WO2020007191A1 - 活体识别检测方法、装置、介质及电子设备 - Google Patents
活体识别检测方法、装置、介质及电子设备 Download PDFInfo
- Publication number
- WO2020007191A1 WO2020007191A1 PCT/CN2019/091723 CN2019091723W WO2020007191A1 WO 2020007191 A1 WO2020007191 A1 WO 2020007191A1 CN 2019091723 W CN2019091723 W CN 2019091723W WO 2020007191 A1 WO2020007191 A1 WO 2020007191A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- frame
- distance
- images
- target object
- image
- 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.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
- G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
Definitions
- the present application relates to the field of biometric technology, and in particular, to a method, device, medium, and electronic device for biometric detection.
- the existing face recognition system has added a process of biometric verification.
- the purpose of the embodiments of the present application is to provide a method, a device, a medium, and an electronic device for detecting a living body, so as to at least to some extent overcome the problem of low security of the identification system.
- a method for detecting a living body including:
- For the multi-frame images analyze changes in the multiple ratios, and determine whether the target object is a living object according to the changes in the multiple ratios.
- the determining whether the target object is a living object according to a change in the multiple ratios includes:
- the multiple ratios are input to a classifier model to obtain a classification result, and whether the target object is a living object is determined according to the classification result.
- the method further includes:
- a deep learning algorithm is used to obtain the classifier model.
- determining whether the target object is a living object according to the classification result includes:
- the target object is a non-living object.
- the acquiring a multi-frame image of a target object at a different position with respect to the acquisition camera includes:
- a reference number of frame images with different distances from the target object to the acquisition camera are acquired.
- the acquiring a multi-frame image of a target object at a different position with respect to the acquisition camera includes:
- the method further includes:
- the size of the detection frame changes.
- calculating the distance between each key point on each frame image separately includes:
- the distance from the pupil point to the nasal point on each frame of image is the first distance
- the distance from the pupil point to the corner of the mouth is the second distance
- the distance from the corner of the mouth to the tip of the nose is the third distance
- the multiple ratios of the frames of each frame of image calculated from the distances calculated based on the images of each frame include:
- the ratio of the first distance to the pupil distance is calculated as a first ratio
- the ratio of the second distance to the pupil distance is calculated as a second ratio
- the third distance and the pupil distance are calculated.
- the pupil distance ratio is a third ratio to obtain each of the first ratio, the second ratio, and the third ratio of each frame of image.
- analyzing the change of the multiple ratios for the multi-frame images includes:
- the changes of the first ratio, the second ratio, and the third ratio are analyzed separately.
- extracting multiple key points on each frame image in the multi-frame image includes:
- Face keypoint location algorithm was used to extract multiple keypoints on each frame of image.
- a biometric detection device including:
- a key point acquisition unit configured to extract a plurality of key points on each frame of the multi-frame image
- a calculation unit configured to separately calculate distances between key points on the frames of images, and obtain multiple ratios of the frames of images based on the distances of the frames of images;
- a result determination unit is configured to analyze changes in the multiple ratios for the multi-frame images, and determine whether the target object is a living object according to the changes in the multiple ratios.
- a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method for detecting a living body according to the first aspect in the foregoing embodiment is implemented .
- an electronic device including: one or more processors; and a storage device for storing one or more programs.
- the one or more processors implement the following operations:
- For the multi-frame images analyze changes in the multiple ratios, and determine whether the target object is a living object according to the changes in the multiple ratios.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- a deep learning algorithm is used to obtain the classifier model.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the target object is a non-living object.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- a reference number of frame images with different distances from the target object to the acquisition camera are acquired.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the one or more processors when the one or more programs are also executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the size of the detection frame changes.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the ratio of the first distance to the pupil distance is a first ratio
- the ratio of the second distance to the pupil distance is a second ratio
- the ratio of the third distance to the pupil distance is The ratio is the third ratio
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- the changes of the first ratio, the second ratio, and the third ratio are analyzed separately.
- the one or more processors when the one or more programs are further executed by the one or more processors, the one or more processors are caused to implement the following operations:
- Face keypoint location algorithm was used to extract multiple keypoints on each frame of image.
- FIG. 1 schematically illustrates a flowchart of a living body recognition detection method according to an embodiment of the present application
- FIG. 2 schematically illustrates a flowchart of a living body recognition detection method according to another embodiment of the present application
- FIG. 3 schematically illustrates a block diagram of a living body recognition and detection device according to an embodiment of the present application
- FIG. 4 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.
- biometrics can be identified by judging whether the user has completed a specified interactive action, such as blinking, opening his mouth, or raising his head.
- the user can complete the specified action within a specified time by identifying.
- a malicious attacker can record a video of the user performing the above actions in advance, and the video can also pass through the identification system, resulting in poor security of the identification system.
- this method requires the support of additional sensor devices, which are not popular on terminal devices such as mobile phones and computers, and cannot be widely used.
- Step S110 Acquire multiple frames of images at different positions of the target object relative to the acquisition camera
- Step S120 extracting multiple key points on each frame of the multi-frame image
- Step S130 Calculate distances between key points on the frames of images, and calculate multiple ratios of the frames of images based on the calculated distances of the frames of images.
- Step S140 For the multi-frame image, analyze changes in the multiple ratios, and determine whether the target object is a living object according to the changes in the multiple ratios.
- the living body detection method in this example embodiment acquires an image by collecting a camera without the need for additional sensors, which can reduce resource occupation and save costs; moreover, it will not Limited by the presence or absence of sensors on the terminal device, which increases flexibility and usability.
- the living body detection method in this example embodiment can accurately identify a situation in which a malicious attacker uses a video of a user who performs a specified action in advance to avoid this It can also pass recognition in situations, and does not require the user to make multiple specified actions, simplifying the user's operation, simple interaction with the user, which can reduce recognition time and improve recognition efficiency.
- Step S110 Acquire multiple frames of images at different positions of the target object relative to the acquisition camera.
- the camera can provide functions such as taking photos, recording videos, and capturing images, and can be applied to various terminal devices, such as mobile phones, computers, and automatic teller machines (ATMs).
- cameras can also be used in various recognition systems.
- a face recognition system a license plate recognition system, a visual recognition system, etc.
- a face recognition system is taken as an example.
- the capture camera can obtain multiple frames of the target object at different positions relative to the capture camera by taking multiple photos of the target object, that is, when the camera captures images, the relative position of the target object and the camera Can change.
- the position of the camera is unchanged, the position of the target object may be changed, or when the position of the target object is not changed, the position of the camera may be changed.
- the multi-frame image may be a multi-frame image acquired multiple times during a change in the relative position of the target object and the camera.
- a multi-frame image may be a multi-frame image acquired multiple times during a change in the position of the target object relative to the camera, or when the position of the target object does not change, each time the camera generates a displacement, one or more frames are collected. image.
- a reference number of frame images with different distances between the target object and the camera can also be set.
- images are collected separately when the target object is at different distances from the camera, and the total number of collected images is a reference number.
- the camera can collect a reference number of frame images of the target object from far to near, or from near to far.
- the reference number can be set according to actual needs, for example, 5 frames, 8 frames, and so on.
- the collection camera can also obtain a dynamic image of the change of the position of the target object relative to the camera, that is, the camera can record the process of changing the position of the target object during the change of the relative position of the target object and the camera to obtain the dynamic image.
- the dynamic mirror may be divided according to a reference time period, and a reference number of frame images may be intercepted. That is, a reference number of reference time periods is set, and a frame image is intercepted from each reference time period in the dynamic image according to the time point of each frame image in the dynamic image to obtain a reference number of frame images.
- any frame image at the time point in the dynamic image that belongs to the reference time period can be randomly captured, or the time point in the dynamic image is equal to the start time of the reference time period Point image, or capture other images during the reference period.
- the durations of the reference quantity reference time periods may be equal, and the reference quantity reference time periods may be continuous, that is, the end time point of the previous reference time period is the start time point of the next reference time period.
- a detection frame may also be used to prompt the user that the image of the target object appears in the detection frame, and the image can be collected on the camera
- the user is prompted to change the distance of the target object from the camera to obtain a multi-frame image of the target object.
- the farther the person is from the camera the smaller the image of the person in the captured image.
- the distance of the target object from the camera can be changed accordingly, so that images of the target object at different positions relative to the acquisition camera can be obtained.
- Step S120 extracting a plurality of key points on each frame of the multi-frame image.
- the key point information on each frame of the multi-frame image can be extracted.
- the key point information of the image can be facial features information or contour information, such as eyes, nose, mouth, or face contour.
- Key point information can be obtained according to ASM (Active Shape Mode) algorithm or deep learning method.
- ASM Active Shape Mode
- the key point information can also be extracted by other methods, for example, the CPR (Cascaded Pose Regression) method.
- the keypoint information on the frame image is extracted, so that at least one keypoint on the frame image can be determined, and the information of each keypoint, including the part to which each keypoint belongs, and the keypoints in Position on the frame image, etc.
- Step S130 Calculate the distances between the key points on the frames of images, and calculate the multiple ratios of the frames of images based on the calculated distances of the frames of images.
- the distance between each key point may be the distance between every two arbitrary key points on the same frame of image. And the distance between any two key points is determined by the positions of these two key points on the same frame of image.
- the distance from the pupil point to the tip of the nose on each frame of image may be taken as the first distance, the distance from the pupil point to the corner of the mouth is the second distance, and the distance from the corner of the mouth to the tip of the nose is the third distance.
- the distance between each key point can be calculated in the above manner, and multiple ratios can also be calculated based on the calculated distance.
- the ratio can be obtained by calculating the distance between the key points by the ratio of any two distances.
- the pupil distances of the two eyes on each frame of the image can be obtained.
- the ratios of the first distance, the second distance, and the third distance to the pupil distance of the frame image are calculated respectively to obtain multiple ratios.
- the ratio of the first distance to the pupil distance may be used as the first ratio
- the ratio of the second distance to the pupil distance may be used as the second ratio
- the ratio of the third distance to the pupil distance may be used as the third ratio.
- a first ratio, a second ratio, and a third ratio can be obtained.
- the ratio of the first distance to the second distance, the ratio of the second distance to the third distance, and the ratio of the first distance to the third distance may be calculated.
- Ratio Or use other methods to calculate multiple ratios.
- Step S140 For the multi-frame image, analyze changes in the multiple ratios, and determine whether the target object is a living object according to the changes in the multiple ratios.
- the ratio of each frame in the multi-frame image is compared, and the value change of each frame in the multi-frame image is analyzed to obtain the change rule of the ratio.
- the value change of each frame of the first ratio in the multi-frame images may be analyzed separately. That is, the first ratio of the first frame image and the first ratio of the second frame image, the first ratio of the third frame image, etc. in the multi-frame image can be compared until the first ratio of the last frame image.
- the second ratio and the third ratio can also be analyzed according to the same method.
- Whether the target object is a living object is determined according to whether a rule of numerical changes of multiple ratios between multiple frames of images conforms to a rule of multiple ratios of living objects.
- acquiring a change rule of multiple ratios of the living object may include: obtaining multiple frames of the living object at different positions of the camera, extracting multiple key points of each frame image in the multi-frame image, and calculating each key point The distances between the frames are calculated based on the distances calculated for each frame of images, and multiple ratios of the living objects are calculated, and the changes of the multiple ratios are analyzed.
- various algorithms can be used to analyze the changes of multiple ratios of the certain number of living objects, so as to summarize the changing rules of multiple ratios of the living objects.
- the target object By comparing whether the change rule of multiple ratios of the target object matches the change rule of multiple ratios of the living object, it can be determined whether the target object is a living object.
- a ratio change threshold determines whether multiple ratio changes of the target object are less than or greater than the threshold, thereby determining whether the target object is a living object.
- the face is closer to a cylinder.
- the change rules of multiple ratios can be used to identify the target object. Taking into account the differences between cylinders and flat objects, it can overcome the problem of attackers using photos or videos to attack .
- the human face is not completely consistent with the cylinder, the surface of the cylinder is relatively smooth, and the facial features of the human face have uneven features, such as the protrusion of the nose, the depression of the eye socket, etc. These features cause the deformation of the face to have a certain regularity. Therefore, by analyzing the changing rules of multiple ratios of living objects, it is possible to use the changing rules of multiple ratios to identify the target object. Taking into account the differences between real faces and cylinders, it is possible to overcome the attacker's bending of the photo into a cylinder To attack.
- this exemplary embodiment further includes steps S210, S220, and S230, as shown in FIG. 2. among them:
- Step S210 Acquire multiple frames of multiple living objects, calculate the multiple ratios based on the multiple frames of each of the multiple living objects, and use the multiple ratios as a positive sample set.
- the living object may be a real user who needs to be identified.
- Real users can perform various interactions with the recognition system. For example, when a user opens an account at a bank, or registers online banking, or binds a bank card on the platform, it is necessary to pass the identification verification of the identification system to ensure the safety of the user's life and property.
- a multi-frame image of the living object is obtained according to step S110, and a plurality of ratios obtained by performing the foregoing steps S120 and S130 on the obtained multi-frame image can be used as a positive sample set.
- the multiple distances of each frame of image are calculated by the distance calculation, so that multiple ratios can be used as a positive sample set.
- Step S220 Obtain multiple frames of multiple non-living objects, calculate the multiple ratios based on the multiple frames of each non-living object, and use the multiple ratios as a negative sample set.
- the non-living object may be an object of a non-real user.
- the non-living object may be a planar object or a cylindrical object.
- a multi-frame image of the non-living object can be obtained according to step S110.
- the multiple ratios corresponding to the non-living objects obtained in the foregoing steps S120 and S130 may be used as the negative sample set.
- Step S230 Use a deep learning algorithm to obtain the classifier model based on the positive sample set and the negative sample set.
- the classification results of the samples can be obtained directly from the classifier model, so that the analysis effect of the ratio can be obtained quickly and efficiently.
- the positive sample set and the negative sample set obtained in steps S210 and S220 may be used as the training set of the classifier model to train the classifier model.
- the trained classifier model can map any sample data to one of the given categories.
- the classifier model can be trained based on deep learning algorithms, or other algorithms can be used to train the classifier model, such as logistic regression algorithms.
- step S140 may obtain a classification result by inputting multiple ratios into the classifier model, and according to the classification result, it may be determined whether the target object is a living object.
- the classification result is a positive class
- the target object may be determined to be a living object
- the classification result is a negative class
- the target object may be determined to be a non-living object.
- the user may be prompted to recognize, and when the target object is determined to be a non-living object, the user may be prompted to fail to recognize.
- the biometric detection device 300 may include:
- An image acquisition unit 310 configured to acquire multiple frames of images of the target object at different positions relative to the acquisition camera;
- a keypoint obtaining unit 320 configured to extract a plurality of keypoints on each frame of the multi-frame image
- the calculating unit 330 is configured to separately calculate distances between key points on each frame of images, and calculate multiple ratios of the images of each frame according to the calculated distances of the frames of images;
- the result determination unit 340 is configured to analyze changes in the multiple ratios for the multiple frames of images, and determine whether the target object is a living object according to the changes in the multiple ratios.
- the result determination unit 340 is further configured to input the multiple ratios into a classifier model to obtain a classification result, and determine whether the target object is a living object according to the classification result. .
- the apparatus further includes a module for performing the following operations:
- a deep learning algorithm is used to obtain the classifier model.
- the result determination unit 340 is further configured to determine that the target object is a living object when the classification result is positive, and when the classification result is negative. , Determining that the target object is a non-living object.
- the image acquisition unit 310 is further configured to acquire reference number frame images of the target object at different distances from the acquisition camera.
- the image acquisition unit 310 is further configured to acquire a dynamic image of a change in position of the target object relative to the acquisition camera; and divide the dynamic image according to a reference time period To capture the reference number of frame images.
- the apparatus further includes a module for performing the following operations:
- the size of the detection frame changes.
- the distance from the pupil point to the nasal point on each frame of image is the first distance
- the distance from the pupil point to the corner of the mouth is the second distance
- the distance from the corner of the mouth to the tip of the nose is the third distance
- the calculation unit 330 is further configured to obtain the pupil distance of the two eyes on each frame of images; for the same frame of images, the ratio of the first distance to the pupil distance Is a first ratio, a ratio of the second distance to the pupil distance is a second ratio, and a ratio of the third distance to the pupil distance is a third ratio.
- the result determination unit 340 is further configured to analyze changes in the first ratio, the second ratio, and the third ratio for the multi-frame images, respectively.
- the key point obtaining unit 320 is further configured to extract a plurality of key points on each frame of the image by using a face key point positioning algorithm.
- each functional module of the biometric detection device of the exemplary embodiment of the present application corresponds to the steps of the exemplary embodiment of the biometric detection method described above, for details not disclosed in the apparatus embodiment of the present application, please refer to the above-mentioned living body of the present application. Examples of identification detection methods.
- the computer system 400 includes a central processing unit (CPU) 401, which can be loaded into a random access memory (RAM) 403 according to a program stored in a read-only memory (ROM) 402 or loaded from a storage section 408 Instead, perform various appropriate actions and processes.
- RAM random access memory
- ROM read-only memory
- various programs and data required for system operation are also stored.
- the CPU 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404.
- An input / output (I / O) interface 405 is also connected to the bus 404.
- the following components are connected to the I / O interface 405: an input portion 406 including a keyboard, a mouse, and the like; an output portion 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the speaker; a storage portion 408 including a hard disk and the like And a communication section 409 including a network interface card such as a LAN card, a modem, and the like.
- the communication section 409 performs communication processing via a network such as the Internet.
- the driver 410 is also connected to the I / O interface 405 as needed.
- a removable medium 411 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed, so that a computer program read therefrom is installed into the storage section 408 as needed.
- the process described above with reference to the flowchart may be implemented as a computer software program.
- embodiments of the present application include a computer program product including a computer program carried on a computer-readable medium, the computer program containing program code for performing the method shown in the flowchart.
- the computer program may be downloaded and installed from a network through the communication section 409, and / or installed from a removable medium 411.
- this computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the system of the present application are executed.
- the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the foregoing.
- the computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programming read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
- each block in the flowchart or block diagram may represent a module, program segment, or part of code, which contains one or more of the logic functions used to implement the specified logic. Executable instructions.
- the functions labeled in the blocks may also occur in a different order than those labeled in the drawings. For example, two blocks represented one after the other may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved.
- each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with A combination of dedicated hardware and computer instructions.
- the units described in the embodiments of the present application may be implemented by software or hardware.
- the described units may also be provided in a processor.
- the names of these units do not, in some cases, define the unit itself.
- the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device in.
- the computer-readable medium carries one or more programs, and when the one or more programs are executed by one of the electronic devices, the electronic device is enabled to implement the method for detecting a living body as described in the foregoing embodiment.
- the electronic device may implement, as shown in FIG. 1: step S110, acquiring multiple frames of images at different positions of the target object relative to the acquisition camera; and step S120, extracting images on each frame of the multiple frames of images. Multiple key points; step S130, calculating the distance between each key point on each frame of the image, and calculating multiple ratios of each frame image according to the calculated distances of each frame image; step S140, for the Multi-frame images, analyzing changes in the multiple ratios, and determining whether the target object is a living object according to the changes in the multiple ratios.
- the electronic device can implement each step shown in FIG. 2.
- modules or units of the device for action execution are mentioned in the detailed description above, this division is not mandatory.
- the features and functions of two or more modules or units described above may be embodied in one module or unit.
- the features and functions of a module or unit described above can be further divided into multiple modules or units to be embodied.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
一种活体识别检测方法、装置、介质及电子设备,该方法包括:获取目标对象相对于采集摄像头处于不同位置的多帧图像(S110);提取多帧图像中各帧图像上的多个关键点(S120);分别计算各帧图像上各个关键点之间的距离,根据各帧图像计算的距离分别计算得到多个比值(S130);针对多帧图像,分析多个比值的变化,根据多个比值的变化确定目标对象是否为活体对象(S140)。上述方法可以提高识别系统的安全性。
Description
本申请要求于2018年7月6日提交、申请号为201810734833.9、发明名称为“活体识别检测方法、装置、介质及电子设备”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及生物识别技术领域,具体而言,涉及一种活体识别检测方法、装置、介质及电子设备。
随着网络技术的发展,人脸识别技术的应用领域越来越广泛,如在线支付、网上银行、安防系统等。
为了防止恶意用户使用已拍摄的目标人脸照片来完成人脸识别,导致人脸识别系统的安全性差的问题,现有人脸识别系统中都加入了活体识别验证的过程。
需要说明的是,在上述背景技术部分公开的信息仅用于加强对本申请的背景的理解,因此可以包括不构成对本领域普通技术人员已知的相关技术的信息。
发明内容
本申请实施例的目的在于提供一种活体识别检测方法、装置、介质及电子设备,进而至少在一定程度上克服识别系统安全性低的问题。
本申请的其他特性和优点将通过下面的详细描述变得显然,或部分地通过本申请的实践而习得。
根据本申请实施例的一方面,提供了一种活体识别检测方法,包括:
获取目标对象相对于采集摄像头处于不同位置的多帧图像;
提取所述多帧图像中各帧图像上的多个关键点;
分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;
针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
在本申请的一种示例实施例中,基于前述方案,所述根据所述多个比值的变化确定所述目标对象是否为活体对象,包括:
将所述多个比值输入分类器模型,得到分类结果,根据所述分类结果确定所述目标对象是否为活体对象。
在本申请的一种示例实施例中,基于前述方案,将所述多个比值输入分类器模型之前,还包括:
获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集;
获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集;
基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
在本申请的一种示例实施例中,基于前述方案,所述根据所述分类结果确定所述目标对象是否为活体对象包括:
在所述分类结果为正类时,确定所述目标对象为活体对象;
在所述分类结果为负类时,确定所述目标对象为非活体对象。
在本申请的一种示例实施例中,基于前述方案,所述获取目标对象相对于采集摄像头处于不同位置的多帧图像包括:
获取所述目标对象距所述采集摄像头不同距离的参考数量帧图像。
在本申请的一种示例实施例中,基于前述方案,所述获取目标对象相对于采集摄像头处于不同位置的多帧图像包括:
获取所述目标对象相对于所述采集摄像头位置变化的动态影像;
将所述动态影像按参考时间段进行划分,截取所述参考数量帧图像。
在本申请的一种示例实施例中,基于前述方案,所述方法还包括:
通过检测框提示用户所述目标对象的影像出现在所述检测框内;
响应于采集所述目标对象的图像,所述检测框大小发生改变。
在本申请的一种示例实施例中,基于前述方案,所述分别计算所述各帧图 像上各个关键点之间的距离包括:
分别计算出所述各帧图像上瞳孔点到鼻尖点的距离、瞳孔点到嘴角点的距离、嘴角点到鼻尖点的距离;
其中,所述各帧图像上瞳孔点到鼻尖点的距离为第一距离,瞳孔点到嘴角点的距离为第二距离,嘴角点到鼻尖点的距离为第三距离。
在本申请的一种示例实施例中,基于前述方案,所述根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值包括:
获取所述各帧图像上双眼的瞳孔距离;
对于同一帧图像,计算所述第一距离与所述瞳孔距离的比值为第一比值,计算所述第二距离与所述瞳孔距离的比值为第二比值,计算所述第三距离与所述瞳孔距离的比值为第三比值,以得到各帧图像的各第一比值、第二比值、第三比值。
在本申请的一种示例实施例中,基于前述方案,所述针对所述多帧图像,分析所述多个比值的变化包括:
针对所述多帧图像,分别分析所述第一比值、第二比值、第三比值的变化。
在本申请的一种示例实施例中,基于前述方案,所述提取所述多帧图像中各帧图像上的多个关键点包括:
利用人脸关键点定位算法提取各帧图像上的多个关键点。
根据本申请实施例的另一方面,提供了一种活体识别检测装置,包括:
图像采集单元,用于获取目标对象相对于采集摄像头处于不同位置的多帧图像;
关键点获取单元,用于提取所述多帧图像中各帧图像上的多个关键点;
计算单元,用于分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像的距离计算得到所述各帧图像的多个比值;
结果确定单元,用于针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
根据本申请实施例的再一方面,提供了一种计算机可读介质,其上存储有计算机程序,所述程序被处理器执行时实现如上述实施例中第一方面所述的活体识别检测方法。
根据本申请实施例的再一方面,提供了一种电子设备,包括:一个或多个处理器;存储装置,用于存储一个或多个程序,当所述一个或多个程序被所述 一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
获取目标对象相对于采集摄像头处于不同位置的多帧图像;
提取所述多帧图像中各帧图像上的多个关键点;
分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;
针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
将所述多个比值输入分类器模型,得到分类结果,根据所述分类结果确定所述目标对象是否为活体对象。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集;
获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集;
基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
在所述分类结果为正类时,确定所述目标对象为活体对象;
在所述分类结果为负类时,确定所述目标对象为非活体对象。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
获取所述目标对象距所述采集摄像头不同距离的参考数量帧图像。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
获取所述目标对象相对于所述采集摄像头位置变化的动态影像;
将所述动态影像按参考时间段进行划分,截取所述参考数量帧图像。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还 被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
通过检测框提示用户所述目标对象的影像出现在所述检测框内;
响应于采集所述目标对象的图像,所述检测框大小发生改变。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
分别计算出所述各帧图像上瞳孔点到鼻尖点的距离,瞳孔点到嘴角点的距离,嘴角点到鼻尖点的距离;
其中,所述各帧图像上瞳孔点到鼻尖点的距离为第一距离,瞳孔点到嘴角点的距离为第二距离,嘴角点到鼻尖点的距离为第三距离。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
获取所述各帧图像上双眼的瞳孔距离;
对于同一帧图像,所述第一距离与所述瞳孔距离的比值为第一比值,所述第二距离与所述瞳孔距离的比值为第二比值,所述第三距离与所述瞳孔距离的比值为第三比值。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
针对所述多帧图像,分别分析所述第一比值、第二比值、第三比值的变化。
在本申请的一种示例实施例中,基于前述方案,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:
利用人脸关键点定位算法提取各帧图像上的多个关键点。
本申请实施例提供的技术方案可以至少包括以下有益效果:
在本申请的一些实施例所提供的技术方案中,通过采集摄像头获取目标对象相对于采集摄像头处于不同位置的多帧图像,无需额外设备,可以减少资源占用,节约成本;同时,提高了活体识别系统的灵活性和可用性;并且,提取各帧图像上的多个关键点,计算各个关键点之间的距离,根据各帧图像计算的距离分别计算得到各帧图像的多个比值,针对多帧图像分析比值的变化,确定目标对象是否是活体对象,可以抵御攻击者使用目标对象的照片或者视频对识别系统的攻击,提高了识别系统的安全性;同时,与用户之间的交互简单,可以减少识别时间,提高识别效率;并且提高用户体验。
应当理解的是,以上的一般描述和后文的细节描述仅是示例性和解释性 的,并不能限制本申请。
此处的附图被并入说明书中并构成本说明书的一部分,示出了符合本申请的实施例,并与说明书一起用于解释本申请的原理。显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。在附图中:
图1示意性示出了根据本申请的实施例的活体识别检测方法的流程图;
图2示意性示出了根据本申请的另一实施例的活体识别检测方法的流程图;
图3示意性示出了根据本申请的实施例的活体识别检测装置的框图;
图4示出了适于用来实现本申请实施例的电子设备的计算机系统的结构示意图。
现在将参考附图更全面地描述示例实施方式。然而,示例实施方式能够以多种形式实施,且不应被理解为限于在此阐述的范例;相反,提供这些实施方式使得本申请将更加全面和完整,并将示例实施方式的构思全面地传达给本领域的技术人员。
此外,所描述的特征、结构或特性可以以任何合适的方式结合在一个或更多实施例中。在下面的描述中,提供许多具体细节从而给出对本申请的实施例的充分理解。然而,本领域技术人员将意识到,可以实践本申请的技术方案而没有特定细节中的一个或更多,或者可以采用其它的方法、组元、装置、步骤等。在其它情况下,不详细示出或描述公知方法、装置、实现或者操作以避免模糊本申请的各方面。
附图中所示的方框图仅仅是功能实体,不一定必须与物理上独立的实体相对应。即,可以采用软件形式来实现这些功能实体,或在一个或多个硬件模块或集成电路中实现这些功能实体,或在不同网络和/或处理器装置和/或微控制器装置中实现这些功能实体。
附图中所示的流程图仅是示例性说明,不是必须包括所有的内容和操作/步骤,也不是必须按所描述的顺序执行。例如,有的操作/步骤还可以分解, 而有的操作/步骤可以合并或部分合并,因此实际执行的顺序有可能根据实际情况改变。
相关的活体识别技术可以通过判断用户是否完成指定的交互动作来进行识别,比如,眨眼、张嘴、抬头等,用户在规定的时间内完成指定的动作,可以通过识别。但是,恶意攻击者可以提前录制用户进行上述动作的视频,使用视频也可以通过识别系统,导致识别系统的安全性差。还有一些活体识别技术是通过3D传感器获取用户的三维信息来进行识别的。照片或者视频的点深度信息是一致的,而活体人脸的点深度信息是不一致的,利用这一点可以克服攻击者利用视频来攻击系统的问题。但是,这种方式需要额外的传感器设备的支持,而传感器设备在手机、计算机等终端设备上并不普及,无法广泛使用。
基于此,本申请的示例实施方式中首先提供了一种活体识别检测方法。如图1所示,该方法可以包括步骤S110、S120、S130、S140。其中:
步骤S110,获取目标对象相对于采集摄像头处于不同位置的多帧图像;
步骤S120,提取所述多帧图像中各帧图像上的多个关键点;
步骤S130,分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;
步骤S140,针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
与通过3D传感器获取用户的三维信息进行识别的方案相比,本示例实施例中的活体识别检测方法,通过采集摄像头获取图像,无需额外设置传感器,可以减少资源占用,节约成本;而且,不会受到终端设备上是否设置传感器的限制,提高了灵活性和可用性。
与要求用户在规定的时间内完成指定动作的方案相比,本示例实施例中的活体识别检测方法,可以准确识别出恶意攻击者使用提前录制的用户进行指定动作的视频的情况,避免这种情况下也能通过识别,而且不需要用户做出多个指定动作,简化了用户的操作,与用户的交互简单,可以减少识别时间,提高识别效率。
综上所述,根据本示例实施例中的活体识别检测方法,通过采集摄像头获取目标对象相对于采集摄像头处于不同位置的多帧图像,无需额外设备,可以减少资源占用,节约成本;同时,提高了活体识别系统的灵活性和可用性;并 且,通过提取各帧图像上的多个关键点,计算各个关键点之间的距离,根据各帧图像计算的距离分别计算得到各帧图像的多个比值,针对多帧图像分析比值的变化,确定目标对象是否是活体对象,可以抵御攻击者使用目标对象的照片或者视频对识别系统的攻击,提高了识别系统的安全性;同时,与用户之间的交互简单,可以减少识别时间,提高识别效率;并且提高用户体验。
下面,将结合图1至图2对本示例实施例中的活体识别检测方法的各个步骤进行更加详细的说明。
步骤S110,获取目标对象相对于采集摄像头处于不同位置的多帧图像。
摄像头可以提供拍摄照片或者录制视频、采集图像等功能,并且可以被应用于各种终端设备,例如,手机、电脑、ATM(Automatic Teller Machine,自动提款机)等。此外,摄像头还可以被用于各种识别系统中。例如,人脸识别系统、车牌识别系统、视觉识别系统等,本实施例中,以人脸识别系统为例。
在本实施例中,采集摄像头可以通过对目标对象进行多次拍照来获取目标对象相对于采集摄像头处于不同位置的多帧图像,也就是说,在摄像头采集图像时,目标对象与摄像头的相对位置可以发生变化。在摄像头位置不变的情况下,可以使目标对象的位置发生变化,也可以在目标对象位置不变的情况下,使摄像头的位置发生变化。例如,在采集目标对象的图像时,调节摄像头伸缩、转动等,或者目标对象前后左右移动等。多帧图像可以是目标对象与摄像头的相对位置发生变化的过程中,多次采集得到的多帧图像。例如,多帧图像可以是在目标对象相对于摄像头发生位置变化的过程中,多次采集得到的多帧图像,或者目标对象的位置不变时,摄像头每产生一次位移,采集一帧或者多帧图像。可选地,还可以设置目标对象距摄像头不同距离的参考数量帧图像。也就是说,在目标对象距摄像头不同距离的情况下分别采集图像,保证采集的图像总数量为参考数量。举例而言,摄像头可以由远到近,或者由近到远采集目标对象的参考数量帧图像。参考数量可以根据实际需要设置,比如,5帧、8帧等。
此外,采集摄像头还可以获取目标对象相对于摄像头位置变化的动态影像,也就是说,摄像头可以在目标对象与摄像头的相对位置发生变化的过程中,将目标对象位置变化的过程录制下来,得到动态影像。在获得动态影像之后, 可以对动态镜像按照参考时间段划分,截取参考数量帧图像。也就是说,设定参考数量个参考时间段,根据每帧图像在动态影像中的时间点,从动态影像中每个参考时间段内截取一帧图像,从而得到参考数量帧图像。
其中,从参考时间段内截取一帧图像时,可以随机截取在动态影像中的时间点属于参考时间段的任一帧图像,或者截取在动态影像中的时间点等于参考时间段的起始时间点的图像,或者截取参考时间段内的其他图像。
另外,该参考数量个参考时间段的时长可以相等,且该参考数量个参考时间段可以连续,即上一个参考时间段的结束时间点为下一个参考时间段的起始时间点。
例如,获得10秒的动态影像,设参考数量为5,那么可以分别截取2秒时的图像,4秒时的图像,6秒时的图像,8秒时的图像和10秒时的图像,组成目标对象的多帧图像。
进一步地,为了获得目标对象相对于采集摄像头处于不同位置的多帧图像,在本示例实施例中,还可以通过检测框,提示用户目标对象的影像出现在检测框内,并且可以在摄像头采集图像时,改变检测框的大小,从而提示用户使目标对象相对于摄像头的距离发生改变,获得目标对象的多帧图像。
由于人离摄像头越远,拍摄的图像中人的影像就越小。在检测框的大小改变时,目标对象的影像若要出现在检测框内,那么目标对象距摄像头的距离可以相应发生改变,从而可以得到目标对象相对于采集摄像头处于不同位置的图像。
步骤S120,提取所述多帧图像中各帧图像上的多个关键点。
在本示例实施例中,可以在获得多帧图像后,提取多帧图像中的每一帧图像上的关键点。
例如,可以提取多帧图像中的每一帧图像上的关键点信息,图像的关键点信息可以是人脸五官信息、也可以是轮廓信息,例如,眼睛、鼻子、嘴巴或者人脸轮廓等。关键点信息可以根据ASM(Active Shape Mode)算法,或者深度学习的方法获取。当然,根据实际情况,关键点信息也可以是用其他方法进行提取,例如,CPR(Cascaded Pose Regression,级联姿势回归)方法等。
对于各帧图像来说,提取该帧图像上的关键点信息,从而可以确定该帧图 像上的至少一个关键点,且确定各个关键点的信息,包括各个关键点所属的部位、各个关键点在该帧图像上的位置等。
步骤S130,分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值。
在本示例实施例中,各个关键点之间的距离可以是在同一帧图像上每任意两个关键点之间的距离。且任意两个关键点之间的距离由这两个关键点在同一帧图像上的位置确定。可选地,可以将每一帧图像上的瞳孔点到鼻尖点的距离作为第一距离、瞳孔点到嘴角点的距离为第二距离、嘴角点到鼻尖点的距离为第三距离。
此外,对于各帧图像,均可采用上述方式计算得到各个关键点之间的距离,还可以根据计算的距离计算得到多个比值。比值可以是计算出关键点之间的距离后,通过任意两个距离的比获取。可选地,可以获取各帧图像上双眼的瞳孔距离,对于同一帧图像,分别计算上述第一距离、第二距离、第三距离与该帧图像的瞳孔距离的比值,得到多个比值。同时,为了方便表述,可以将第一距离与瞳孔距离的比值作为第一比值,第二距离与瞳孔距离的比值作为第二比值,第三距离与瞳孔距离的比值作为第三比值。对于每一帧图像,都可以得到第一比值、第二比值、第三比值。
可选地,对于同一帧图像,还可以计算上述第一距离与上述第二距离的比值,上述第二距离与上述第三距离的比值,上述第一距离与上述第三距离的比值,得到多个比值。或者采用其他方式计算得到多个比值。
步骤S140,针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
在本示例实施例中,对于每个比值,将多帧图像中每帧图像的该比值进行比较,分析出该比值在多帧图像中的每一帧图像的数值变化,得到该比值的变化规律。
可选地,可以分别分析出第一比值在多帧图像中的每一帧图像的数值变化。也就是说,可以将多帧图像中第一帧图像的第一比值和第二帧图像的第一比值、第三帧图像的第一比值等等,直到最后一帧图像的第一比值进行比较,分析第一比值的数值变化,第二比值、第三比值也可以根据同样的方法进行分 析。
根据多个比值在多帧图像之间的数值变化的规律是否符合活体对象的多个比值的变化规律来确定目标对象是否是活体对象。可选地,获取活体对象的多个比值的变化规律,可以包括:可以通过获得活体对象在摄像头不同位置的多帧图像,提取多帧图像中各帧图像的多个关键点,计算各个关键点之间的距离,根据各帧图像计算的距离分别计算得到活体对象的多个比值,分析多个比值的变化。可以对一定数量的活体对象,采用各种算法分析该一定数量的活体对象的多个比值的变化,从而总结出活体对象的多个比值的变化规律。
通过对比目标对象的多个比值的变化规律是否符合活体对象的多个比值的变化规律,可以确定目标对象是否是活体对象。
或者也可以判断多个比值中的每一个比值的大小是否在活体对象对应的该比值的一定范围内来判断目标对象是否是活体对象。此外,还可以分析活体对象的多个比值的变化规律,比如活体人脸的多个比值变化规律,或者可以分析非活体对象的多个比值的变化规律,根据多个比值的变化规律可以设定一个比值变化阈值,判断目标对象的多个比值变化是否小于或者大于该阈值,从而确定目标对象是否为活体对象。
比如,相较于图片或视频,人脸更接近于圆柱体,摄像头距离人脸越近,采集到的图像变形越大,而摄像头距离平面的图片或视频的远近,不会造成采集到的图像变形,因此图片或视频的多个比值的变化规律与人脸的多个比值的变化规律不同。通过分析活体对象的多个比值的变化规律,能够在识别目标对象时利用多个比值的变化规律进行识别,考虑到了圆柱体与平面物体的差异,能够克服攻击者利用照片或视频进行攻击的问题。
并且,人脸与圆柱体不是完全一致,圆柱体的表面较为平滑,而人脸的五官存在凹凸特征,如鼻尖的突起、眼窝的凹陷等,这些特征导致人脸的变形具有一定的规律性。因此,通过分析活体对象的多个比值的变化规律,能够在识别目标对象时利用多个比值的变化规律进行识别,考虑到了真实人脸与圆柱体的差异,能够克服攻击者将照片弯曲成圆柱体来进行攻击的问题。
进一步地,为了更精确的根据多个比值的变化确定出目标对象是否是活体对象,本示例实施例还包括了步骤S210、S220、S230,如图2所示。其中:
步骤S210,获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集。
在本示例实施例中,活体对象可以是需要进行识别的真实用户。真实用户可以与识别系统进行各种交互操作。比如,用户在银行开户,或者注册网上银行、在平台上绑定银行卡时,都需要通过识别系统的识别验证,以保证用户的生命财产安全。将活体对象作为样本,根据步骤S110获得活体对象的多帧图像,对得到的多帧图像进行上述步骤S120、S130的处理得到的多个比值可以作为正样本集。也就是说,可以用摄像头采集活体对象相对于摄像头处于不同位置的多帧图像,提取多帧图像中每帧图像的多个关键点,计算多个关键点之间的距离,根据每帧图像计算的距离计算得到每帧图像的多个比值,从而可以将多个比值作为正样本集。
步骤S220,获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集。
在本示例实施例中,非活体对象可以是非真实用户的物体。例如,照片、视频、电子设备等。可选地,非活体对象可以是平面物体或者柱面物体。将非活体对象作为样本,可以根据步骤S110获得非活体对象的多帧图像。并且可以根据上述步骤S120、S130得到的非活体对象对应的多个比值,得到的多个比值作为负样本集。也就是说,可以用摄像头采集非活体对象相对于摄像头处于不同位置的多帧图像,提取多帧图像中每帧图像的多个关键点,计算多个关键点之间的距离,根据每帧图像计算的距离计算得到每帧图像的多个比值,从而可以将多个比值作为负样本集。
步骤S230,基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
可以直接根据分类器模型获取样本的分类结果,从而可以根据快速、高效地获取比值的分析效果。在本示例实施例中,可以将步骤S210和步骤S220中获得的正样本集和负样本集作为分类器模型的训练集,对分类器模型进行训练。训练后的分类器模型可以将任何一个样本数据映射到给定类别中的一个。可以基于深度学习算法训练分类器模型,也可以使用其他算法训练分类器模 型,例如,逻辑回归算法等。
进一步地,在得到上述分类器模型之后,步骤S140可以通过将多个比值输入分类器模型中,得到分类结果,根据分类结果可以确定目标对象是否为活体对象。在本示例实施例中,如果分类结果为正类时,可以确定目标对象为活体对象,如果分类结果为负类时,可以确定目标对象为非活体对象。此外,在目标对象确定为活体对象时,还可以提示用户通过识别,在目标对象确定为非活体对象时,可以提示用户识别失败。
以下介绍本申请的装置实施例,可以用于执行本申请上述的活体识别检测方法。如图3所示,该活体识别检测装置300可以包括:
图像采集单元310,用于获取目标对象相对于采集摄像头处于不同位置的多帧图像;
关键点获取单元320,用于提取所述多帧图像中各帧图像上的多个关键点;
计算单元330,用于分别计算各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;
结果确定单元340,用于针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
在本申请的一种示例性实施例中,所述结果确定单元340还用于将所述多个比值输入分类器模型,得到分类结果,根据所述分类结果确定所述目标对象是否为活体对象。
在本申请的另一种示例性实施例中,所述装置还包括用于执行以下操作的模块:
获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集;
获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集;
基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
在本申请的另一种示例性实施例中,所述结果确定单元340还用于在所述分类结果为正类时,确定所述目标对象为活体对象;在所述分类结果为负类时,确定所述目标对象为非活体对象。
在本申请的另一种示例性实施例中,所述图像采集单元310还用于获取所述目标对象距所述采集摄像头不同距离的参考数量帧图像。
在本申请的另一种示例性实施例中,所述图像采集单元310还用于获取所述目标对象相对于所述采集摄像头位置变化的动态影像;将所述动态影像按参考时间段进行划分,截取所述参考数量帧图像。
在本申请的另一种示例性实施例中,所述装置还包括用于执行以下操作的模块:
通过检测框提示用户所述目标对象的影像出现在所述检测框内;
响应于采集所述目标对象的图像,所述检测框大小发生改变。
在本申请的另一种示例性实施例中,所述计算单元330还用于分别计算出所述各帧图像上瞳孔点到鼻尖点的距离,瞳孔点到嘴角点的距离,嘴角点到鼻尖点的距离;
其中,所述各帧图像上瞳孔点到鼻尖点的距离为第一距离,瞳孔点到嘴角点的距离为第二距离,嘴角点到鼻尖点的距离为第三距离。
在本申请的另一种示例性实施例中,所述计算单元330还用于获取所述各帧图像上双眼的瞳孔距离;对于同一帧图像,所述第一距离与所述瞳孔距离的比值为第一比值,所述第二距离与所述瞳孔距离的比值为第二比值,所述第三距离与所述瞳孔距离的比值为第三比值。
在本申请的另一种示例性实施例中,所述结果确定单元340还用于针对所述多帧图像,分别分析所述第一比值、第二比值、第三比值的变化。
在本申请的另一种示例性实施例中,所述关键点获取单元320还用于利用人脸关键点定位算法提取各帧图像上的多个关键点。
由于本申请的示例实施例的活体识别检测装置的各个功能模块与上述活体识别检测方法的示例实施例的步骤对应,因此对于本申请装置实施例中未披露的细节,请参照本申请上述的活体识别检测方法的实施例。
下面参考图4,其示出了适于用来实现本申请实施例的电子设备的计算机系统400的结构示意图。图4示出的电子设备的计算机系统400仅是一个示例,不应对本申请实施例的功能和使用范围带来任何限制。
如图4所示,计算机系统400包括中央处理单元(CPU)401,其可以根据存储在只读存储器(ROM)402中的程序或者从存储部分408加载到随机访 问存储器(RAM)403中的程序而执行各种适当的动作和处理。在RAM 403中,还存储有系统操作所需的各种程序和数据。CPU 401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
以下部件连接至I/O接口405:包括键盘、鼠标等的输入部分406;包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分407;包括硬盘等的存储部分408;以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分409。通信部分409经由诸如因特网的网络执行通信处理。驱动器410也根据需要连接至I/O接口405。可拆卸介质411,诸如磁盘、光盘、磁光盘、半导体存储器等等,根据需要安装在驱动器410上,以便于从其上读出的计算机程序根据需要被安装入存储部分408。
特别地,根据本申请的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本申请的实施例包括一种计算机程序产品,其包括承载在计算机可读介质上的计算机程序,该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中,该计算机程序可以通过通信部分409从网络上被下载和安装,和/或从可拆卸介质411被安装。在该计算机程序被中央处理单元(CPU)401执行时,执行本申请的系统中限定的上述功能。
需要说明的是,本申请所示的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中,计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介 质以外的任何计算机可读介质,该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:无线、电线、光缆、RF等等,或者上述的任意合适的组合。
附图中的流程图和框图,图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,上述模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图或流程图中的每个方框、以及框图或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现,所描述的单元也可以设置在处理器中。其中,这些单元的名称在某种情况下并不构成对该单元本身的限定。
作为另一方面,本申请还提供了一种计算机可读介质,该计算机可读介质可以是上述实施例中描述的电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。上述计算机可读介质承载有一个或者多个程序,当上述一个或者多个程序被一个该电子设备执行时,使得该电子设备实现如上述实施例中所述的活体识别检测方法。
例如,所述的电子设备可以实现如图1中所示的:步骤S110,获取目标对象相对于采集摄像头处于不同位置的多帧图像;步骤S120,提取所述多帧图像中各帧图像上的多个关键点;步骤S130,分别计算各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;步骤S140,针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
又如,所述的电子设备可以实现如图2所示的各个步骤。
应当注意,尽管在上文详细描述中提及了用于动作执行的设备的若干模块或者单元,但是这种划分并非强制性的。实际上,根据本申请的实施方式,上文描述的两个或更多模块或者单元的特征和功能可以在一个模块或者单元中具体化。反之,上文描述的一个模块或者单元的特征和功能可以进一步划分为由多个模块或者单元来具体化。
通过以上的实施方式的描述,本领域的技术人员易于理解,这里描述的示例实施方式可以通过软件实现,也可以通过软件结合必要的硬件的方式来实现。因此,根据本申请实施方式的技术方案可以以软件产品的形式体现出来,该软件产品可以存储在一个非易失性存储介质(可以是CD-ROM,U盘,移动硬盘等)中或网络上,包括若干指令以使得一台计算设备(可以是个人计算机、服务器、触控终端、或者网络设备等)执行根据本申请实施方式的方法。
本领域技术人员在考虑说明书及实践这里公开的发明后,将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化,这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的,本申请的真正范围和精神由下面的权利要求指出。
应当理解的是,本申请并不局限于上面已经描述并在附图中示出的精确结构,并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求来限制。
Claims (24)
- 一种活体识别检测方法,其特征在于,包括:获取目标对象相对于采集摄像头处于不同位置的多帧图像;提取所述多帧图像中各帧图像上的多个关键点;分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
- 根据权利要求1所述的活体识别检测方法,其特征在于,所述根据所述多个比值的变化确定所述目标对象是否为活体对象,包括:将所述多个比值输入分类器模型,得到分类结果,根据所述分类结果确定所述目标对象是否为活体对象。
- 根据权利要求2所述的活体识别检测方法,其特征在于,将所述多个比值输入分类器模型之前,还包括:获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集;获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集;基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
- 根据权利要求2所述的活体识别检测方法,其特征在于,所述根据所述分类结果确定所述目标对象是否为活体对象包括:在所述分类结果为正类时,确定所述目标对象为活体对象;在所述分类结果为负类时,确定所述目标对象为非活体对象。
- 根据权利要求1所述的活体识别检测方法,其特征在于,所述获取目标对象相对于采集摄像头处于不同位置的多帧图像包括:获取所述目标对象距所述采集摄像头不同距离的参考数量帧图像。
- 根据权利要求5所述的活体识别检测方法,其特征在于,所述获取目标对象相对于采集摄像头处于不同位置的多帧图像包括:获取所述目标对象相对于所述采集摄像头位置变化的动态影像;将所述动态影像按参考时间段进行划分,截取所述参考数量帧图像。
- 根据权利要求5所述的活体识别检测方法,其特征在于,还包括:通过检测框提示用户所述目标对象的影像出现在所述检测框内;响应于采集所述目标对象的图像,所述检测框大小发生改变。
- 根据权利要求1所述的活体识别检测方法,其特征在于,所述分别计算所述各帧图像上各个关键点之间的距离包括:分别计算出所述各帧图像上瞳孔点到鼻尖点的距离,瞳孔点到嘴角点的距离,嘴角点到鼻尖点的距离;其中,所述各帧图像上瞳孔点到鼻尖点的距离为第一距离,瞳孔点到嘴角点的距离为第二距离,嘴角点到鼻尖点的距离为第三距离。
- 根据权利要求8所述的活体识别检测方法,其特征在于,所述根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值包括:获取所述各帧图像上双眼的瞳孔距离;对于同一帧图像,所述第一距离与所述瞳孔距离的比值为第一比值,所述第二距离与所述瞳孔距离的比值为第二比值,所述第三距离与所述瞳孔距离的比值为第三比值。
- 根据权利要求9所述的活体识别检测方法,其特征在于,所述针对所述多帧图像,分析所述多个比值的变化包括:针对所述多帧图像,分别分析所述第一比值、第二比值、第三比值的变化。
- 根据权利要求1-10任一项所述的活体图像识别检测方法,其特征在于,所述提取所述多帧图像中各帧图像上的多个关键点包括:利用人脸关键点定位算法提取各帧图像上的多个关键点。
- 一种活体识别检测装置,其特征在于,包括:图像采集单元,用于获取目标对象相对于采集摄像头处于不同位置的多帧图像;关键点获取单元,用于提取所述多帧图像中各帧图像上的多个关键点;计算单元,用于分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像的距离计算得到所述各帧图像的多个比值;结果确定单元,用于针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
- 一种计算机可读介质,其上存储有计算机程序,其特征在于,所述程序被处理器执行时实现如权利要求1至11中任一项所述的活体识别检测方法。
- 一种电子设备,其特征在于,包括:一个或多个处理器;存储装置,用于存储一个或多个程序,当所述一个或多个程序被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:获取目标对象相对于采集摄像头处于不同位置的多帧图像;提取所述多帧图像中各帧图像上的多个关键点;分别计算所述各帧图像上各个关键点之间的距离,根据所述各帧图像计算的距离分别计算得到所述各帧图像的多个比值;针对所述多帧图像,分析所述多个比值的变化,根据所述多个比值的变化确定所述目标对象是否为活体对象。
- 根据权利要求14所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:将所述多个比值输入分类器模型,得到分类结果,根据所述分类结果确定所述目标对象是否为活体对象。
- 根据权利要求15所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:获取多个活体对象的多帧图像,根据所述多个活体对象中的各个活体对象的多帧图像计算所述多个比值,将所述多个比值作为正样本集;获取多个非活体对象的多帧图像,根据所述多个非活体对象中的各个非活体对象的多帧图像计算所述多个比值,将所述多个比值作为负样本集;基于所述正样本集和所述负样本集,利用深度学习算法,获取所述分类器模型。
- 根据权利要求15所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:在所述分类结果为正类时,确定所述目标对象为活体对象;在所述分类结果为负类时,确定所述目标对象为非活体对象。
- 根据权利要求14所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:获取所述目标对象距所述采集摄像头不同距离的参考数量帧图像。
- 根据权利要求18所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:获取所述目标对象相对于所述采集摄像头位置变化的动态影像;将所述动态影像按参考时间段进行划分,截取所述参考数量帧图像。
- 根据权利要求18所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:通过检测框提示用户所述目标对象的影像出现在所述检测框内;响应于采集所述目标对象的图像,所述检测框大小发生改变。
- 根据权利要求14所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:分别计算出所述各帧图像上瞳孔点到鼻尖点的距离,瞳孔点到嘴角点的距离,嘴角点到鼻尖点的距离;其中,所述各帧图像上瞳孔点到鼻尖点的距离为第一距离,瞳孔点到嘴角点的距离为第二距离,嘴角点到鼻尖点的距离为第三距离。
- 根据权利要求21所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:获取所述各帧图像上双眼的瞳孔距离;对于同一帧图像,所述第一距离与所述瞳孔距离的比值为第一比值,所述第二距离与所述瞳孔距离的比值为第二比值,所述第三距离与所述瞳孔距离的比值为第三比值。
- 根据权利要求22所述的电子设备,其特征在于,当所述一个或多个程 序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:针对所述多帧图像,分别分析所述第一比值、第二比值、第三比值的变化。
- 根据权利要求14-23任一项所述的电子设备,其特征在于,当所述一个或多个程序还被所述一个或多个处理器执行时,使得所述一个或多个处理器实现如下操作:利用人脸关键点定位算法提取各帧图像上的多个关键点。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/258,423 US20210295016A1 (en) | 2018-07-06 | 2019-06-18 | Living body recognition detection method, medium and electronic device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810734833.9A CN110688878B (zh) | 2018-07-06 | 2018-07-06 | 活体识别检测方法、装置、介质及电子设备 |
| CN201810734833.9 | 2018-07-06 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020007191A1 true WO2020007191A1 (zh) | 2020-01-09 |
Family
ID=69060574
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/091723 Ceased WO2020007191A1 (zh) | 2018-07-06 | 2019-06-18 | 活体识别检测方法、装置、介质及电子设备 |
Country Status (3)
| Country | Link |
|---|---|
| US (1) | US20210295016A1 (zh) |
| CN (1) | CN110688878B (zh) |
| WO (1) | WO2020007191A1 (zh) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232121A (zh) * | 2020-09-10 | 2021-01-15 | 北京迈格威科技有限公司 | 活体检测方法、装置、设备及介质 |
| CN113965692A (zh) * | 2020-11-30 | 2022-01-21 | 深圳卡多希科技有限公司 | 一种光源点控制摄像头装置转动的方法和装置 |
| CN114694196A (zh) * | 2020-12-11 | 2022-07-01 | 香港城市大学深圳研究院 | 活体分类器建立方法、人脸活体检测方法及装置 |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112926464B (zh) * | 2021-03-01 | 2023-08-29 | 创新奇智(重庆)科技有限公司 | 一种人脸活体检测方法以及装置 |
| CN112966666A (zh) * | 2021-04-01 | 2021-06-15 | 支付宝(杭州)信息技术有限公司 | 活体识别方法、装置、电子设备和服务器 |
| CN113989321B (zh) * | 2021-09-10 | 2025-03-21 | 浙江大华技术股份有限公司 | 入侵检测方法、装置及系统、计算机存储介质 |
| CN115798059A (zh) * | 2022-12-20 | 2023-03-14 | 平安银行股份有限公司 | 一种活体检测方法、装置、计算机设备及存储介质 |
| JP7457991B1 (ja) * | 2023-03-14 | 2024-03-29 | 有限会社バラエティーエム・ワン | なりすまし検知システムおよびなりすまし検知プログラム |
| CN118474522B (zh) * | 2023-11-07 | 2024-12-31 | 荣耀终端有限公司 | 拍照方法、终端设备、芯片及存储介质 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106875191A (zh) * | 2017-02-27 | 2017-06-20 | 努比亚技术有限公司 | 一种扫描支付处理方法、装置及终端 |
| CN107316029A (zh) * | 2017-07-03 | 2017-11-03 | 腾讯科技(深圳)有限公司 | 一种活体验证方法及设备 |
| CN107368769A (zh) * | 2016-05-11 | 2017-11-21 | 北京市商汤科技开发有限公司 | 人脸活体检测方法、装置及电子设备 |
| CN107437067A (zh) * | 2017-07-11 | 2017-12-05 | 广东欧珀移动通信有限公司 | 人脸活体检测方法及相关产品 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| SG11201900117PA (en) * | 2016-07-05 | 2019-02-27 | Yecheng Wu | Spoofing attack detection during live image capture |
| CN107368777A (zh) * | 2017-06-02 | 2017-11-21 | 广州视源电子科技股份有限公司 | 一种微笑动作检测方法和装置及活体识别方法和系统 |
| WO2019127365A1 (zh) * | 2017-12-29 | 2019-07-04 | 深圳前海达闼云端智能科技有限公司 | 人脸活体检测方法、电子设备和计算机程序产品 |
-
2018
- 2018-07-06 CN CN201810734833.9A patent/CN110688878B/zh active Active
-
2019
- 2019-06-18 WO PCT/CN2019/091723 patent/WO2020007191A1/zh not_active Ceased
- 2019-06-18 US US17/258,423 patent/US20210295016A1/en not_active Abandoned
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107368769A (zh) * | 2016-05-11 | 2017-11-21 | 北京市商汤科技开发有限公司 | 人脸活体检测方法、装置及电子设备 |
| CN106875191A (zh) * | 2017-02-27 | 2017-06-20 | 努比亚技术有限公司 | 一种扫描支付处理方法、装置及终端 |
| CN107316029A (zh) * | 2017-07-03 | 2017-11-03 | 腾讯科技(深圳)有限公司 | 一种活体验证方法及设备 |
| CN107437067A (zh) * | 2017-07-11 | 2017-12-05 | 广东欧珀移动通信有限公司 | 人脸活体检测方法及相关产品 |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112232121A (zh) * | 2020-09-10 | 2021-01-15 | 北京迈格威科技有限公司 | 活体检测方法、装置、设备及介质 |
| CN113965692A (zh) * | 2020-11-30 | 2022-01-21 | 深圳卡多希科技有限公司 | 一种光源点控制摄像头装置转动的方法和装置 |
| CN114694196A (zh) * | 2020-12-11 | 2022-07-01 | 香港城市大学深圳研究院 | 活体分类器建立方法、人脸活体检测方法及装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110688878B (zh) | 2021-05-04 |
| US20210295016A1 (en) | 2021-09-23 |
| CN110688878A (zh) | 2020-01-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020007191A1 (zh) | 活体识别检测方法、装置、介质及电子设备 | |
| US10992666B2 (en) | Identity verification method, terminal, and server | |
| US10699103B2 (en) | Living body detecting method and apparatus, device and storage medium | |
| CN109359548B (zh) | 多人脸识别监控方法及装置、电子设备及存储介质 | |
| WO2020207189A1 (zh) | 身份验证方法、装置、存储介质和计算机设备 | |
| US10438077B2 (en) | Face liveness detection method, terminal, server and storage medium | |
| EP3477519A1 (en) | Identity authentication method, terminal device, and computer-readable storage medium | |
| WO2018086543A1 (zh) | 活体判别方法、身份认证方法、终端、服务器和存储介质 | |
| CN109766785B (zh) | 一种人脸的活体检测方法及装置 | |
| CN107609462A (zh) | 待检测信息生成及活体检测方法、装置、设备及存储介质 | |
| US11710353B2 (en) | Spoof detection based on challenge response analysis | |
| WO2017185630A1 (zh) | 基于情绪识别的信息推荐方法、装置和电子设备 | |
| CN108229330A (zh) | 人脸融合识别方法及装置、电子设备和存储介质 | |
| WO2020019591A1 (zh) | 用于生成信息的方法和装置 | |
| CN108280418A (zh) | 脸部图像的欺骗识别方法及装置 | |
| CN110443237B (zh) | 证件识别方法、装置、电子设备及计算机可读存储介质 | |
| CN110866236A (zh) | 隐私图片显示方法、装置、终端及存储介质 | |
| WO2018205468A1 (zh) | 生物识别交易处理方法、电子装置及存储介质 | |
| US20240177519A1 (en) | Digital Verification of Users Based On Real-time Video Stream | |
| CN116012851A (zh) | 凭证检测方法、凭证检测装置、介质、设备及产品 | |
| CN108154070A (zh) | 人脸识别方法及装置 | |
| US12561427B2 (en) | Methods and systems for enhancing detection of multimedia data generated using artificial intelligence | |
| CN111898505A (zh) | 一种判定多人间关系的方法、智能终端及存储介质 | |
| CN115204893A (zh) | 用于电子支付的人脸识别方法、装置、计算机设备 | |
| CN111368644B (zh) | 图像处理方法、装置、电子设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19830204 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19830204 Country of ref document: EP Kind code of ref document: A1 |