CN112069878A - Target object legality judging method and device and electronic equipment - Google Patents
Target object legality judging method and device and electronic equipment Download PDFInfo
- Publication number
- CN112069878A CN112069878A CN202010707941.4A CN202010707941A CN112069878A CN 112069878 A CN112069878 A CN 112069878A CN 202010707941 A CN202010707941 A CN 202010707941A CN 112069878 A CN112069878 A CN 112069878A
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- target
- video stream
- body detection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000001514 detection method Methods 0.000 claims abstract description 116
- 238000001727 in vivo Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 230000000977 initiatory effect Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
- G07F19/20—Automatic teller machines [ATMs]
- G07F19/207—Surveillance aspects at ATMs
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention provides a method and a device for judging the legality of a target object and electronic equipment, wherein the method comprises the following steps: acquiring a video stream containing a target object; performing at least one identification and/or at least one living body detection on at least one frame of image in the video stream until whether the target object is legal is judged; the identity recognition of different times aims at different frame images, the living body detection of different times aims at different frame images, and the frame images aimed at by the identity recognition and the living body detection are the same or different. The method can effectively improve the accuracy of judging the legality of the target object.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for determining validity of a target object, and an electronic device.
Background
In order to ensure safety, the validity judgment of personnel is involved in many occasions, and the personnel who are judged to be legal (namely, meet the requirement) are allowed to do follow-up things, such as the legal personnel (such as the personnel with the right of passage) are allowed to pass through the entrance guard in the entrance guard occasion; in a bank ATM (Automatic Teller Machine), legitimate persons (card owners such as bank cards) are allowed to perform operations such as withdrawal; in a partial APP (Application), a legitimate person (such as an APP member) is allowed to use a partial function of the APP. In the existing legality judging method, misjudgment conditions often exist, and the judging accuracy is not high.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for determining validity of a target object, and an electronic device, which can effectively improve accuracy of determining validity of the target object.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides a method for determining validity of a target object, including: acquiring a video stream containing a target object; performing at least one identification and/or at least one living body detection on at least one frame of image in the video stream until judging whether the target object is legal or not; wherein different times of identification are directed to different frame images.
Further, the step of judging whether the target object is legal includes: if the first specified number of identification results pass and the second specified number of living body detection results pass, determining that the target object is legal; the method comprises the steps of identifying the identity of a user, wherein each time of identity identification correspondingly generates an identity identification result, and each time of in vivo detection correspondingly generates an in vivo detection result; and if the frame images participating in the identification and/or the live body detection reach a third specified number or the frame images in the video stream both participate in the identification and/or the live body detection, determining that the target object is illegal, wherein the passing number of the identification result still does not reach the first specified number or the passing number of the live body detection result still does not reach the second specified number.
Further, the step of performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream comprises: selecting a frame of image from the video stream as a target image; if the target image is the first frame image selected from the video stream, respectively carrying out identity recognition and living body detection on the target image; if the target image is not the first frame image selected from the video stream, counting a first passing number of an identity recognition result and a second passing number of a living body detection result which are obtained before the target image, determining a target operation corresponding to the target image according to the first passing number and the second passing number, and executing the target operation on the target image; the target operation comprises identification and/or living body detection; and if the target object is not judged to be legal, continuously selecting a frame image from the video stream as a target image, and executing target operation corresponding to the target image until the frame image is stopped being selected from the video stream when the judgment result of the legality of the target object is obtained.
Further, the step of determining a target operation corresponding to the target image according to the first number of passes and the second number of passes includes: if the first passing number does not reach a preset first threshold value, determining that the target operation corresponding to the target image comprises identity recognition; and if the second pass number does not reach a preset second threshold, determining that the target operation corresponding to the target image comprises living body detection.
Further, before performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream, the method further comprises: selecting a preset number of frame images from the video stream, and forming a target image set by the preset number of frame images; the step of performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream comprises: at least one identification and/or at least one liveness detection is performed on at least one image of the target image set.
Further, the method further comprises: and if the target object is judged to be legal, providing specified service for the target object.
Further, the method further comprises: and if the target object is judged to be illegal, initiating a warning prompt.
In a second aspect, an embodiment of the present invention further provides an apparatus for determining validity of a target object, including: the acquisition module is used for acquiring a video stream containing a target object; the judging module is used for carrying out at least one time of identity recognition and/or at least one time of living body detection on at least one frame of image in the video stream until judging whether the target object is legal or not; wherein, different times of identification are aimed at different frame images, and different times of living body detection are aimed at different frame images.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a processor and a storage device; the storage means has stored thereon a computer program which, when executed by the processor, performs the method of any of the first aspects.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps of the method according to any one of the above first aspects.
The embodiment of the invention provides a method and a device for judging the legality of a target object and electronic equipment, which are used for acquiring a video stream containing the target object; performing at least one identification and/or at least one living body detection on at least one frame of image in the video stream until whether the target object is legal is judged; wherein, different times of identification are aimed at different frame images, and different times of living body detection are aimed at different frame images. By the method, the frame images in the video stream can be subjected to identity recognition and in-vivo detection, the identity recognition and in-vivo detection can be respectively carried out on different frame images, and the identity recognition and in-vivo detection can be simultaneously carried out on the same frame image.
Additional features and advantages of embodiments of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of the invention as set forth above.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for determining validity of a target object according to an embodiment of the present invention;
fig. 3 shows a flowchart of a method for determining a right of way according to an embodiment of the present invention;
fig. 4 is a block diagram illustrating a structure of an apparatus for determining validity of a target object according to an embodiment of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, not all, embodiments of the present invention.
In the prior art, when the legality of a person is judged, a password judgment mode is traditionally adopted, if the password is correct, the person is determined to be legal, but because the password is easy to leak, an image judgment mode is gradually adopted nowadays, such as acquiring an image, and then performing identity verification through a face recognition mode. However, this method is easily affected by the image quality or the shooting angle of the person, such as when the shot image is blurred, or the person in the image is at an angle which is not easy to recognize, such as a head-down or side face, the erroneous judgment phenomenon is very easy to occur, so that the person who should be legal is erroneously judged to be illegal, which affects the user experience, or the person who should be illegal is erroneously judged to be legal, which causes a potential safety hazard. Based on this, the embodiment of the invention provides a method and a device for judging the legality of a target object and electronic equipment, which can effectively improve the legality judgment accuracy of the target object and reduce the probability of occurrence of misjudgment. The technology can be applied to occasions where the legality of the target object needs to be judged, such as intelligent terminals of access control systems, bank ATM machines and the like, and the embodiment of the invention is described in detail below.
The first embodiment is as follows:
first, an exemplary electronic device 100 for implementing a method, an apparatus, and an electronic device for legitimacy determination of a target object according to an embodiment of the present invention is described with reference to fig. 1.
As shown in fig. 1, an 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 type 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 implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), the processor 102 may be one or a combination of several of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), or other forms of processing units 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 or sounds) to the outside (e.g., a user), and may include one or more of a display, a speaker, and the like.
The image capture device 110 may take images (e.g., photographs, videos, etc.) desired by the user and store the taken images in the storage device 104 for use by other components.
Exemplary electronic devices for implementing the method and apparatus for legitimacy determination of a target object according to the embodiments of the present invention may be implemented as smart terminals such as an access control system, an ATM machine, a safe, a smart phone, a tablet computer, a computer, and the like.
Example two:
referring to a flowchart of a method for determining the validity of a target object shown in fig. 2, the method may be executed by the electronic device in the foregoing embodiment, and mainly includes the following steps S202 to S204:
in step S202, a video stream containing the target object is acquired.
In practical applications, for example, a camera arranged at a designated position may be used to collect a video in real time, and a video stream containing a target object is determined based on a target detection algorithm, that is, the target object is present in all frame images contained in the obtained video stream. The target object in this embodiment is mainly a person.
For convenience of understanding, firstly, an access control system is taken as an example for explanation, a camera of the access control system may be installed at an access control entrance, and the camera may be right opposite to a direction in which a target object moves toward the access control, so that a front view of the target object may be taken, and when it is detected that a target object appears, a video stream including the target object is obtained. Taking a bank ATM as an example, the camera may be disposed above the ATM and may be configured to capture the face of the object, and if the electronic device implementing the embodiment is a mobile phone, the camera of the mobile phone may be directly used to capture a video stream including a human face.
Step S204, at least one time of identity recognition and/or at least one time of living body detection are carried out on at least one frame of image in the video stream until whether the target object is legal or not is judged; the identity recognition of different times aims at different frame images, the living body detection of different times aims at different frame images, and the frame images aimed at by the identity recognition and the living body detection are the same or different.
In this embodiment, the legitimacy determination operation of the target object may be performed on one or more frames of images in the video stream containing the target object until whether the target object is legitimate is determined (that is, the legitimacy determination result of the target object is obtained). In the above-described mode, the identification and the live body detection can be performed for different frame images, respectively, or for the same frame image.
The method for judging the legality of the target object provided by the embodiment of the invention can be used for carrying out identity recognition and living body detection on the frame images in the video stream, respectively carrying out identity recognition and living body detection on different frame images, and simultaneously carrying out identity recognition and living body detection on the same frame image.
The embodiment provides a specific implementation manner for judging whether a target object is legal or not: if the first specified number of identification results pass and the second specified number of living body detection results pass, determining that the target object is legal; the method comprises the steps of identifying the identity of a user, wherein each time of identity identification correspondingly generates an identity identification result, and each time of in vivo detection correspondingly generates an in vivo detection result; and if the frame images participating in the identification and/or the live body detection reach the third specified number or the frame images in the video stream both participate in the identification and/or the live body detection, determining that the passing number of the identification result does not reach the first specified number or the passing number of the live body detection result does not reach the second specified number, and determining that the target object is illegal. In practical application, the identification can be performed by a face recognition technology, if the identification result does not pass, the target object is indicated as a person not recorded in the system, and if the living body detection result does not pass, the target object is indicated as a living body attack object, such as the target object is a person wearing a headgear.
In practical applications, the first designated number, the second designated number and the third designated number may be flexibly set according to requirements, and the first designated number and the second designated number may be the same or different, such as setting both the first designated number and the second designated number to 1 and setting the third designated number to 3. This can be performed with reference to one of two embodiments:
the first embodiment: selecting a frame of image from the video stream, respectively performing identification and live body detection on the frame of image, if both the frame of image and the frame of image pass, determining that a target object in the video stream is legal, if one frame of image does not pass (assuming that the identification result does not pass), selecting a second frame of image from the video stream, performing identification only on the second frame of image, if the identification result of the second frame of image passes, determining that the target object in the video stream is legal, if the identification result of the second frame of image still does not pass, selecting a third frame of image from the video stream, performing identification on the third frame of image, if the identification result of the third frame of image passes, determining that the target object in the video stream is legal, if the identification result of the third frame of image still does not pass, at this time, the extracted frame of image (i.e. the frame of image participating in identification/live body detection) has reached a third specified number (3), therefore, the frame images are not continuously extracted, and the target object in the video stream is directly judged to be illegal.
The second embodiment: the method comprises the steps of directly selecting three frames of images from a video stream, carrying out identity recognition and live body detection on the three frames of images, determining that a target object is legal if at least one identity recognition result passes through and at least one live body detection result passes through, and determining that the target object is illegal if the identity recognition results do not pass through (namely, the first specified number 1 is not reached) or the live body detection results do not pass through (namely, the second specified number 1 is not reached).
The above is merely an example, and should not be considered as a limitation, and in practical applications, the numerical values of the first specified number and the second specified number may also be set to be greater than 1 to ensure the safety and reliability of the validity determination.
Since the first embodiment requires less processing amount and can determine whether the target object is legal or not more quickly than the second embodiment, taking the first embodiment as an example, the step of performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream in the present embodiment can be implemented with reference to the following steps (1) to (4):
(1) and selecting a frame of image from the video stream as a target image. In practical applications, the frame images may be selected from the video stream in time sequence, or the frame images may be selected according to the degree of sharpness of the target object in the frame images in the video stream, or the frame images may be selected according to the face proportion of the target object in the frame images, or the next frame image may be selected according to the position of the previously selected frame image in the video stream (such as a specified interval from the previous frame image), which is not limited herein.
(2) And if the target image is the first frame image selected from the video stream, respectively carrying out identity recognition and living body detection on the target image. If the target image is the first frame image selected from the video stream (i.e. the first selected frame image), the identification and the living body detection can be directly performed on the target image.
(3) And if the target image is not the first frame image selected from the video stream, counting a first passing number of the identification result and a second passing number of the living body detection result which are obtained before the target image, and determining the target operation corresponding to the target image according to the first passing number and the second passing number. And executing target operation on the target image; the target operation includes identification and/or liveness detection.
If the target image is not the first frame image selected from the video stream (i.e. other frame images have been selected from the video stream before the identification and/or the live body detection), it needs to be determined whether the identification or the live body detection or both needs to be performed on the target image, and specifically, the target operation corresponding to the target image can be determined according to the first pass number and the second pass number. In one embodiment, when determining the target operation corresponding to the target image according to the first pass number and the second pass number, if the first pass number does not reach a preset first threshold, determining that the target operation corresponding to the target image comprises identity recognition; and if the second pass number does not reach a preset second threshold value, determining that the target operation corresponding to the target image comprises living body detection. In practical applications, the preset first threshold may be equal to the first specified number, and the preset second threshold may be equal to the second specified number.
(4) And if the target object is not judged to be legal, continuously selecting a frame of image from the video stream as the target image, executing target operation corresponding to the target image, and stopping selecting the frame of image from the video stream until the legality judgment result of the target object is obtained.
That is, if the currently obtained identification result does not reach the first specified number or the live body detection result does not reach the second specified number, and the frame images involved in the identification and/or the live body detection do not reach the third specified number, the frame images may be continuously selected to perform the target image while the target object is not judged to be legal, and the operation in (3) may be performed on the target image until the frame image is stopped being selected when the result of judging the validity of the target object is obtained. The number of the frame images participating in the identity recognition and/or the living body detection does not exceed a third specified number, and the obtained legality judging result is that the target object is legal; and if the number of the frame images participating in the identity recognition and/or the living body detection reaches a third specified number, but the identity recognition result does not reach the first specified number or the living body detection result still does not reach the second specified number, the obtained legality judgment result is that the target object is illegal.
In practical application, one frame image to be processed can be directly selected from a video stream as a target image each time, or a third specified number of frame images can be selected from the video stream at one time to form a target image set, and then identity recognition and/or liveness detection are directly performed on the frame images in the target image set, that is, after the video stream is obtained, a preset number of frame images can be selected from the video stream in advance, the preset number of frame images form the target image set, and then at least one identity recognition and/or at least one liveness detection is performed on at least one frame image in the target image set. In this way, frame images can be selected from the video stream to form a target image set based on a preset mode at a time, then images are selected from the target image set to perform corresponding operations, and if the passing number of the identity recognition result does not reach the first specified number or the passing number of the living body detection result does not reach the second specified number after all the images in the target image set are selected, the target object is determined to be illegal. The preset manner may be to extract a specified number of images at equal time intervals, or to select a specified number of images with a higher definition rank, or to select a specified number of images with a higher ratio between the face of the target object and the whole image, and the like, which is not limited herein.
Further, if the target object is judged to be legal, the specified service is provided for the target object. The specified service can be flexibly defined according to the scene to which the validity judgment of the target object is applied. For example, the access control system may provide release services such as opening a door (or opening a door) for the target object, the smart terminal such as a mobile phone or a bank ATM may provide functional services such as withdrawing, transferring, and modifying information for the target object, and the attendance checking device may provide attendance checking services for the target object, which is not limited herein. And if the target object is judged to be illegal, initiating warning prompt. Such as initiating a voice alert or sending an alert message directly to a designated terminal.
According to the method for judging the legality of the target object, the phenomenon of single-frame misjudgment which often occurs in the prior art is avoided, identity recognition and/or in-vivo detection can be carried out on multi-frame images, the collected multi-frame images containing the target object can be effectively utilized, for example, an access control system can effectively utilize video frame images of the target object which are shot by a camera in the process of advancing towards an entrance of the access control, comprehensive judgment is carried out through multiple identity recognition results and in-vivo detection results, and the legality judging reliability of the target object is greatly guaranteed.
Example three:
on the basis of the foregoing embodiments, this embodiment provides a specific example of a method for determining validity of the target object, which is mainly described by taking an access control system as an example, and in an application scenario of the access control system, it can be considered that a legal target object has a right of passage, so determining whether the target object is legal is equivalent to determining whether the target object has the right of passage. The processor is provided with an identity recognition module and a living body detection module, the identity recognition module is used for carrying out identity recognition on an input image to obtain an identity recognition result, and the living body detection module is used for carrying out living body detection on the input image to obtain a living body detection result. In specific execution, the method can be implemented by referring to a flow chart of the method for judging the passing authority shown in fig. 3:
step S302: and selecting a first frame image from a video stream shot by a camera. In practical applications, the video stream used is a video stream containing a target object, and in a specific embodiment, a section of the video stream may be selected in units of track (track), where a section of the track is defined as: video stream from the very beginning of a face to the point where the face completely leaves the picture. For example, when a person a comes and goes toward the entrance and enters a shooting range of a camera provided at the entrance, a video shot by the person a within the shooting range of the camera may be referred to as a track, and when the person a enters the shooting range, the video is a starting point of the track, and when the person a leaves the shooting range (for example, when the person a stands at the entrance, the camera is located above the top of the person, and the person a cannot be shot again), the video is an end point of the track.
Step S304: inputting the first frame image into an identity recognition module for identity recognition to obtain an identity recognition result; and inputting the first frame image into the living body detection model for living body detection to obtain a living body detection result.
Step S306: judging whether a passing authority judgment result of a target object in the video stream is obtained or not according to the existing identity recognition result, the existing living body detection result and the number of the selected frame images; if not, go to step S308, if yes, go to step S312: for example, if the number of passes of the existing identification result does not reach the first specified number, the number of passes of the existing live body detection result does not reach the second specified number, and the number of selected frame images does not reach the preset threshold value K, it is determined that the passing right discrimination result of the target object in the video stream has not been obtained. The specific manner for determining whether the target object has the right of passage may be implemented by referring to the manner for determining whether the target object is legal in the foregoing embodiments, and details are not repeated herein.
Step S308: selecting a frame of image from the video stream, and determining a target module required to be input by the frame of image according to the previously obtained identity recognition result and the living body detection result; the target module comprises an identity recognition module and/or a living body detection module. The identity recognition module and the living body detection module are both functional modules which can be realized by software, and can be realized by adopting a neural network model, and reference can be made to related technologies, and details are not repeated here. For example, if the passing number of the existing identification results does not reach the first specified number, and if the passing number of the existing living body detection results reaches the second specified number, the target module required to be input by the newly selected frame image is determined as the living body detection module.
Step S310: and inputting the frame image into a target module to execute target operation to obtain an identity recognition result and/or a living body detection result. Then returning to execute the step S306; the target operation corresponding to the identity recognition module is identity recognition, and the target operation corresponding to the living body detection module is living body detection.
Step S312: and outputting the pass authority judgment result, and executing the operation corresponding to the pass authority judgment result. For example, when the authority discrimination result indicates that the target object has the authority, the access control system executes a door opening (or opening) operation, and when the authority discrimination result indicates that the target object has no authority, the access control system executes a non-response operation or directly executes an alarm operation.
In summary, in the above manner provided by this embodiment, the access control system can effectively utilize the video frame image of the target object in the process of moving toward the access control, and can determine whether the target object has the right of passage according to the multiple identity recognition results and/or the live body detection results, so that the determination accuracy of the right of passage can be effectively improved, and the single-frame false determination probability can be reduced.
Example four:
as to the method for determining the validity of the target object provided in the second embodiment, an embodiment of the present invention provides a device for determining the validity of the target object, referring to a block diagram of a structure of the device for determining the validity of the target object shown in fig. 4, where the device includes the following modules:
an obtaining module 402, configured to obtain a video stream including a target object;
a determining module 404, configured to perform at least one identity recognition and/or at least one liveness detection on at least one frame of image in the video stream until determining whether the target object is legal; the identity recognition of different times aims at different frame images, the living body detection of different times aims at different frame images, and the frame images aimed at by the identity recognition and the living body detection are the same or different.
The device for judging the legality of the target object provided by the embodiment of the invention can perform identity recognition and living body detection on the frame images in the video stream, can perform identity recognition and living body detection respectively aiming at different frame images, and can also perform identity recognition and living body detection simultaneously on the same frame image.
In one embodiment, the determination module 404 is configured to: if the first specified number of identification results pass and the second specified number of living body detection results pass, determining that the target object is legal; the method comprises the steps of identifying the identity of a user, wherein each time of identity identification correspondingly generates an identity identification result, and each time of in vivo detection correspondingly generates an in vivo detection result; and if the frame images participating in the identification and/or the live body detection reach the third specified number or the frame images in the video stream both participate in the identification and/or the live body detection, determining that the passing number of the identification result does not reach the first specified number or the passing number of the live body detection result does not reach the second specified number, and determining that the target object is illegal.
In one embodiment, the determination module 404 is configured to: selecting a frame of image from the video stream as a target image; if the target image is the first frame image selected from the video stream, respectively carrying out identity recognition and living body detection on the target image; if the target image is not the first frame image selected from the video stream, counting a first passing number of an identity recognition result and a second passing number of a living body detection result which are obtained before the target image, determining a target operation corresponding to the target image according to the first passing number and the second passing number, and executing the target operation on the target image; the target operation comprises identification and/or living body detection; and if the target object is not judged to be legal, continuously selecting a frame of image from the video stream as the target image, executing target operation corresponding to the target image, and stopping selecting the frame of image from the video stream until the legality judgment result of the target object is obtained.
In one embodiment, the determination module 404 is further configured to: if the first passing number does not reach a preset first threshold value, determining that the target operation corresponding to the target image comprises identity recognition; and if the second pass number does not reach the preset second threshold, determining that the target operation corresponding to the target image comprises living body detection.
In one embodiment, the above apparatus further comprises: the image selection module is used for selecting a preset number of frame images from the video stream and forming a target image set by the preset number of frame images; on this basis, the determination module 404 is configured to: the method comprises the following steps of carrying out at least one identification and/or at least one living body detection on at least one frame of image in a video stream, wherein the steps comprise: at least one identification and/or at least one liveness detection is performed on at least one image of the target image set.
In one embodiment, the above apparatus further comprises: and the service providing module is used for providing the specified service for the target object if the target object is judged to be legal.
In one embodiment, the above apparatus further comprises: and the warning module is used for initiating warning prompt if the target object is judged to be illegal.
The device provided by the embodiment has the same implementation principle and technical effect as the foregoing embodiment, and for the sake of brief description, reference may be made to the corresponding contents in the foregoing method embodiment for the portion of the embodiment of the device that is not mentioned.
Further, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, performs the steps of any of the methods described above.
The method and the device for judging the passing permission and the computer program product of the electronic device provided by the embodiment of the invention comprise a computer readable storage medium storing program codes, wherein instructions included in the program codes can be used for executing the method in the previous method embodiment, and specific implementation can be referred to the method embodiment and is not repeated herein.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A method for judging the validity of a target object, comprising:
acquiring a video stream containing a target object;
performing at least one identification and/or at least one living body detection on at least one frame of image in the video stream until judging whether the target object is legal or not; wherein, different times of identification are aimed at different frame images, and different times of living body detection are aimed at different frame images.
2. The method of claim 1, wherein the step of determining whether the target object is legitimate comprises:
if the first specified number of identification results pass and the second specified number of living body detection results pass, determining that the target object is legal; the method comprises the steps of identifying the identity of a user, wherein each time of identity identification correspondingly generates an identity identification result, and each time of in vivo detection correspondingly generates an in vivo detection result;
and if the frame images participating in the identification and/or the live body detection reach a third specified number or the frame images in the video stream both participate in the identification and/or the live body detection, determining that the target object is illegal, wherein the passing number of the identification result still does not reach the first specified number or the passing number of the live body detection result still does not reach the second specified number.
3. The method according to claim 1 or 2, wherein the step of performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream comprises:
selecting a frame of image from the video stream as a target image;
if the target image is the first frame image selected from the video stream, respectively carrying out identity recognition and living body detection on the target image;
if the target image is not the first frame image selected from the video stream, counting a first passing number of an identity recognition result and a second passing number of a living body detection result which are obtained before the target image, determining a target operation corresponding to the target image according to the first passing number and the second passing number, and executing the target operation on the target image; the target operation comprises identification and/or living body detection;
and if the target object is not judged to be legal, continuously selecting a frame image from the video stream as a target image, and executing target operation corresponding to the target image until the frame image is stopped being selected from the video stream when the judgment result of the legality of the target object is obtained.
4. The method according to claim 3, wherein the step of determining the target operation corresponding to the target image according to the first number of passes and the second number of passes comprises:
if the first passing number does not reach a preset first threshold value, determining that the target operation corresponding to the target image comprises identity recognition; and if the second pass number does not reach a preset second threshold, determining that the target operation corresponding to the target image comprises living body detection.
5. The method of claim 1, wherein prior to performing at least one identification and/or at least one liveness check on at least one image of the video stream, the method further comprises: selecting a preset number of frame images from the video stream, and forming a target image set by the preset number of frame images;
the step of performing at least one identification and/or at least one liveness detection on at least one frame of image in the video stream comprises: at least one identification and/or at least one liveness detection is performed on at least one image of the target image set.
6. The method of claim 1, further comprising:
and if the target object is judged to be legal, providing specified service for the target object.
7. The method of claim 1, further comprising:
and if the target object is judged to be illegal, initiating a warning prompt.
8. An apparatus for judging the legitimacy of a target object, comprising:
the acquisition module is used for acquiring a video stream containing a target object;
the judging module is used for carrying out at least one time of identity recognition and/or at least one time of living body detection on at least one frame of image in the video stream until judging whether the target object is legal or not; wherein, different times of identification are aimed at different frame images, and different times of living body detection are aimed at different frame images.
9. An electronic device, comprising: a processor and a storage device;
the storage device has stored thereon a computer program which, when executed by the processor, performs the method of any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of the claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010707941.4A CN112069878A (en) | 2020-07-21 | 2020-07-21 | Target object legality judging method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010707941.4A CN112069878A (en) | 2020-07-21 | 2020-07-21 | Target object legality judging method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112069878A true CN112069878A (en) | 2020-12-11 |
Family
ID=73657485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010707941.4A Pending CN112069878A (en) | 2020-07-21 | 2020-07-21 | Target object legality judging method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069878A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426723A (en) * | 2015-11-20 | 2016-03-23 | 北京得意音通技术有限责任公司 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
| US20180285628A1 (en) * | 2017-03-28 | 2018-10-04 | Samsung Electronics Co., Ltd. | Face verification method and apparatus |
| CN108875333A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | Terminal unlock method, terminal and computer readable storage medium |
| CN208225154U (en) * | 2018-05-30 | 2018-12-11 | 中海云智慧（北京）物联网科技有限公司 | A kind of smart identity cards are swiped the card opening gate system |
| CN110473311A (en) * | 2018-05-09 | 2019-11-19 | 杭州海康威视数字技术股份有限公司 | Take precautions against rogue attacks method, apparatus and electronic equipment |
| KR20200080533A (en) * | 2018-12-27 | 2020-07-07 | 주식회사 유니온커뮤니티 | Apparatus and Method for Recognizing Fake Face By Using Minutia Data Variation |
-
2020
- 2020-07-21 CN CN202010707941.4A patent/CN112069878A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
| CN105426723A (en) * | 2015-11-20 | 2016-03-23 | 北京得意音通技术有限责任公司 | Voiceprint identification, face identification and synchronous in-vivo detection-based identity authentication method and system |
| US20180285628A1 (en) * | 2017-03-28 | 2018-10-04 | Samsung Electronics Co., Ltd. | Face verification method and apparatus |
| CN108875333A (en) * | 2017-09-22 | 2018-11-23 | 北京旷视科技有限公司 | Terminal unlock method, terminal and computer readable storage medium |
| CN110473311A (en) * | 2018-05-09 | 2019-11-19 | 杭州海康威视数字技术股份有限公司 | Take precautions against rogue attacks method, apparatus and electronic equipment |
| CN208225154U (en) * | 2018-05-30 | 2018-12-11 | 中海云智慧（北京）物联网科技有限公司 | A kind of smart identity cards are swiped the card opening gate system |
| KR20200080533A (en) * | 2018-12-27 | 2020-07-07 | 주식회사 유니온커뮤니티 | Apparatus and Method for Recognizing Fake Face By Using Minutia Data Variation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805047B (en) | Living body detection method and device, electronic equipment and computer readable medium | |
| US11256902B2 (en) | People-credentials comparison authentication method, system and camera | |
| US10275684B2 (en) | Authentication method and apparatus, and method and apparatus for training a recognizer | |
| US9594958B2 (en) | Detection of spoofing attacks for video-based authentication | |
| CN110390229B (en) | Face picture screening method and device, electronic equipment and storage medium | |
| CN108875484B (en) | Face unlocking method, device and system for mobile terminal and storage medium | |
| CN110675582A (en) | Automatic alarm method and device | |
| CN107025425B (en) | Authentication method and device and method and device for training recognizer | |
| CN113780212A (en) | User identity verification method, device, equipment and storage medium | |
| CN112257124A (en) | Image processing method and device | |
| CN111866600A (en) | Method, device and system for protecting privacy | |
| CN112215037A (en) | Object tracking method and device, electronic equipment and computer readable storage medium | |
| JP2002304651A (en) | Device and method for managing entering/leaving room, program for executing the same method and recording medium with the same execution program recorded thereon | |
| CN110795715A (en) | Data entry method, device and system and storage medium | |
| CN112016509B (en) | Personnel station abnormality reminding method and device | |
| US20160180149A1 (en) | Video surveillance system and method for fraud detection | |
| CN112069878A (en) | Target object legality judging method and device and electronic equipment | |
| CN111046804A (en) | Living body detection method, living body detection device, electronic equipment and readable storage medium | |
| CN113516481B (en) | Face brushing willingness confirmation method and device and face brushing equipment | |
| KR20130062489A (en) | Device for tracking object and method for operating the same | |
| CN111144181A (en) | Risk detection method, device and system based on background collaboration | |
| CN114387674A (en) | Living body detection method, living body detection system, living body detection apparatus, storage medium, and program product | |
| JP5361014B2 (en) | Traffic monitoring system | |
| CN113705428B (en) | Living body detection method and device, electronic equipment and computer readable storage medium | |
| WO2021084895A1 (en) | A method, an apparatus and a system for managing an event to generate an alert indicating a subject is likely to be unauthorized |
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 |