CN108875478B - People-authentication-integrated verification method, device and system and storage medium - Google Patents
People-authentication-integrated verification method, device and system and storage medium Download PDFInfo
- Publication number
- CN108875478B CN108875478B CN201710692598.9A CN201710692598A CN108875478B CN 108875478 B CN108875478 B CN 108875478B CN 201710692598 A CN201710692598 A CN 201710692598A CN 108875478 B CN108875478 B CN 108875478B
- Authority
- CN
- China
- Prior art keywords
- time
- face image
- real
- face
- verification
- 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
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Collating Specific Patterns (AREA)
- Processing Or Creating Images (AREA)
Abstract
Embodiments of the present invention provide a method, apparatus and system and a storage medium. The method comprises the following steps: step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful. The method, the device and the system as well as the storage medium have high verification efficiency, high speed and good user experience.
Description
Technical Field
The invention relates to the field of face recognition, in particular to a people-certificate-integrated verification method, a device and a system and a storage medium.
Background
Verification of the consistency of human faces and identity documents has become an increasingly important verification link in many public fields. For example, in the field of high-speed rail and airplane trips, check-in links of hotels and hotels, entertainment places such as internet cafes and the like, a face technology of people and card integration is gradually applied in a large-scale manner to perform identity verification.
In addition to the core accuracy, the response speed is also a key factor to be considered in the verification process. During the entire verification process, essentially three main steps are performed: 1. document reading, identifying faces on documents (e.g., identification cards); 2. after reading the certificate, capturing a face in a video stream through a camera; 3. and comparing the two faces, determining whether the two faces are matched, and giving a result.
The existing witness-integration verification takes long time, a user feels a card pause, and the user experience is not good. Therefore, a certain optimization of the existing verification process is needed.
Disclosure of Invention
The present invention has been made in view of the above problems. The invention provides a person-certificate-integrated verification method, a person-certificate-integrated verification device, a person-certificate-integrated verification system and a storage medium.
According to an aspect of the present invention, there is provided a person-authentication-in-one verification method, including: step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
Exemplarily, the step S240 further includes: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; or step S250 further includes: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the method further comprises the following steps: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Exemplarily, the step S280 further includes: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290 further comprises: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
Illustratively, the method further comprises: and determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the method further comprises: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
According to another aspect of the invention, a people-certification integrated verification device is provided, which comprises a real-time face image acquisition module, a cache module, a certificate face image acquisition module, a cache image searching module and a cache verification module, wherein the real-time face image acquisition module is used for acquiring a real-time face image of a user to be authenticated, which is acquired by an image acquisition device in real time; the caching module is used for caching the real-time face image acquired in a preset caching time period before the current moment; the certificate face image acquisition module is used for acquiring a certificate face image of a user to be authenticated; the cache image searching module is used for searching a cache face image meeting the preset requirement from the cache face images cached in the preset cache time period before the certificate face image is acquired, and if the cache face image meeting the preset requirement is searched, the cache checking module is started; the cache checking module is used for matching the face in the searched cache face image with the face in the certificate face image and judging whether the person-certificate-integrated checking is successful or not.
Exemplarily, the device further comprises a real-time image searching module, a real-time verification module and a failure determining module, wherein the cache image searching module further comprises a first time determining sub-module, which is used for taking the time when the certificate face image is acquired or the current time as a searching starting time and starting the real-time image searching module if the cache face image meeting the preset requirement is not searched; or the cache checking module also comprises a second moment determining submodule used for taking the moment of acquiring the face image of the certificate or the current moment as the starting moment of searching and starting the real-time image searching module if the person-certificate-based checking fails; the real-time image searching module is used for searching a real-time face image meeting preset requirements from the real-time face images acquired after the searching starting time, if the real-time face image meeting the preset requirements is searched from the real-time face images acquired in a preset searching time period after the searching starting time, the real-time checking module is started, and if the real-time face image meeting the preset requirements is not searched from the real-time face images acquired in the preset searching time period after the searching starting time, the failure determining module is started; the real-time checking module is used for matching the face in the searched real-time face image with the face in the certificate face image and judging whether the person-certificate-integrated checking is successful or not so as to obtain a real-time checking result; the failure determination module is used for determining the person-certificate-based verification failure so as to obtain a real-time verification result.
Exemplarily, the real-time verification module further includes a first counting submodule and a first count judgment submodule, wherein the first counting submodule is configured to count the number of times of the verification failure if the real-time verification result is that the verification failure is a verification failure; the first time judgment submodule is used for judging whether the times of the check failures reach a time threshold value, if the times of the check failures do not reach the time threshold value, the current time is used as the search starting time and a real-time check module is started, and if the times of the check failures reach the time threshold value, the real-time check result is determined to be a final check result; and/or the failure determining module further comprises a second counting submodule and a second secondary number judging submodule, wherein the second counting submodule is used for counting the times of the verification failure; the second time judgment submodule is used for judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, the current time is used as the search starting time, the real-time verification module is started, and if the times of the verification failures reach the time threshold value, the real-time verification result is determined to be the final verification result.
Illustratively, the apparatus further comprises: and the final result determining module is used for determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the apparatus further comprises: and the deleting module is used for deleting the cached face image of which the difference between the acquisition time and the current time exceeds the preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
According to another aspect of the present invention, there is provided a people-authentication-verification system, comprising an image-capturing device, a processor and a memory, wherein the memory stores computer program instructions, and the computer program instructions are executed by the processor for performing the following steps: step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
Illustratively, the step S240 for execution by the computer program instructions when executed by the processor further comprises: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; or the step S250 for execution when the computer program instructions are executed by the processor further comprises: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the computer program instructions when executed by the processor are further operable to perform the steps of: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Illustratively, the step S280 for execution by the processor when the computer program instructions are executed further comprises: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290, performed by the processor when the computer program instructions are executed, further comprises: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
Illustratively, the computer program instructions when executed by the processor are further for performing the steps of: and determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the computer program instructions when executed by the processor are further for performing the steps of: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
According to another aspect of the present invention, there is provided a storage medium having stored thereon program instructions operable when executed to perform the steps of: step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
Illustratively, the step S240 for execution of the program instructions when running further comprises: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; or the step S250 for execution when the program instructions are executed further includes: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the program instructions are further operable when executed to perform the steps of: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Illustratively, the step S280 for execution of the program instructions when running further comprises: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290, executed by the program instructions when executed, further comprises: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
Illustratively, the program instructions are further operable when executed to perform the steps of: and determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the program instructions are further operable when executed to perform the steps of: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
According to the person-certificate-in-one verification method, the device and the system as well as the storage medium, the real-time face image is cached in advance, and the face comparison is carried out on the cached real-time face image and the certificate-based face image, so that the verification efficiency of the method is high, the speed is high, and the user experience is good.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail embodiments of the present invention with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 illustrates a schematic block diagram of an example electronic device for implementing a witness verification method and apparatus in accordance with embodiments of the invention;
FIG. 2 shows a schematic flow diagram of a people-authentication-verification method according to one embodiment of the invention;
FIG. 3 shows a schematic diagram of a person-to-verify-check flow, according to one embodiment of the invention;
FIG. 4 shows a schematic block diagram of a witness-verification apparatus in accordance with one embodiment of the present invention; and
FIG. 5 shows a schematic block diagram of a witness unified verification system, according to one embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of embodiments of the invention and not all embodiments of the invention, with the understanding that the invention is not limited to the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the invention described herein without inventive step, shall fall within the scope of protection of the invention.
As described above, in the existing whole testimonial-to-human verification process, three main steps are essentially performed: 1. document reading, identifying faces on documents (e.g., identification cards); 2. after reading the certificate, capturing a face in a video stream through a camera; 3. and comparing the two faces, determining whether the two faces are matched, and giving a result. Considering that in the operation of step 2, capturing a face from a video stream often takes a certain time, because a face capture image with excellent quality (such as a front face, a clear face, no closed eyes, soft illumination, no virtual focus, etc.) needs to be selected within a certain time, this time often needs about 0.5 seconds. In the case where the certificate is an identification card, the reading operation of step 1 is 0.8 seconds in accordance with the ministry of public security standard. In addition, a general face contrast requires at least 0.2 seconds. Thus, the total verification time is expected to reach: 0.8+0.5+0.2 ═ 1.5. Generally speaking, from the user experience, the verification time of about 1 second is relatively free from the feeling of pause, and the user experience is affected by too long time.
In order to solve the above-mentioned problems, embodiments of the present invention provide a person-authentication-in-one verification method, apparatus and system, and a storage medium. According to the verification method and the verification device for the person-certificate-in-one, the verification speed is high, and the card-free experience of a user can be realized. The person-certificate-integrated verification method provided by the embodiment of the invention can be well applied to various fields of identity verification by adopting the person-certificate-integrated verification technology, such as the fields of access control monitoring, public travel, travel and lodging and the like.
First, an example electronic device 100 for implementing the human authentication-verification method and apparatus according to an embodiment of the present invention is described with reference to fig. 1.
As shown in FIG. 1, electronic device 100 includes one or more processors 102, one or more memory devices 104, an input device 106, an output device 108, and an image capture device 110, which are interconnected via a bus system 112 and/or other form of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.
The processor 102 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement client-side functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 108 may output various information (e.g., images and/or sounds) to an external (e.g., user), and may include one or more of a display, a speaker, etc.
The image capture device 110 may capture images (including video frames) and store the captured images in the storage device 104 for use by other components. The image capture device 110 may be a surveillance camera. It should be understood that the image capture device 110 is merely an example, and the electronic device 100 may not include the image capture device 110. In this case, the face image (and the certificate image) may be captured by other image capturing means and the captured image may be transmitted to the electronic apparatus 100.
Illustratively, the exemplary electronic device for implementing the witness verification method and apparatus according to embodiments of the present invention may be implemented on a device such as a personal computer or a remote server.
Next, a testimonial-to-testimonial verification method according to an embodiment of the present invention will be described with reference to fig. 2. FIG. 2 shows a schematic flow diagram of a people-authentication-verification method 200, according to one embodiment of the invention. As shown in FIG. 2, a human authentication-verification method 200 includes the following steps.
In step S210, a real-time face image of the user to be authenticated, which is acquired in real time by the image acquisition device, is acquired.
The real-time face image may be any suitable image containing face information. Illustratively, the image acquisition device can capture a face in front based on a face capture technology to obtain an image containing face information. Subsequently, a real-time face image may be acquired based on the acquired image. In one example, the real-time face image may be an original-size face image containing background information acquired by the image acquisition device. In another example, the face image may be a face image obtained after face extraction is performed on an original-size face image containing background information acquired by an image acquisition device.
The real-time face image and the certificate face image described below may be sent to the electronic device 100 by a client device (such as a security device including a camera) to be verified by the processor 102 of the electronic device 100, or may be collected by the image collecting device 110 included in the electronic device 100 and transmitted to the processor 102 to be verified by the verification.
In step S220, the real-time face image obtained in the preset caching period before the current time is cached.
The real-time face image cached in step S220 is the real-time face image acquired in step S210. For example, a real-time face image acquired in a preset caching period before the current time may be cached in the image caching library. In the description herein, after the real-time face image is cached, the real-time face image will be referred to as a cached face image.
In one example, the method 200 may further include: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
The image cache library may only cache real-time face images acquired within a fixed time length (i.e. a preset cache period). For example, the preset buffering period may be 3 seconds. The testimony of a witness unification verification system can take a candid photograph the face that appears in front of the camera in a circulating reciprocating way, obtains the real-time face image that contains face information. Meanwhile, real-time face images acquired within a period of 3 seconds can be cached in the image cache library. For example, at second 0, the image cache library may be empty, followed by gradual accumulation of real-time face images; in the 3 rd second, the image cache library caches the real-time face images acquired from the 0 th second to the 3 rd second; in the 4 th second, the image cache library caches the real-time face images acquired in the 1 st to 4 th seconds, and deletes the previously cached real-time face images acquired in the 0 th to 1 st seconds; in the 5 th second, the image cache library caches the real-time face images acquired in the 2 nd to 5 th seconds, and deletes the previously cached real-time face images acquired in the 1 st to 2 nd seconds; and so on.
Because the probability that the real-time face image and the certificate face image cached closer to the acquisition moment of the certificate face image come from the same user (the person needing to confirm the consistency of the face and the certificate) is higher, only the recently acquired real-time face image can be cached, and the real-time face image with the earlier caching time is discarded, so that the storage space is saved, and the data reading and writing time is shortened.
Of course, if necessary, the cached face image whose difference between the acquisition time and the current time exceeds the preset caching period may not be deleted.
In step S230, a certificate face image of the user to be authenticated is acquired.
Illustratively, a credential may be, but is not limited to, one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
It is understood that, in step S210, the operation of acquiring the real-time face image by the image acquisition device is continuously performed (described as real-time acquisition). In step S230, the operation of acquiring the face image of the certificate occurs when the user performs the person-certificate-based verification.
In the case where the certificate is a certificate having a built-in chip (e.g., a second-generation identification card, a social security card, etc.), a face image of the certificate may be acquired through a card reader. For example, taking a second-generation identification card as an example, a user uses the identification card to perform a card swiping operation, and an identification card reader can read user information stored in a built-in chip of the identification card through Radio Frequency Identification (RFID) technology and the like, including a photo of a head portrait of the user (i.e., a face image of the identification card).
When the certificate is a certificate without a built-in chip (such as a generation of identity card, passport, driver's license and the like), the image acquisition device can be used for acquiring the certificate image of the certificate, and the part where the face is located is identified from the whole certificate image to obtain the certificate face image. The image acquisition device for acquiring the certificate image can be the same device as the image acquisition device for acquiring the real-time human face image, and can also be a different device.
In step S240, a cached face image meeting the preset requirement is searched from cached face images cached in a preset caching period before the certificate face image is acquired, and if the cached face image meeting the preset requirement is found, the process goes to step S250.
In step S250, the face in the searched cached face image is matched with the face in the certificate face image, and whether the person-certificate-in-one verification is successful is determined.
Under the condition that the image cache library caches real-time face images acquired within a fixed time length, when certificate face images are acquired, the certificate face images can be directly searched from the image cache library, and whether cached face images meeting preset requirements exist in the face images cached in the image cache library at the moment is determined.
The preset requirements may be set as desired, for example, the preset requirements may include, but are not limited to, one or more of the following: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
If 30 face images are cached in the image cache library at the moment, and 5 cached face images meeting preset requirements exist in the image cache library, the certificate face images and the 5 cached face images can be compared one by one. If the 5 cached face images have cached face images with the faces matched with the faces in the certificate face images, the person-certificate-integration verification is determined to be successful. If the 5 cached face images do not have the cached face image with the face matched with the face in the certificate face image, the real-time face image acquired after the certificate face image is acquired can be continuously acquired. And then, carrying out face matching based on the acquired face image and the certificate face image, and determining whether the person-certificate-in-one verification is successful.
Continuing with the above example, a cache space with a time length of 3 seconds can be provided to cache the real-time face image captured by the camera, and the face image is automatically discarded after 3 seconds. When the user X swipes the identity card (step 1 in the prior art), the system does not start a face snapshot process (step 2 in the prior art), but first checks the cache within 3 seconds before to determine whether a possible face of the user X already exists. If the certificate face image exists, the face in the cached face image can be directly compared with the face in the certificate face image; if not, a comparison process based on the snap faces in the new video stream may be started. This can be done with a high probability to eliminate the time of step 2, thereby greatly speeding up the human-authentication-verification process.
In actual measurement experience, the face captured in advance within 3 seconds often has a very high probability (about 90%) to replace the face captured actively later. In the example where the document is an identification card, the mathematical expectation of time consumption using the witness-in-check strategy described herein is:
total time to verify
Identity card reading time + face snapshot time + matching time
Identification card reading time + (probability of direct hit to cache + probability of active snapshot without hit) + matching time
=0.8+(0.9*0+0.1*0.5)+0.2
=1.05s
In total verification time, the people-evidence-in-one verification strategy optimizes about 33% compared with the existing people-evidence-in-one verification strategy, so that the user interaction time of about 1 second can be reached, the user can be basically used without blocking, and the people-evidence-in-one efficiency can be greatly improved.
According to the person-certificate-in-one verification method provided by the embodiment of the invention, the real-time face image is cached in advance, and the face comparison is carried out on the cached real-time face image and the certificate face image, so that the verification efficiency is high, the speed is high, and the user experience is good.
Illustratively, the human authentication-verification method according to the embodiment of the present invention may be implemented in a device, apparatus or system having a memory and a processor.
The witness verification method according to the embodiment of the invention can be deployed at an image acquisition end, for example, at the image acquisition end of an access management system or at the image acquisition end of a security monitoring system at a place such as a station, a hotel, a bank, and the like. Alternatively, the testimonial verification method according to the embodiment of the invention can also be distributively deployed at the server side (or the cloud side) and the client side. For example, a real-time face image can be collected at the client and a certificate face image can be obtained, the client transmits the collected real-time face image and the certificate face image to the server (or the cloud), and the server (or the cloud) performs people authentication verification.
In one example, the result (hereinafter, referred to as a cache check result) indicating whether the human verification is successful or not obtained in step S250 may be directly used as the final check result. Preferably, if the cached verification result is that the verification-verification failure occurs, further verification can be continued based on the real-time face image acquired after the certificate face image is acquired. In addition, if the cached face image meeting the preset requirement is not found in step S240, the verification may also be continued based on the real-time face image acquired after the certificate face image is acquired.
According to the embodiment of the present invention, step S240 may further include: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; the method 200 may further include: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Similarly to the cache check result, the real-time check result may be understood as information indicating whether the human verification is successful. Because it takes a little time to search the cached face image in the image cache library, the time when all cached face images are searched and the cached face image which meets the preset requirement does not exist is found to possibly have a certain time difference with the time when the certificate face image is acquired. If the real-time face image acquired within the time difference is already stored, for example, in the above-mentioned image cache library or another storage space, the time when the certificate face image is acquired can be used as the initial time for searching. If the real-time face image acquired within the time difference is not completely stored, the current time can be used as the initial searching time. Of course, there may be other suitable setting manners for searching the initial time, which may be determined according to the needs, and the present invention is not limited thereto.
The length of the preset search time period may be any length, and may be the same as or different from the length of the preset cache time period. For example, the length of the preset seek period may be 8 seconds. For example, each real-time face image can be checked one by one from the beginning of searching, if a real-time face image meeting the preset requirement is found in the 5 th second, the face in the real-time face image can be matched with the face in the certificate face image, and whether the person-certificate-in-one verification is successful or not is determined according to the matching result; and if no real-time face image meeting the preset requirement is found up to the 8 th second, determining that the person-certificate-integration verification fails.
Under the condition that a cached face image meeting preset requirements does not exist, the verification success rate can be improved by continuously performing verification based on a real-time face image acquired after the certificate face image, so that the condition that the verification fails due to the fact that the face is grabbed in advance is made up.
According to the embodiment of the present invention, step S250 may further include: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the method 200 may further include: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
As described above, in the case where the cache verification result is a failure of the integrated verification, the verification may be continued based on the real-time face image acquired after the certificate face image is acquired. The implementation of this embodiment can be understood with reference to the previous embodiment, which is not described herein again.
The above embodiment is described below with reference to fig. 3. FIG. 3 shows a schematic diagram of a person-to-verify-check flow, according to one embodiment of the invention.
As shown in fig. 3, the image capturing device continuously performs face snapshot and caches the obtained real-time face image. In the example of fig. 3, the preset buffering period is 5 seconds. In the example of fig. 3, the cache comparison hit is to determine whether a cache face image in which a face included in the cache face image matches a face in the certificate face image exists, if so, the verification is successful, and if not, the real-time face image behind the certificate face image is continuously acquired. The comparison hit is to judge whether a real-time face image matched with the face in the face image of the certificate exists, if so, the verification is successful, and if not, the verification is failed.
In one example, if it is determined that the human-authentication-one-verification failure is performed at the first verification based on the real-time face image acquired after the certificate face image, such a result may be taken as a final verification result, i.e., it is directly determined that the human-authentication-one-verification failure. Illustratively, the method 200 may further include: and determining the real-time checking result as a final checking result.
In another example, the person-authentication-one-authentication failure is finally determined only if the obtained real-time authentication results are all person-authentication-one-authentication failures after the authentication is performed on the basis of the real-time face image acquired after the certificate face image for a plurality of times.
According to the embodiment of the present invention, step S280 may further include: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290 may further include: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
The threshold number may be any suitable value, which may be set as desired, and the invention is not limited thereto. For example, the number threshold may be 3.
The verification failure times refer to the times that the real-time verification result is a verification failure. For example, if step S280 is further performed after step S270 is performed for the first time and a conclusion that the human verifies that the verification is successful is reached, it may be directly used as the final verification result. After the first execution of step S270, step S270 may be executed again, regardless of whether the conclusion of the human authentication-verification failure is obtained from step S280 or step S290. After the results of the 3 human-authentication-one-check failures are continuously obtained (correspondingly, the step S270 is continuously performed 3 times), the conclusion of the human-authentication-one-check failure can be taken as the final check result, regardless of whether the conclusion is obtained from the step S280 or the step S290.
It should be understood that the search starting time is different each time step S270 is re-executed, and needs to be determined according to the current time.
The way of checking based on the real-time face image acquired after the certificate face image can be repeated
Further improving the success rate of the verification.
According to the embodiment of the invention, the real-time face image acquired after the initial searching time can comprise a cached face image cached after the initial searching time.
Since the real-time face image is continuously cached, for example, in the image cache library, the required real-time face image obtained after the initial searching time can be directly selected from the cache image library.
In another embodiment, if the cached face image meeting the preset requirement is not found, the new real-time face image sent by the image acquisition device may be received again instead of being selected from the image cache library. And then, taking the newly acquired real-time face image as the real-time face image acquired after the initial searching time.
According to another aspect of the present invention, a human authentication verification apparatus is provided. FIG. 4 shows a schematic block diagram of a witness verification apparatus 400, in accordance with one embodiment of the present invention.
As shown in fig. 4, the human-certificate-in-one verification apparatus 400 according to the embodiment of the present invention includes a real-time face image obtaining module 410, a cache module 420, a certificate face image obtaining module 430, a cache image searching module 440, and a cache verification module 450. The various modules may perform the various steps/functions of the witness-verification method described above in connection with fig. 2 and 3, respectively. Only the main functions of the respective components of the human authentication-verification apparatus 400 will be described below, and the details that have been described above will be omitted.
The real-time facial image acquiring module 410 is configured to acquire a real-time facial image of a user to be authenticated, which is acquired by the image acquisition device in real time. The real-time facial image acquisition module 410 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The caching module 420 is configured to cache a real-time face image acquired in a preset caching period before the current time. The cache module 420 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The certificate face image acquisition module 430 is used for acquiring a certificate face image of a user to be authenticated. The credential facial image acquisition module 430 can be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The cache image searching module 440 is configured to search for a cache face image meeting a preset requirement from the cache face images cached in a preset cache period before the certificate face image is acquired, and if the cache face image meeting the preset requirement is found, start the cache verification module 450. The cached image lookup module 440 can be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The cache verification module 450 is configured to match the face in the searched cache face image with the face in the certificate face image, and determine whether the people-certificate-integrated verification is successful. The cache verification module 450 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
Exemplarily, the apparatus further includes a real-time image searching module, a real-time verification module, and a failure determination module (not shown), wherein the cache image searching module 440 further includes a first time determination sub-module, configured to, if a cache face image meeting preset requirements is not found, take a time at which the certificate face image is acquired or a current time as a search starting time and start the real-time image searching module; or the cache verification module 450 further comprises a second time determination sub-module, configured to, if the person-certificate-based verification fails, take the time at which the certificate face image is acquired or the current time as a search start time and start the real-time image search module; the real-time image searching module is used for searching a real-time face image meeting preset requirements from the real-time face images acquired after the searching starting time, if the real-time face image meeting the preset requirements is searched from the real-time face images acquired in a preset searching time period after the searching starting time, the real-time checking module is started, and if the real-time face image meeting the preset requirements is not searched from the real-time face images acquired in the preset searching time period after the searching starting time, the failure determining module is started; the real-time checking module is used for matching the face in the searched real-time face image with the face in the certificate face image and judging whether the person-certificate-integrated checking is successful or not so as to obtain a real-time checking result; the failure determination module is used for determining the person-certificate-based verification failure so as to obtain a real-time verification result.
Exemplarily, the real-time verification module further includes a first counting submodule and a first count judgment submodule, wherein the first counting submodule is configured to count the number of times of the verification failure if the real-time verification result is that the verification failure is a verification failure; the first time judgment submodule is used for judging whether the times of the check failures reach a time threshold value, if the times of the check failures do not reach the time threshold value, the current time is used as the search starting time and a real-time check module is started, and if the times of the check failures reach the time threshold value, the real-time check result is determined to be a final check result; and/or the failure determining module further comprises a second counting submodule and a second secondary number judging submodule, wherein the second counting submodule is used for counting the times of the verification failure; the second time judgment submodule is used for judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, the current time is used as the search starting time, the real-time verification module is started, and if the times of the verification failures reach the time threshold value, the real-time verification result is determined to be the final verification result.
Illustratively, the apparatus 400 further comprises: and a final result determining module (not shown) for determining the real-time verification result as a final verification result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the apparatus 400 further comprises: and a deleting module (not shown) for deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
FIG. 5 shows a schematic block diagram of a witness verification system 500, in accordance with one embodiment of the present invention. The witness verification system 500 includes an image capture device 510, a storage device 520, and a processor 530.
The image capturing device 510 is used for capturing real-time face images. The image capture device 510 is optional and the witness verification system 500 may not include the image capture device 510. In this case, other image acquisition devices may be used to acquire the real-time face image and send the acquired real-time face image to the integrated authentication and verification system 500.
The storage 520 stores computer program instructions for implementing the corresponding steps in the witness-verification method according to an embodiment of the present invention.
The processor 530 is configured to run the computer program instructions stored in the storage device 520 to execute the corresponding steps of the human-image-authentication and verification method according to the embodiment of the present invention, and is configured to implement the real-time human face image obtaining module 410, the cache module 420, the certificate human face image obtaining module 430, the cache image searching module 440, and the cache verification module 450 in the human-image-authentication and verification device 400 according to the embodiment of the present invention.
In one embodiment, the computer program instructions, when executed by the processor 530, are for performing the steps of: step S210: acquiring a real-time face image of a user to be authenticated, acquired in real time by an image acquisition device 510; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
Illustratively, the step S240 for execution by the computer program instructions when executed by the processor 530 further comprises: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; or step S250 for execution when the computer program instructions are executed by the processor 530 further comprises: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the computer program instructions when executed by the processor 530 are further operable to perform the steps of: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Illustratively, the step S280 for execution by the computer program instructions when executed by the processor 530 further comprises: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290, executed by the processor 530, of the computer program instructions further comprises: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
Illustratively, the computer program instructions when executed by the processor 530 are further operable to perform the steps of: and determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the computer program instructions when executed by the processor 530 are further operable to perform the steps of: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image containing background information acquired by the image acquisition device 510.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on an original-size face image containing background information acquired by the image acquisition device 510.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
Furthermore, according to an embodiment of the present invention, there is also provided a storage medium on which program instructions are stored, which when executed by a computer or a processor are used for executing the corresponding steps of the human authentication-integration verification method according to an embodiment of the present invention, and for implementing the corresponding modules in the human authentication-integration verification apparatus according to an embodiment of the present invention. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a portable compact disc read only memory (CD-ROM), a USB memory, or any combination of the above storage media.
In one embodiment, the program instructions, when executed by a computer or a processor, may cause the computer or the processor to implement the respective functional modules of the human authentication-verification apparatus according to the embodiment of the present invention and/or may perform the human authentication-verification method according to the embodiment of the present invention.
In one embodiment, the program instructions are operable when executed to perform the steps of: step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device; step S220: caching a real-time face image acquired in a preset caching time period before the current moment; step S230: acquiring a certificate face image of a user to be authenticated; step S240: searching a cached face image meeting preset requirements from cached face images cached in a preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
Illustratively, the step S240 for execution of the program instructions when running further comprises: if the cached face image meeting the preset requirement is not found, the moment when the certificate face image is obtained or the current moment is taken as the search starting moment and the step S270 is carried out; or the step S250 for execution when the program instructions are executed further includes: if the person-certificate-integrated verification fails, the moment when the face image of the certificate is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out; the program instructions are further operable when executed to perform the steps of: step S270: searching for a real-time face image meeting a preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290; step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and step S290: and determining that the person-certificate-based verification fails to obtain a real-time verification result.
Illustratively, the step S280 for execution of the program instructions when running further comprises: if the real-time verification result is that the one-time verification fails, counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as a search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining the real-time verification result as a final verification result; and/or step S290, executed by the program instructions when executed, further comprises: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold, if the times of the verification failures do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold, determining that the real-time verification result is the final verification result.
Illustratively, the program instructions are further operable when executed to perform the steps of: and determining the real-time checking result as a final checking result.
Illustratively, the real-time face image acquired after the search start time includes a cached face image cached after the search start time.
Illustratively, the program instructions are further operable when executed to perform the steps of: and deleting the cached face image of which the difference between the acquisition time and the current time exceeds a preset caching time period.
Illustratively, the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
Illustratively, the real-time face image is an original-size face image which contains background information and is acquired by the image acquisition device.
Illustratively, the real-time face image is a face image obtained after face extraction is performed on a face image of an original size containing background information acquired by an image acquisition device.
Illustratively, a credential is one of the following: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
The modules in the testimonial-to-testimonial verification system according to the embodiment of the present invention may be implemented by a processor of the electronic device implementing the testimonial-to-testimonial verification according to the embodiment of the present invention running computer program instructions stored in a memory, or may be implemented when computer instructions stored in a computer-readable storage medium of a computer program product according to the embodiment of the present invention are run by a computer.
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the foregoing illustrative embodiments are merely exemplary and are not intended to limit the scope of the invention thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the scope or spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as set forth in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another device, or some features may be omitted, or not executed.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the method of the present invention should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where such features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some of the blocks in a witness verification device according to embodiments of the present invention. The present invention may also be embodied as apparatus programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the specific embodiment of the present invention or the description thereof, and the protection scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (13)
1. A testimony-human-identity verification method comprises the following steps:
step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device;
step S220: caching a real-time face image acquired in a preset caching time period before the current moment;
step S230: acquiring a certificate face image of the user to be authenticated;
step S240: searching a cached face image meeting preset requirements from cached face images cached in the preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and
step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
2. The method of claim 1, wherein the step S240 further comprises: if the cached face image meeting the preset requirement is not found, taking the moment when the certificate face image is obtained or the current moment as a search starting moment and turning to the step S270; or the step S250 further includes: if the person-certificate-integrated verification fails, the moment when the certificate face image is acquired or the current moment is taken as the search starting moment, and the step S270 is carried out;
the method further comprises the following steps:
step S270: searching for a real-time face image meeting the preset requirement from the real-time face images acquired after the search starting time, if the real-time face image meeting the preset requirement is searched for from the real-time face images acquired within a preset search time period after the search starting time, going to step S280, and if the real-time face image meeting the preset requirement is not searched for from the real-time face images acquired within the preset search time period after the search starting time, going to step S290;
step S280: matching the face in the searched real-time face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful or not so as to obtain a real-time verification result; and
step S290: and determining that the person-certificate-based verification fails to obtain the real-time verification result.
3. The method of claim 2, wherein,
the step S280 further includes: if the real-time verification result is a person-to-person verification failure, counting the times of the verification failure, and judging whether the times of the verification failure reach a time threshold, if the times of the verification failure do not reach the time threshold, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failure reach the time threshold, determining that the real-time verification result is a final verification result; and/or
The step S290 further includes: counting the times of the verification failures, judging whether the times of the verification failures reach a time threshold value, if the times of the verification failures do not reach the time threshold value, taking the current time as the search starting time and returning to the step S270, and if the times of the verification failures reach the time threshold value, determining that the real-time verification result is the final verification result.
4. The method of claim 2, wherein the method further comprises:
and determining the real-time checking result as a final checking result.
5. The method of claim 2, wherein the real-time facial image acquired after the seek start time comprises a cached facial image cached after the seek start time.
6. The method of claim 1, wherein the method further comprises:
and deleting the cached face image of which the difference between the acquisition time and the current time exceeds the preset caching time period.
7. The method of claim 1, wherein the preset requirements include one or more of: the shielding degree of the face in the face image does not exceed a shielding threshold, the deflection angle of the face in the face image does not exceed an angle threshold, the blurring degree of the face image is lower than a blurring threshold, the face in the face image is not closed, and the exposure degree of the face image is in a preset exposure range.
8. The method of claim 1, wherein the real-time facial image is an original-size facial image collected by the image collection device that contains background information.
9. The method of claim 1, wherein the real-time face image is a face image obtained after face extraction is performed on an original-size face image containing background information acquired by the image acquisition device.
10. The method of claim 1, wherein the credential is one of: identity cards, employee's cards, social security cards, access cards, passports, and driver's licenses.
11. A human-certificate integrated verification device comprises a real-time face image acquisition module, a cache module, a certificate face image acquisition module, a cache image searching module and a cache verification module, wherein,
the real-time face image acquisition module is used for acquiring a real-time face image of a user to be authenticated, which is acquired by the image acquisition device in real time;
the cache module is used for caching the real-time face image acquired in a preset cache time period before the current moment;
the certificate face image acquisition module is used for acquiring a certificate face image of the user to be authenticated;
the cache image searching module is used for searching a cache face image meeting a preset requirement from cache face images cached in the preset cache time period before the certificate face image is acquired, and if the cache face image meeting the preset requirement is searched, the cache verification module is started;
the cache checking module is used for matching the face in the searched cache face image with the face in the certificate face image and judging whether the person-certificate-integrated checking is successful or not.
12. A witness unified verification system comprising an image acquisition device, a processor and a memory, wherein the memory has stored therein computer program instructions which, when executed by the processor, are adapted to perform the steps of:
step S210: acquiring a real-time face image of a user to be authenticated, which is acquired by the image acquisition device in real time;
step S220: caching a real-time face image acquired in a preset caching time period before the current moment;
step S230: acquiring a certificate face image of the user to be authenticated;
step S240: searching a cached face image meeting preset requirements from cached face images cached in the preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and
step S250: matching the face in the searched cache face image with the face in the certificate face image, and judging whether the person-certificate-integrated verification is successful.
13. A storage medium having stored thereon program instructions which when executed are for performing the steps of:
step S210: acquiring a real-time face image of a user to be authenticated, which is acquired in real time by an image acquisition device;
step S220: caching a real-time face image acquired in a preset caching time period before the current moment;
step S230: acquiring a certificate face image of the user to be authenticated;
step S240: searching a cached face image meeting preset requirements from cached face images cached in the preset caching time period before the certificate face image is acquired, and if the cached face image meeting the preset requirements is searched, turning to the step S250; and
step S250: matching the face in the searched cache face image with the face in the certificate face image to determine whether the person-certificate-integrated check is successful.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710692598.9A CN108875478B (en) | 2017-08-14 | 2017-08-14 | People-authentication-integrated verification method, device and system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710692598.9A CN108875478B (en) | 2017-08-14 | 2017-08-14 | People-authentication-integrated verification method, device and system and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108875478A CN108875478A (en) | 2018-11-23 |
CN108875478B true CN108875478B (en) | 2022-04-12 |
Family
ID=64325450
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710692598.9A Active CN108875478B (en) | 2017-08-14 | 2017-08-14 | People-authentication-integrated verification method, device and system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108875478B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008664A (en) * | 2018-12-04 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Authentication information acquisition, account-opening method, device and electronic equipment |
CN109840407A (en) * | 2018-12-24 | 2019-06-04 | 航天信息股份有限公司 | Intelligent personnel's verification system and method |
CN109685018A (en) * | 2018-12-26 | 2019-04-26 | 深圳市捷顺科技实业股份有限公司 | A kind of testimony of a witness method of calibration, system and relevant device |
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 |
CN112241674A (en) * | 2019-07-19 | 2021-01-19 | 北京创璞科技有限公司 | Face recognition method and system |
CN110675539B (en) * | 2019-09-26 | 2022-08-12 | 深圳市商汤科技有限公司 | Identity verification method and device, electronic equipment and storage medium |
CN111931808B (en) * | 2020-06-28 | 2024-04-16 | 深圳市金溢科技股份有限公司 | RFID data and image data matching method, main control equipment and system |
CN112434196A (en) * | 2020-12-01 | 2021-03-02 | 深圳市血之缘医疗科技有限公司 | Gift card issuing method and device, card issuing terminal and storage medium |
CN114357419A (en) * | 2022-01-05 | 2022-04-15 | 厦门熵基科技有限公司 | Face verification method and device, storage medium and computer equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103559485A (en) * | 2013-11-08 | 2014-02-05 | 广州广电运通金融电子股份有限公司 | Identity authentication method and device based on remote bank VTM |
CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
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 |
CN106203553A (en) * | 2016-07-18 | 2016-12-07 | 北京红马传媒文化发展有限公司 | A kind of certificate recognition methods, device and a kind of equipment |
CN206147663U (en) * | 2016-08-19 | 2017-05-03 | 北京旷视科技有限公司 | Authentication system based on face identification |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5147426B2 (en) * | 2008-01-25 | 2013-02-20 | 日立オムロンターミナルソリューションズ株式会社 | Cash transaction system |
GB2500823B (en) * | 2013-03-28 | 2014-02-26 | Paycasso Verify Ltd | Method, system and computer program for comparing images |
CN105447532A (en) * | 2015-03-24 | 2016-03-30 | 北京天诚盛业科技有限公司 | Identity authentication method and device |
-
2017
- 2017-08-14 CN CN201710692598.9A patent/CN108875478B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103559485A (en) * | 2013-11-08 | 2014-02-05 | 广州广电运通金融电子股份有限公司 | Identity authentication method and device based on remote bank VTM |
CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
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 |
CN106203553A (en) * | 2016-07-18 | 2016-12-07 | 北京红马传媒文化发展有限公司 | A kind of certificate recognition methods, device and a kind of equipment |
CN206147663U (en) * | 2016-08-19 | 2017-05-03 | 北京旷视科技有限公司 | Authentication system based on face identification |
Also Published As
Publication number | Publication date |
---|---|
CN108875478A (en) | 2018-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108875478B (en) | People-authentication-integrated verification method, device and system and storage medium | |
US11113514B2 (en) | Identity verification methods, systems, apparatuses, and devices | |
CN106599772B (en) | Living body verification method and device and identity authentication method and device | |
US10949952B2 (en) | Performing detail enhancement on a target in a denoised image | |
CN109117714B (en) | Method, device and system for identifying fellow persons and computer storage medium | |
CN108804884B (en) | Identity authentication method, identity authentication device and computer storage medium | |
CN108875732B (en) | Model training and instance segmentation method, device and system and storage medium | |
US8724856B1 (en) | Method, system and computer program for comparing images | |
CN106899567B (en) | User body checking method, device and system | |
CN111886842B (en) | Remote user authentication using threshold-based matching | |
KR20190072563A (en) | Method and apparatus for detecting facial live varnish, and electronic device | |
CN108875341A (en) | A kind of face unlocking method, device, system and computer storage medium | |
US9049379B2 (en) | Apparatus and method for recognizing image | |
CN108875484B (en) | Face unlocking method, device and system for mobile terminal and storage medium | |
CN108875481B (en) | Method, device, system and storage medium for pedestrian detection | |
CN110750670B (en) | Stranger monitoring method, device and system and storage medium | |
CN108959884B (en) | Human authentication verification device and method | |
CN106203425B (en) | Character recognition method and device | |
CN110263680B (en) | Image processing method, device and system and storage medium | |
CN112307817B (en) | Face living body detection method, device, computing equipment and computer storage medium | |
CN110991231B (en) | Living body detection method and device, server and face recognition equipment | |
WO2020070821A1 (en) | Biometric identification device, biometric identification method, and biometric identification program | |
CN108875512B (en) | Face recognition method, device, system, storage medium and electronic equipment | |
CN110031697B (en) | Method, device, system and computer readable medium for testing target identification equipment | |
CN107679457A (en) | User identity method of calibration and device |
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 |