit investigation records and/or loan times of the user according to the identity identification information input by the user;
And the credit investigation record execution module is used for refusing the face sign if the user is determined to belong to the credit loss personnel and/or the loan frequency is larger than the frequency threshold according to the credit investigation record of the user.
11. a computer device, characterized in that the computer device comprises:
One or more processors;
Storage means for storing one or more programs;
the one or more programs being executable by the one or more processors to cause the one or more processors to implement the image facetagging method of any one of claims 1-5.
12. a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out an image facetagging method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810539006.4A CN110555330A (en) | 2018-05-30 | 2018-05-30 | image surface signing method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810539006.4A CN110555330A (en) | 2018-05-30 | 2018-05-30 | image surface signing method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110555330A true CN110555330A (en) | 2019-12-10 |
Family
ID=68734059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810539006.4A Pending CN110555330A (en) | 2018-05-30 | 2018-05-30 | image surface signing method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110555330A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275540A (en) * | 2020-01-14 | 2020-06-12 | 河南中原消费金融股份有限公司 | Consumption credit approval method and device and terminal equipment |
| CN111598686A (en) * | 2020-07-21 | 2020-08-28 | 成都新希望金融信息有限公司 | Video surface signing method and system based on intelligent face recognition |
| CN112288398A (en) * | 2020-10-29 | 2021-01-29 | 平安信托有限责任公司 | Surface label verification method and device, computer equipment and storage medium |
| CN112598064A (en) * | 2020-12-25 | 2021-04-02 | 中国农业银行股份有限公司 | Data processing method and device |
| CN112911180A (en) * | 2021-01-28 | 2021-06-04 | 中国建设银行股份有限公司 | Video recording method and device, electronic equipment and readable storage medium |
| CN114092121A (en) * | 2022-01-18 | 2022-02-25 | 成都车晓科技有限公司 | Remote surface-signing method and system based on big data and image recognition technology |
| CN114677634A (en) * | 2022-05-30 | 2022-06-28 | 成都新希望金融信息有限公司 | Surface label identification method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468950A (en) * | 2014-09-03 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus, terminal and server |
| CN105518708A (en) * | 2015-04-29 | 2016-04-20 | 北京旷视科技有限公司 | Method and equipment for verifying living human face, and computer program product |
| CN105989263A (en) * | 2015-01-30 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method for authenticating identities, method for opening accounts, devices and systems |
| CN106599772A (en) * | 2016-10-31 | 2017-04-26 | 北京旷视科技有限公司 | Living body authentication method, identity authentication method and device |
| CN106850648A (en) * | 2015-02-13 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Auth method, client and service platform |
| US20170295177A1 (en) * | 2015-05-21 | 2017-10-12 | Tencent Technology (Shenzhen) Company Limited | Identity verification method, terminal, and server |
| CN107845033A (en) * | 2017-11-08 | 2018-03-27 | 上海壹账通金融科技有限公司 | Air control report-generating method, device, equipment and computer-readable recording medium |
-
2018
- 2018-05-30 CN CN201810539006.4A patent/CN110555330A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468950A (en) * | 2014-09-03 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Identity authentication method and apparatus, terminal and server |
| CN105989263A (en) * | 2015-01-30 | 2016-10-05 | 阿里巴巴集团控股有限公司 | Method for authenticating identities, method for opening accounts, devices and systems |
| CN106850648A (en) * | 2015-02-13 | 2017-06-13 | 腾讯科技（深圳）有限公司 | Auth method, client and service platform |
| CN105518708A (en) * | 2015-04-29 | 2016-04-20 | 北京旷视科技有限公司 | Method and equipment for verifying living human face, and computer program product |
| US20170295177A1 (en) * | 2015-05-21 | 2017-10-12 | Tencent Technology (Shenzhen) Company Limited | Identity verification method, terminal, and server |
| CN106599772A (en) * | 2016-10-31 | 2017-04-26 | 北京旷视科技有限公司 | Living body authentication method, identity authentication method and device |
| CN107845033A (en) * | 2017-11-08 | 2018-03-27 | 上海壹账通金融科技有限公司 | Air control report-generating method, device, equipment and computer-readable recording medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111275540A (en) * | 2020-01-14 | 2020-06-12 | 河南中原消费金融股份有限公司 | Consumption credit approval method and device and terminal equipment |
| CN111598686A (en) * | 2020-07-21 | 2020-08-28 | 成都新希望金融信息有限公司 | Video surface signing method and system based on intelligent face recognition |
| CN112288398A (en) * | 2020-10-29 | 2021-01-29 | 平安信托有限责任公司 | Surface label verification method and device, computer equipment and storage medium |
| CN112598064A (en) * | 2020-12-25 | 2021-04-02 | 中国农业银行股份有限公司 | Data processing method and device |
| CN112911180A (en) * | 2021-01-28 | 2021-06-04 | 中国建设银行股份有限公司 | Video recording method and device, electronic equipment and readable storage medium |
| CN114092121A (en) * | 2022-01-18 | 2022-02-25 | 成都车晓科技有限公司 | Remote surface-signing method and system based on big data and image recognition technology |
| CN114677634A (en) * | 2022-05-30 | 2022-06-28 | 成都新希望金融信息有限公司 | Surface label identification method and device, electronic equipment and storage medium |
| CN114677634B (en) * | 2022-05-30 | 2022-09-27 | 成都新希望金融信息有限公司 | Surface label identification method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110555330A (en) | image surface signing method and device, computer equipment and storage medium | |
| US11853406B2 (en) | System for verifying the identity of a user | |
| US8284985B2 (en) | Interactive device for processing documents | |
| US10817707B2 (en) | Attack sample generating method and apparatus, device and storage medium | |
| WO2016184325A1 (en) | Identity authentication method, terminal and server | |
| WO2018166187A1 (en) | Server, identity verification method and system, and a computer-readable storage medium | |
| US10509895B2 (en) | Biometric authentication | |
| CN107609463B (en) | Living body detection method, living body detection device, living body detection equipment and storage medium | |
| WO2021175019A1 (en) | Guide method for audio and video recording, apparatus, computer device, and storage medium | |
| CN108429619A (en) | Identity identifying method and system | |
| CN107545241A (en) | Neural network model is trained and biopsy method, device and storage medium | |
| US20190026606A1 (en) | To-be-detected information generating method and apparatus, living body detecting method and apparatus, device and storage medium | |
| TW201710945A (en) | System and method for validating authorship of an electronic signature session | |
| CN109816521A (en) | A kind of banking processing method, apparatus and system | |
| Oloyede et al. | Fingerprint biometric authentication for enhancing staff attendance system | |
| WO2021191659A1 (en) | Liveness detection using audio-visual inconsistencies | |
| WO2019027970A1 (en) | Mobile application for automatic information synthesis | |
| WO2020007191A1 (en) | Method and apparatus for living body recognition and detection, and medium and electronic device | |
| EP3154013A1 (en) | Apparatus, method and system providing remote user authentication | |
| Ahmed et al. | A multifactor student attendance management system using fingerprint biometrics and RFID techniques | |
| CN112201254A (en) | Non-sensitive voice authentication method, device, equipment and storage medium | |
| Czyżewski et al. | The project IDENT: multimodal biometric system for bank client identity verification | |
| US11521428B1 (en) | Methods and systems for signature verification | |
| CN209149305U (en) | A kind of unified biological identification platform applied to banking | |
| US20240126855A1 (en) | System for verifying the identity of a user |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191210 |