WO2019011073A1 - 人脸活体检测方法及相关产品 - Google Patents

人脸活体检测方法及相关产品 Download PDF

Info

Publication number
WO2019011073A1
WO2019011073A1 PCT/CN2018/088896 CN2018088896W WO2019011073A1 WO 2019011073 A1 WO2019011073 A1 WO 2019011073A1 CN 2018088896 W CN2018088896 W CN 2018088896W WO 2019011073 A1 WO2019011073 A1 WO 2019011073A1
Authority
WO
WIPO (PCT)
Prior art keywords
reference image
user
frame
size
shooting range
Prior art date
Application number
PCT/CN2018/088896
Other languages
English (en)
French (fr)
Inventor
唐城
周意保
周海涛
张学勇
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Publication of WO2019011073A1 publication Critical patent/WO2019011073A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • 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; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • 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
    • G06V40/18—Eye characteristics, e.g. of the iris
    • 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

Definitions

  • the present invention relates to the field of mobile terminal technologies, and in particular, to a method for detecting a living body of a human face and related products.
  • biometric identification is often used, such as fingerprint recognition, face recognition, and iris recognition.
  • Biometric identification techniques such as vein recognition and palmprint recognition.
  • face recognition technology is widely used and will continue to be used. More and more mobile terminals are equipped with face recognition devices. For example, face images can be captured by a front camera. Face recognition technology has high accuracy and convenience. Fast and other features.
  • the embodiment of the invention provides a method for detecting a living body of a human face and related products, which can improve the security, reliability and accuracy of the biometric identification of the mobile terminal. .
  • an embodiment of the present invention provides a mobile terminal, including a biological information collection device and a processor, where the biological information collection device is connected to the processor, where
  • the processor is configured to continuously collect, by using the biometric information collecting device, a reference image of a plurality of frames in a current shooting range when detecting a preset image that includes a completeness greater than a preset threshold in the current shooting range;
  • the processor is further configured to preprocess the reference image of the multi-frame
  • the processor is further configured to acquire a feature point set of each frame reference image after the pre-processing
  • the processor is further configured to determine, according to the acquired feature point set, whether the user in the shooting range is a real user.
  • an embodiment of the present invention provides a method for detecting a living body of a human face, including:
  • Whether the user within the shooting range is a real user is determined according to the set of feature points obtained above.
  • an embodiment of the present invention provides a mobile terminal, including a processing unit and an acquisition unit.
  • the processing unit is configured to continuously collect, by using the collecting unit, a reference image of a plurality of frames in a current shooting range when detecting a preset image that includes a completeness greater than a preset threshold in the current shooting range;
  • the processing unit is further configured to preprocess the reference image of the multiple frames.
  • the processing unit is further configured to acquire a feature point set of each of the pre-processed reference images
  • the processing unit is further configured to determine, according to the acquired feature point set, whether the user in the shooting range is a real user.
  • an embodiment of the present invention provides a mobile terminal, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured by the foregoing processing. Executed, the above program includes instructions for performing the steps in any of the methods of the first aspect of the embodiments of the present invention.
  • an embodiment of the present invention provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, wherein the computer program causes the computer to execute the embodiment of the present invention.
  • the computer comprises a mobile terminal.
  • an embodiment of the present invention provides a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program, the computer program being operative to cause a computer to perform the implementation of the present invention Some or all of the steps described in any of the methods of the first aspect.
  • the computer program product can be a software installation package, and the computer includes a mobile terminal.
  • the mobile terminal firstly collects the reference image of the multiple frames in the current shooting range when detecting the preset image whose integrity is greater than the preset threshold in the current shooting range, and secondly, preprocessing The reference image of the multi-frame is obtained, and then the feature point set of each of the pre-processed reference images is obtained. Finally, whether the user in the shooting range is a real user is determined according to the acquired feature point set. It can be seen that before the biometric recognition, the mobile terminal firstly identifies whether the current face is a living face according to the facial expression change of the user, effectively avoiding false photos and the like, and is beneficial to improving the safety, reliability and accuracy of the biometric identification. Sex.
  • FIG. 1 is a schematic structural diagram of a mobile terminal according to an embodiment of the present invention.
  • FIG. 2A is a schematic flowchart of a method for detecting a living body of a human face according to an embodiment of the present invention
  • 2B is a diagram showing an example of a reference image according to an embodiment of the present invention.
  • 2C is a diagram showing an example of a reference image according to an embodiment of the present invention.
  • FIG. 3 is a schematic structural diagram of a mobile terminal disclosed in an embodiment of the present invention.
  • FIG. 4 is a block diagram of a functional unit of a mobile terminal according to an embodiment of the present invention.
  • references to "an embodiment” herein mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the invention.
  • the appearances of the phrases in various places in the specification are not necessarily referring to the same embodiments, and are not exclusive or alternative embodiments that are mutually exclusive. Those skilled in the art will understand and implicitly understand that the embodiments described herein can be combined with other embodiments.
  • the mobile terminal involved in the embodiments of the present invention may include various handheld devices, wireless devices, wearable devices, computing devices, or other processing devices connected to the wireless modem, and various forms of user equipment (User Equipment, UE), mobile station (MS), terminal device, and the like.
  • UE User Equipment
  • MS mobile station
  • terminal device and the like.
  • the devices mentioned above are collectively referred to as mobile terminals.
  • the mobile terminal described in the embodiment of the present invention is provided with a biological information collecting device, and the biological information collecting device specifically includes a fingerprint information collecting device, an iris information collecting device and a facial information collecting device, wherein the fingerprint information collecting device may be a fingerprint sensor module.
  • the iris information collecting device may include an infrared light source and an iris camera, and the face information collecting device may be a general camera module, such as a front camera.
  • FIG. 1 is a schematic structural diagram of a mobile terminal 100.
  • the mobile terminal 100 includes a housing, a touch display screen, a main board, a battery, and a sub-board.
  • the infrared light source is disposed on the main board. 21.
  • the iris camera 22, the front camera 23, the processor 110, the memory 120, and the SIM card slot, etc., the sub-board is provided with a vibrator, an integrated sound chamber, a VOOC flash charging interface and a fingerprint module 24, the infrared light source 21 and the iris
  • the camera 22 constitutes an iris information collecting device of the mobile terminal 100
  • the front camera 23 constitutes a face information collecting device of the mobile terminal 100
  • the fingerprint sensor module 24 constitutes a fingerprint information collecting device of the mobile terminal 100
  • the iris information is collected.
  • the device, the face information collecting device, and the fingerprint information collecting device are collectively referred to as the biological information collecting device of the mobile terminal 100, wherein
  • the biometric information collecting apparatus is configured to continuously acquire a reference image of a plurality of frames in a current shooting range when detecting a preset image that includes a completeness greater than a preset threshold in the current shooting range.
  • the biological information collecting device is an iris information collecting device
  • the infrared light source 21 is configured to emit infrared light to illuminate the iris of the user to form reflected light
  • the iris camera 22 is configured to collect the reflected light to form an iris image
  • the processor 110 acquires the iris image
  • An iris image quality evaluation, an iris region localization (including coarse positioning and fine positioning), an iris preprocessing, an iris feature point extraction, and an iris template generation process are performed on the iris image, and the generated iris template is the above biological information.
  • the specific implementation manner of collecting biological information may be that the biological information collecting device collects a biological image of the user.
  • the processor 110 is configured to preprocess the reference image of the multi-frame.
  • the processor 110 is further configured to acquire a feature point set of each of the pre-processed reference images.
  • the processor 110 is further configured to determine, according to the acquired feature point set, whether the user in the shooting range is a real user.
  • the mobile terminal firstly collects the reference image of the multiple frames in the current shooting range when detecting the preset image whose integrity is greater than the preset threshold in the current shooting range, and secondly, preprocessing The reference image of the multi-frame is obtained, and then the feature point set of each of the pre-processed reference images is obtained. Finally, whether the user in the shooting range is a real user is determined according to the acquired feature point set. It can be seen that before the biometric recognition, the mobile terminal firstly identifies whether the current face is a living face according to the facial expression change of the user, effectively avoiding false photos and the like, and is beneficial to improving the safety, reliability and accuracy of the biometric identification. Sex.
  • the processor 110 is specifically configured to: detect whether the size of the face area in each reference image in the reference image of the multi-frame is equal to a preset area.
  • the size of the face is used to scale the reference image when the size of the face is not equal to the preset size, so that the size of the face in each of the reference images is equal to the preset size.
  • the processor 110 is specifically configured to: detect a face definition in each frame reference image after scaling; and at least one frame reference for selecting a face resolution greater than a preset definition threshold. image.
  • the processor 110 is specifically configured to: acquire any two feature points in the feature point set according to the above-mentioned feature point set obtained according to the foregoing, and determine whether the user in the shooting range is a real user. And determining a first relative reference value between any two feature points; and determining that the user within the shooting range is a real user when the first relative reference value is greater than the first preset threshold.
  • the processor 110 is specifically configured to: acquire any two frames of reference images in the reference image of the multi-frame, in the foregoing, whether the user in the shooting range is determined to be a real user according to the foregoing set of feature points. a set of feature points; and a second relative reference value between the corresponding feature points in the set of feature points for determining any two frame reference images; and when the second relative reference value is greater than the second preset threshold , to determine that the user within the above shooting range is a real user.
  • the processor 110 when the second relative reference value is greater than the second preset threshold, determining that the user in the shooting range is a real user, the processor 110 is specifically configured to: determine that the second relative reference value is greater than a number of feature point groups of the second preset threshold; and determining that the user in the shooting range is a real user when the number of feature point groups is greater than a third preset threshold.
  • FIG. 2A is a schematic flowchart of a method for detecting a living body of a human face, which is applied to a mobile terminal. As shown in the figure, the method for detecting a living body of the face includes:
  • S201 The mobile terminal continuously collects the reference image of the multiple frames in the current shooting range when detecting the preset image that the integrity is greater than the preset threshold in the current shooting range.
  • the preset image may be a face image or an iris image.
  • the integrity of the face image or the iris image in the preset image should be greater than a preset threshold.
  • the integrity of a face in a face image needs to be greater than 90%, so that face images with different expressions can be prevented from camouflaging adult face recognition, because in the process of replacing photos, there will be captured
  • the face integrity is low or the face is not photographed, and in turn, the false photo recognition can be effectively avoided.
  • the preset thresholds corresponding to the face image and the iris image may be different.
  • the mobile terminal continuously collects the reference image of the multi-frame in the current shooting range when the preset image in the shooting range is detected to include the preset image with the completeness greater than the preset threshold, and the reference image of the multi-frame is the face image. .
  • the mobile terminal preprocesses the reference image of the multiple frames.
  • the multi-frame reference image is pre-processed, and the multi-frame image can be processed in brightness, contrast and smoothness to facilitate the extraction of the feature points and reduce the error between the feature points.
  • the reference image of the multi-frame After the reference image of the multi-frame is collected, the reference image of the multi-frame is continuously collected, and whether the expression of the face changes is determined according to the reference image of the multi-frame, thereby determining whether the face is a living body.
  • the mobile terminal acquires a feature point set of each pre-processed reference image.
  • the feature point set of each frame of the reference image after preprocessing is obtained, and the feature points may be eyes, nose, mouth, eyebrows, and the like.
  • the selection of the feature points may be set by the user, or the mobile terminal performs intelligent learning according to the usage habits of the user to obtain a feature point set. For example, in the process of using the mobile terminal by the user, it is detected that the user habitually moves the mouth or moves the eye or the eyebrows, and these elements can be used as feature points.
  • the mobile terminal determines, according to the acquired feature point set, whether the user in the shooting range is a real user.
  • the reference image of the continuous multi-frame is collected, if the captured user's expression changes, the feature point set in each frame reference image also changes, so according to the acquired feature point The collection can further determine whether the user's expression changes, thereby determining whether it is a human face detection.
  • the mobile terminal firstly collects the reference image of the multiple frames in the current shooting range when detecting the preset image whose integrity is greater than the preset threshold in the current shooting range, and secondly, preprocessing The reference image of the multi-frame is obtained, and then the feature point set of each of the pre-processed reference images is obtained. Finally, whether the user in the shooting range is a real user is determined according to the acquired feature point set. It can be seen that before the biometric recognition, the mobile terminal firstly identifies whether the current face is a living face according to the facial expression change of the user, effectively avoiding false photos and the like, and is beneficial to improving the safety, reliability and accuracy of the biometric identification. Sex.
  • the pre-processing the reference image of the multi-frame includes: detecting whether a size of a face in each reference image in the reference image of the multi-frame is equal to a preset area size; When the area size is not equal to the preset area size, the reference image is scaled such that the size of the face area in each of the reference images is equal to the preset area size.
  • the reference image of the multi-frame is pre-processed to detect whether the size of the face area in the reference image of each frame is equal to the preset area size.
  • the reference image is performed on the reference image. Zooming so that the size of the face area in the reference image is equal to the preset area size, and further, the size of the face in each reference image of the multi-frame reference image is the same, equal to the preset area size.
  • the preset area size should satisfy a clear feature point set that can be extracted from the face image of the preset area size.
  • the size of the face area in the reference image of the obtained multi-frame is not the same. Detecting the size of the face area in each frame of the reference image, thereby normalizing the size of the face area in the reference image, so that the size of the face in each frame of the reference image is the same, which is advantageous for multi-frames When the reference image is extracted, the area of the corresponding feature point image is the same, thereby reducing the error of the feature point.
  • the reference image when the size of the face is not equal to the preset size, the reference image is scaled such that the size of the face in the reference image of each frame is equal to the preset.
  • the size of the area includes: detecting the face sharpness in each frame of the reference image after the zooming; and selecting at least one frame reference image whose face sharpness is greater than the preset sharpness threshold.
  • the reference image is adjusted to the preset area size, it should be ensured that the face resolution in each frame reference image is greater than the preset definition threshold, so that a clear feature point image can be obtained.
  • determining whether the user in the shooting range is a real user according to the set of feature points obtained above includes: acquiring any two feature points in the feature point set; and determining any two feature points. a first relative reference value; determining that the user in the shooting range is a real user when the first relative reference value is greater than the first preset threshold.
  • the first relative reference value between the two feature points is compared, and the first relative reference value may be a relative distance between the two feature points.
  • relative angle, relative direction, relative coordinate displacement, etc. are not limited here.
  • the first relative reference value is a relative distance
  • the two selected feature points are the corner of the mouth and the tip of the nose.
  • the distance between the corner of the mouth and the tip of the nose should be different.
  • the distance between the corner of the mouth and the tip of the nose may be greater than the distance between the corner of the mouth and the tip of the nose when the user smiles.
  • the distance between the corner of the mouth and the tip of the nose may change to some extent, but The scope of the change should be within a reasonable range of change. If it exceeds this range of variation, it is not considered to be a normal face smile.
  • the first relative reference value is a relative coordinate
  • the nose tip is used as a coordinate origin.
  • the relative coordinate of the corner of the mouth is (X1, Y1)
  • the relative coordinate of the corner of the mouth is (X2). , Y2)
  • the first relative reference value is the displacement between the coordinates (X2, Y2) and the coordinates (X1, Y1).
  • the first relative reference value is greater than the first preset threshold, that is, the displacement between (X2, Y2) and the coordinate (X1, Y1) is greater than the first preset threshold, indicating that the user has a certain degree of smile, It is intentionally smiling to determine that the current user is a real user.
  • determining whether the user in the shooting range is a real user can accurately identify whether the user has changed the expression, thereby determining whether For the living face, it is beneficial to improve the accuracy and reliability of biometric identification.
  • determining whether the user in the shooting range is a real user according to the set of feature points obtained above includes: acquiring a feature point set of any two frame reference images in the reference image of the multi-frame; determining the foregoing A second relative reference value between the corresponding feature points in the feature point set of the two frames of the reference image; and when the second relative reference value is greater than the second preset threshold value, determining that the user in the shooting range is a real user.
  • the corresponding one or more feature points are selected, and the second relative reference value between the feature points is compared.
  • the second relative reference value may be a change in distance, a change in displacement, an change in angle, or the like occurring in the two frame reference images by one or more corresponding feature points.
  • FIG. 2B is the reference image 1
  • the distance between the corner 1 and the corner 2 of the reference image 1 is d1
  • FIG. 2C is the reference image. 2.
  • the distance between the corner 1 of the reference image 2 and the corner 2 of the mouth is d2
  • the second reference value is the absolute value of the difference between d1 and d2. It can be seen that the distances d1 and d2 between the corners of the reference image 1 and the reference image 2 are different.
  • the second relative reference value may be determined,
  • the second relative reference value is greater than the second preset threshold, it indicates that the user's expression in the reference image 1 and the reference image 2 has changed, and the user's face in the current shooting range may be determined to be a human face.
  • the expression according to the face is The degree of change and change is determined to be a living face.
  • determining that the user in the shooting range is a real user includes: determining that the second relative reference value is greater than a second preset threshold. The number of feature point groups; when the number of feature point groups is greater than a third preset threshold, determining that the user within the shooting range is a real user.
  • the feature point set includes a plurality of feature points of the user, and the user's expression change may include a change of the plurality of feature points.
  • the detected first feature point is a corner of the mouth, and after determining the change of the corner of the mouth, Detecting whether the user's eyes change, because the eyes change when the user smiles, the plurality of sets of feature points of any two frames of reference images may be compared, and the second relative reference value between the feature points is determined to be greater than the second preset.
  • the number of groups of thresholds are used to determine the second relative reference value between the feature points.
  • the user within the shooting range may be determined to be a real user. For example, if the third preset threshold is 2, if it is detected that only the corner of the face of the face changes, the current face or the face may not be judged, and if both the corners of the face and the eyes of the face are detected, the two sets of feature points occur. A certain degree of change can be determined as a human face.
  • the number of feature point groups whose second relative reference value is greater than the second preset threshold is greater than the third preset threshold, it can be determined that the user within the shooting range is a real user.
  • the user before using the biometric recognition, the user must first make a certain degree of expression transformation, and in the process of changing the expression, it is not only a simple expression change, and the number of feature points that change must be greater than the third preset threshold. It is conducive to improving the accuracy and reliability of human face detection.
  • FIG. 3 is a schematic structural diagram of a mobile terminal according to an embodiment of the present invention.
  • the mobile terminal includes a processor, a memory, and a communication interface. And one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, the program including instructions for performing the following steps;
  • Whether the user within the shooting range is a real user is determined according to the set of feature points obtained above.
  • the mobile terminal firstly collects the reference image of the multiple frames in the current shooting range when detecting the preset image whose integrity is greater than the preset threshold in the current shooting range, and secondly, preprocessing The reference image of the multi-frame is obtained, and then the feature point set of each of the pre-processed reference images is obtained. Finally, whether the user in the shooting range is a real user is determined according to the acquired feature point set. It can be seen that before the biometric recognition, the mobile terminal firstly identifies whether the current face is a living face according to the facial expression change of the user, effectively avoiding false photos and the like, and is beneficial to improving the safety, reliability and accuracy of the biometric identification. Sex.
  • the instruction in the foregoing program is specifically configured to: detect whether the size of the face in each reference image in the reference image of the multi-frame is The size of the face is equal to the size of the preset area.
  • the reference image is scaled so that the size of the face in each reference frame is equal to the size of the preset area.
  • the instruction in the foregoing program is specifically configured to perform the following steps: acquiring any two of the feature point sets. a feature point; determining a first relative reference value between any two of the feature points; and determining that the user in the shooting range is a real user when the first relative reference value is greater than the first preset threshold.
  • the instruction in the foregoing program is specifically configured to perform the following steps: acquiring any of the reference images of the multi-frame a set of feature points of the two frames of the reference image; determining a second relative reference value between the corresponding feature points in the feature point set of any two frame reference images; and determining, when the second relative reference value is greater than the second preset threshold
  • the users within the above shooting range are real users.
  • the instructions in the foregoing program are specifically configured to perform the following steps: determining the second a number of feature point groups whose relative reference value is greater than a second preset threshold;
  • the number of feature point groups is greater than the third preset threshold, it is determined that the user in the shooting range is a real user.
  • the mobile terminal includes corresponding hardware structures and/or software modules for performing various functions.
  • the present invention can be implemented in a combination of hardware or hardware and computer software in combination with the elements and algorithm steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods for implementing the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present invention.
  • the embodiment of the present invention may divide the functional unit into the mobile terminal according to the foregoing method example.
  • each functional unit may be divided according to each function, or two or more functions may be integrated into one processing unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present invention is schematic, and is only a logical function division, and the actual implementation may have another division manner.
  • FIG. 4 shows a block diagram of a possible functional unit composition of the mobile terminal involved in the above embodiment.
  • the mobile terminal 400 includes a processing unit 402 and an acquisition unit 403.
  • the processing unit 402 is configured to control and manage the actions of the mobile terminal.
  • the processing unit 402 is configured to support the mobile terminal to perform steps S201-S203 in FIG. 2A and/or other processes for the techniques described herein.
  • the collecting unit 403 is configured to support communication between the mobile terminal and other devices.
  • the mobile terminal may further include a storage unit 401 for storing program codes and data of the mobile terminal.
  • the processing unit 402 is configured to continuously collect, by using the collecting unit 403, a reference image of a plurality of frames in a current shooting range when detecting a preset image that includes a completeness greater than a preset threshold in the current shooting range; Pre-processing the reference image of the multi-frame; and acquiring a feature point set for each of the pre-processed reference images; and determining whether the user in the shooting range is a real user according to the acquired feature point set.
  • the processing unit 402 is configured to detect whether the size of the face area in each reference image in the reference image of the multi-frame is equal to a preset area.
  • the size of the face is used to scale the reference image when the size of the face is not equal to the preset size, so that the size of the face in each of the reference images is equal to the preset size.
  • the processing unit 402 is specifically configured to: detect a face sharpness in each frame reference image after being scaled; and at least one frame reference for selecting a face sharpness greater than a preset sharpness threshold. image.
  • the processing unit 402 is specifically configured to: acquire any two feature points in the feature point set according to the foregoing determining, according to the set of the feature points that are obtained by the foregoing, whether the user in the shooting range is a real user. And determining a first relative reference value between any two feature points; and determining that the user within the shooting range is a real user when the first relative reference value is greater than the first preset threshold.
  • the processing unit 402 is specifically configured to: acquire any two frame reference images in the reference image of the multi-frame, in the foregoing, whether the user in the shooting range is determined to be a real user according to the foregoing set of feature points. a set of feature points; and a second relative reference value between the corresponding feature points in the set of feature points for determining any two frame reference images; and when the second relative reference value is greater than the second preset threshold , to determine that the user within the above shooting range is a real user.
  • the processing unit 402 when the second relative reference value is greater than the second preset threshold, determining that the user in the shooting range is a real user, is specifically configured to: determine that the second relative reference value is greater than a number of feature point groups of the second preset threshold; and determining that the user in the shooting range is a real user when the number of feature point groups is greater than a third preset threshold.
  • the processing unit 402 may be a processor or a controller
  • the collecting unit 403 may be a biological information collecting device, such as an iris information collecting device, a facial information collecting device, a fingerprint information collecting device, etc.
  • the storage unit 401 may be a memory.
  • the embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, the computer program causing the computer to perform some or all of the steps of any of the methods described in the foregoing method embodiments.
  • the above computer includes a mobile terminal.
  • the embodiment of the present invention further provides a computer program product, the computer program product comprising a non-transitory computer readable storage medium storing a computer program, the computer program being operative to cause the computer to execute any one of the methods described in the foregoing method embodiments Part or all of the steps of the method.
  • the computer program product can be a software installation package, and the computer includes a mobile terminal.
  • the disclosed apparatus may be implemented in other ways.
  • the device embodiments described above are merely illustrative.
  • the division of the above units is only a logical function division. In actual implementation, there may be another division manner. For example, multiple units or components may be combined or integrated. Go to another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be electrical or otherwise.
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the above-described integrated unit can be stored in a computer readable memory if it is implemented in the form of a software functional unit and sold or used as a standalone product. Based on such understanding, the technical solution of the present invention may contribute to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a memory. A number of instructions are included to cause a computer device (which may be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-described methods of various embodiments of the present invention.
  • the foregoing memory includes: a U disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and the like, which can store program codes.
  • ROM Read-Only Memory
  • RAM Random Access Memory

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Ophthalmology & Optometry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)

Abstract

本发明实施例公开了一种人脸活体检测方法及相关产品。方法包括：移动终端在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像；预处理所述多帧的参考图像；获取所述预处理后的每帧参考图像的特征点集合；根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户。本发明实施例有利于提高移动终端生物识别的安全性、可靠性和准确性。

Description

人脸活体检测方法及相关产品 技术领域
本发明涉及移动终端技术领域，具体涉及人脸活体检测方法及相关产品。
背景技术
随着社会的进步和科学的发展，信息交互越来越频繁，为保证信息的安全，需对用户身份进行验证，因此，常常会用到生物识别，例如：指纹识别、人脸识别、虹膜识别、静脉识别、掌纹识别等生物识别技术。
目前，人脸识别技术应用广泛并且将会继续被推广使用，越来越多的移动终端配备有人脸识别装置，如可通过前置摄像头拍摄人脸图像，人脸识别技术具有准确率高、方便快捷等特点。
发明内容
本发明实施例提供了人脸活体检测方法及相关产品，可以提高移动终端生物识别的安全性、可靠性和准确性。。
第一方面，本发明实施例提供一种移动终端，包括生物信息采集装置、处理器，上述生物信息采集装置连接上述处理器，其中，
上述处理器，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，通过上述生物信息采集装置连续采集当前拍摄范围内的多帧的参考图像；
上述处理器，还用于预处理上述多帧的参考图像；
上述处理器，还用于获取上述预处理后的每帧参考图像的特征点集合；
上述处理器，还用于根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
第二方面，本发明实施例提供一种人脸活体检测方法，包括：
在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像；
预处理上述多帧的参考图像；
获取上述预处理后的每帧参考图像的特征点集合；
根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
第三方面，本发明实施例提供一种移动终端，包括处理单元和采集单元，
上述处理单元，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，通过上述采集单元连续采集当前拍摄范围内的多帧的参考图像；
上述处理单元，还用于预处理上述多帧的参考图像；
上述处理单元，还用于获取上述预处理后的每帧参考图像的特征点集合；
上述处理单元，还用于根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
第四方面，本发明实施例提供一种移动终端，包括处理器、存储器、通信接口以及一个或多个程序，其中，上述一个或多个程序被存储在上述存储器中，并且被配置由上述处理器执行，上述程序包括用于执行本发明实施例第一方面任一方法中的步骤的指令。
第五方面，本发明实施例提供了一种计算机可读存储介质，其中，上述计算机可读存储介质存储用于电子数据交换的计算机程序，其中，上述计算机程序使得计算机执行如本发明实施例第一方面任一方法中所描述的部分或全部步骤，上述计算机包括移动终端。
第六方面，本发明实施例提供了一种计算机程序产品，其中，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如本发明实施例第一方面任一方法中所描述的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括移动终端。
可以看出，本发明实施例中，移动终端首先在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像，其次，预处理上述多帧的参考图像，然后，获取上述预处理后的每帧参考 图像的特征点集合，最后，根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。可见，移动终端在进行生物识别之前，先根据用户的脸部表情变化，识别当前人脸是否为人脸活体，有效地避免了假照片等情况，有利于提高生物识别的安全性、可靠性和准确性。
附图说明
下面将对本发明实施例所涉及到的附图作简单地介绍。
图1是本发明实施例提供的一种移动终端的结构示意图；
图2A是本发明实施例提供的一种人脸活体检测方法的流程示意图；
图2B是本发明实施例提供的一种参考图像的示例图；
图2C是本发明实施例提供的一种参考图像的示例图；
图3发明实施例公开的一种移动终端的结构示意图；
图4是本发明实施例公开的一种移动终端的功能单元组成框图。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别不同对象，而不是用于描述特定顺序。此外，术语“包括”和“具有”以及它们任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
在本文中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本发明的至少一个实施例中。在说明书中的各个位置出现该短语并 不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域技术人员显式地和隐式地理解的是，本文所描述的实施例可以与其它实施例相结合。
本发明实施例所涉及到的移动终端可以包括各种具有无线通信功能的手持设备、车载设备、可穿戴设备、计算设备或连接到无线调制解调器的其他处理设备，以及各种形式的用户设备(User Equipment，UE)，移动台(Mobile Station，MS)，终端设备(terminal device)等等。为方便描述，上面提到的设备统称为移动终端。
本发明实施例所描述的移动终端设置有生物信息采集装置，该生物信息采集装置具体包括指纹信息采集装置、虹膜信息采集装置和面部信息采集装置，其中，指纹信息采集装置可以是指纹传感器模组、虹膜信息采集装置可以包括红外光源和虹膜摄像头，面部信息采集装置可以是通用摄像头模组，如前置摄像头。下面结合附图对本发明实施例进行介绍。
请参阅图1，图1是本发明实施例提供了一种移动终端100的结构示意图，上述移动终端100包括：壳体、触控显示屏、主板、电池和副板，主板上设置有红外光源21、虹膜摄像头22、前置摄像头23、处理器110、存储器120和SIM卡槽等，副板上设置有振子、一体音腔、VOOC闪充接口和指纹模组24，上述红外光源21和虹膜摄像头22组成该移动终端100的虹膜信息采集装置，上述前置摄像头23组成该移动终端100的面部信息采集装置，上述指纹传感器模组24组成该移动终端100的指纹信息采集装置，上述虹膜信息采集装置、面部信息采集装置和指纹信息采集装置统称为该移动终端100的生物信息采集装置，其中，
上述生物信息采集装置，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像。
其中，生物信息采集装置为虹膜信息采集装置时，红外光源21用于发射红外光线照射用户的虹膜形成反射光线，虹膜摄像头22用于采集反射光线形成虹膜图像，处理器110获取该虹膜图像后，针对该虹膜图像执行虹膜图像质量评估、虹膜区域定位(包含粗定位和精定位)、虹膜预处理、虹膜特征点提 取、虹膜模板生成等处理过程，生成的虹膜模板即上述生物信息。
采集生物信息的具体实现方式可以是生物信息采集装置采集用户的生物图像。
上述处理器110，用于预处理上述多帧的参考图像。
上述处理器110，还用于获取上述预处理后的每帧参考图像的特征点集合。
上述处理器110，还用于根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户
可以看出，本发明实施例中，移动终端首先在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像，其次，预处理上述多帧的参考图像，然后，获取上述预处理后的每帧参考图像的特征点集合，最后，根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。可见，移动终端在进行生物识别之前，先根据用户的脸部表情变化，识别当前人脸是否为人脸活体，有效地避免了假照片等情况，有利于提高生物识别的安全性、可靠性和准确性。
在一个可能的示例中，在上述预处理上述多帧的参考图像方面，上述处理器110具体用于：检测上述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；以及用于在检测到上述人脸面积大小不等于预设面积大小时，对上述参考图像进行缩放，使得上述每帧参考图像中的人脸面积大小等于预设面积大小。
在一个可能的示例中，在所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小方面，所述处理器110具体用于：对缩放后的每帧参考图像中的人脸清晰度进行检测；以及用于选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述处理器110具体用于：获取上述特征点集合中的任意两个特征点；以及用于确定上述任意两个特征点之间的第一相对参考值；以及用于在上述第一相对参考值大于第一预设阈值时，确定上述拍摄 范围内的用户为真实用户。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述处理器110具体用于：获取上述多帧的参考图像中任意两帧参考图像的特征点集合；以及用于确定上述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；以及用于在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户。
在本可能的示例中，在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户方面，上述处理器110具体用于：确定上述第二相对参考值大于第二预设阈值的特征点组数；以及用于在上述特征点组数大于第三预设阈值时，确定上述拍摄范围内的用户为真实用户。
请参阅图2A，图2A是本发明实施例提供了一种人脸活体检测方法的流程示意图，应用于移动终端，如图所示，本人脸活体检测方法包括：
S201，移动终端在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像。
其中，预设图像可为人脸图像或虹膜图像。
其中，预设图像中人脸图像或虹膜图像的完整度应大于预设阈值。例如，人脸图像中的人脸的完整度需大于百分之九十，如此，可避免用不同表情的人脸照片伪装成人脸活体识别，因为在替换照片的过程中，会有拍摄到的人脸完整度低甚至拍摄不到人脸的情况，进而，可有效避免假照片识别的情况。
其中，人脸图像和虹膜图像对应的预设阈值可不相同。
其中，移动终端在检测到拍摄范围内的预设图像中包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像，该多帧的参考图像为人脸图像。
S202，上述移动终端预处理上述多帧的参考图像。
其中，对多帧的参考图像进行预处理，可将该多帧图像进行亮度、对比度以及平滑度的处理，以方便特征点的提取和减少特征点之间的误差。
其中，在采集到多帧的参考图像后，由于这多帧的参考图像是连续采集的， 可根据该多帧的参考图像判断人脸的表情是否发生变换，从而确定是否为人脸活体。
S203，上述移动终端获取上述预处理后的每帧参考图像的特征点集合。
其中，获取预处理后的每帧参考图像的特征点集合，特征点可以是眼睛、鼻子、嘴巴、眉毛等。
其中，特征点的选取可由用户进行设置，或者，移动终端根据用户的使用习惯，进行智能学习，得到特征点集合。例如，在用户使用移动终端的过程中，检测到用户习惯性的会动嘴或者动眼睛或者动眉毛，可将这些元素作为特征点。
S204，上述移动终端根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
其中，由于采集到的是时间连续的多帧的参考图像，假设拍摄到的用户的表情发生变化时，每帧参考图像中的特征点集合也会发生变化，因此可根据获取的到的特征点集合，可进一步确定用户的表情是否发生变化，从而，确定是否为人脸活体检测。
可以看出，本发明实施例中，移动终端首先在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像，其次，预处理上述多帧的参考图像，然后，获取上述预处理后的每帧参考图像的特征点集合，最后，根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。可见，移动终端在进行生物识别之前，先根据用户的脸部表情变化，识别当前人脸是否为人脸活体，有效地避免了假照片等情况，有利于提高生物识别的安全性、可靠性和准确性。
在一个可能的示例中，上述预处理上述多帧的参考图像，包括：检测上述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；在检测到上述人脸面积大小不等于预设面积大小时，对上述参考图像进行缩放，使得上述每帧参考图像中的人脸面积大小等于预设面积大小。
其中，对多帧的参考图像进行预处理，检测每帧参考图像中的人脸面积大小是否等于预设的面积大小，在人脸面积大小不等于预设的面积大小时，对该参考图像进行缩放，使得该参考图像中的人脸面积大小的等于预设的面积大小， 进而，使得多帧的参考图像中每帧参考图像中的人脸面积大小都相同，等于预设的面积大小
其中，预设面积大小应满足可从该预设面积大小的人脸图像中提取到清晰的特征点集合。
可见，本示例中，由于用户在进行人脸识别时，和移动终端之间的距离可能发生了变化，进而，使得得到的多帧的参考图像中人脸面积的大小不相同。对每帧参考图像中的人脸面积大小进行检测，从而，对参考图像中的人脸面积大小进行归一化处理，使得每帧参考图像中的人脸面积大小相同，有利于在对多帧的参考图像进行特征点提取的时候，使得相应的特征点图像面积大小相同，从而，减少特征点的误差。
在一个可能的示例中，所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小，包括：对缩放后的每帧参考图像中的人脸清晰度进行检测；选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
其中，将参考图像调整为预设面积大小后，应保证每帧参考图像中的人脸清晰度大于预设清晰度阈值，使得可以获取到清晰的特征点图像。
可见，本示例中，通过对参考图像进行预处理，有利于在对多帧的参考图像进行特征点提取的时候，使得相应的特征点图像面积大小相同，同时特征点图像清晰。
在一个可能的示例中，上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户，包括：获取上述特征点集合中的任意两个特征点；确定上述任意两个特征点之间的第一相对参考值；在上述第一相对参考值大于第一预设阈值时，确定上述拍摄范围内的用户为真实用户。
其中，在任一参考图像的特征点集合中，任意选取两个特征点，比较这两个特征点之间的第一相对参考值，第一相对参考值可以是两个特征点之间的相对距离、相对角度、相对方向、相对坐标位移等，此处不做限定。
例如，第一相对参考值为相对距离，选取的两个特征点为嘴角和鼻尖，用户在微笑时和不微笑时，嘴角和鼻尖之间的距离应不相同。比如，可能用户在 微笑时，嘴角和鼻尖之间的距离会大于不微笑时嘴角和鼻尖之间的距离，根据微笑程度的不同，嘴角和鼻尖之间的距离也会发生一定程度的变化，但是变化的范围应该在合理的变换范围在之内，如超出这个变化范围，则不认为是正常的人脸微笑表情。
又例如，第一相对参考值为相对坐标，以鼻尖为坐标原点，用户没有做任何表情时，嘴角的相对坐标为(X1，Y1)，在用户有做表情时，嘴角的相对坐标为(X2，Y2)，第一相对参考值为坐标(X2，Y2)和坐标(X1，Y1)之间的位移。其中，在第一相对参考值大于第一预设阈值时，即(X2，Y2)和坐标(X1，Y1)之间的位移大于第一预设阈值时，说明用户发生了一定程度的微笑，是有意的在微笑，可确定当前用户为真实用户。
可见，在本示例中，根据特征点集合中任意两个特征点之间的第一相对参考值，确定拍摄范围内的用户是否为真实用户，可准确识别用户是否发生了表情变化，从而确定是否为人脸活体，有利于提高生物识别的准确性和可靠性。
在一个可能的示例中，上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户，包括：获取上述多帧的参考图像中任意两帧参考图像的特征点集合；确定上述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户。
其中，在连续采集多帧的人脸参考图像时，若用户的人脸表情发生了变化，则在多帧的参考图像中，每帧参考图像中的特征点集合中的同一个或多个特征点也是不相同的，会有一定程度上的变化。
其中，在任意两帧参考图像的特征点集合中，选取对应的一个或多个特征点，比较特征点之间的第二相对参考值。第二相对参考值可以是一个或多个对应特征点在两帧参考图像中发生的距离变化、位移变化、角度变化等。
例如，选取特征点中的两个嘴角进行比较，在用户表情发生变化，如微笑时，参考图像1中两嘴角之间的距离和参考图像2中两嘴角之间的距离可能不相同，因为参考图像1和参考图像2为在不同的时刻采集到的两幅参考图像，用户在表情发生变化的过程中，两嘴角之间的距离自然也会发生变化。如图 2B和图2C所示，为多帧参考图像中的任意两帧参考图像，图2B为参考图像1，参考图像1中嘴角1和嘴角2之间的距离为d1，图2C为参考图像2，参考图像2中嘴角1和嘴角2之间的距离为d2，第二参考值为d1和d2差值的绝对值。可以看出，参考图像1和参考图像2中嘴角之间的距离d1和d2不相同。
其中，根据两帧参考图像中的对应特征点之间的第二相对参考值，如参考图1和参考图像2中的两嘴角之间的距离d1和d2，可确定第二相对参考值，在第二相对参考值大于第二预设阈值时，表明参考图像1和参考图像2中用户的表情发生了变化，可确定当前拍摄范围内的用户人脸为人脸活体。
可见，本示例中，由于多帧的参考图像为连续采集的人脸图像，并且参考图像1和参考图像2为多帧的参考图像中的任意两张参考图像，因此，跟根据人脸的表情变化及变化程度确定为人脸活体。
在本可能的示例中，上述在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户，包括：确定上述第二相对参考值大于第二预设阈值的特征点组数；在上述特征点组数大于第三预设阈值时，确定上述拍摄范围内的用户为真实用户。
其中，特征点集合中包含用户的多个特征点，用户的表情变化可包含多个特征点的变化，例如，检测到的第一个特征点为嘴角，在确定嘴角发生变换后，进而，可检测用户的眼睛是否发生变换，由于用户在微笑时眼睛也会发生变化，可对任意两帧参考图像的多组特征点进行比较，确定特征点之间的第二相对参考值大于第二预设阈值的组数。
其中，在特征点组数大于第三预设阈值时，可确定拍摄范围内的用户为真实用户。例如，第三预设阈值为2，若检测到仅仅是人脸的嘴角发生了变化，则不能判断当前人脸或人脸活体，若检测到人脸的嘴角和眼睛这两组特征点都发生了一定程度的变化，则可确定为人脸活体。
可见，本示例中，在第二相对参考值大于第二预设阈值的特征点组数大于第三预设阈值时，才可确定拍摄范围内的用户为真实用户。如此，使用用户在进行生物识别之前，先要做出一定程度的表情变换，并且在表情变化的过程中， 不能只是简单的表情变化，发生变化的特征点数目需大于第三预设阈值，有利于提高人脸活体检测的准确性和可靠性。
与上述图2A所示的实施例一致的，请参阅图3，图3是本发明实施例提供的一种移动终端的结构示意图，如图所示，该移动终端包括处理器、存储器、通信接口以及一个或多个程序，其中，上述一个或多个程序被存储在上述存储器中，并且被配置由上述处理器执行，上述程序包括用于执行以下步骤的指令；
在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像；
预处理上述多帧的参考图像；
获取上述预处理后的每帧参考图像的特征点集合；
根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
可以看出，本发明实施例中，移动终端首先在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像，其次，预处理上述多帧的参考图像，然后，获取上述预处理后的每帧参考图像的特征点集合，最后，根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。可见，移动终端在进行生物识别之前，先根据用户的脸部表情变化，识别当前人脸是否为人脸活体，有效地避免了假照片等情况，有利于提高生物识别的安全性、可靠性和准确性。
在一个可能的示例中，在上述预处理上述多帧的参考图像方面，上述程序中的指令具体用于执行以下步骤：检测上述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；在检测到上述人脸面积大小不等于预设面积大小时，对上述参考图像进行缩放，使得上述每帧参考图像中的人脸面积大小等于预设面积大小。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述程序中的指令具体用于执行以下步骤：获取上述特征点集合中的任意两个特征点；确定上述任意两个特征点之间的第一相对参考值；在上述第一相对参考值大于第一预设阈值时，确定上述拍摄范围内的用户为真实用户。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述程序中的指令具体用于执行以下步骤：获取上述多帧的参考图像中任意两帧参考图像的特征点集合；确定上述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户。
在一个可能的示例中，在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户方面，上述程序中的指令具体用于执行以下步骤：确定上述第二相对参考值大于第二预设阈值的特征点组数；
在上述特征点组数大于第三预设阈值时，确定上述拍摄范围内的用户为真实用户。
上述主要从方法侧执行过程的角度对本发明实施例的方案进行了介绍。可以理解的是，移动终端为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
本发明实施例可以根据上述方法示例对移动终端进行功能单元的划分，例如，可以对应各个功能划分各个功能单元，也可以将两个或两个以上的功能集成在一个处理单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。需要说明的是，本发明实施例中对单元的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用集成的单元的情况下，图4示出了上述实施例中所涉及的移动终端的一种可能的功能单元组成框图。移动终端400包括：处理单元402和采集单元403。处理单元402用于对移动终端的动作进行控制管理，例如，处理单元402用于支持移动终端执行图2A中的步骤S201-S203和/或用于本文所描述的技术的其它过程。采集单元403用于支持移动终端与其他设备的通信。移动终 端还可以包括存储单元401，用于存储移动终端的程序代码和数据。
其中，上述处理单元402，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，通过上述采集单元403连续采集当前拍摄范围内的多帧的参考图像；以及用于预处理上述多帧的参考图像；以及用于获取上述预处理后的每帧参考图像的特征点集合；以及用于根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户。
在一个可能的示例中，在上述预处理上述多帧的参考图像方面，上述处理单元402具体用于：检测上述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；以及用于在检测到上述人脸面积大小不等于预设面积大小时，对上述参考图像进行缩放，使得上述每帧参考图像中的人脸面积大小等于预设面积大小。
在一个可能的示例中，在所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小方面，所述处理单元402具体用于：对缩放后的每帧参考图像中的人脸清晰度进行检测；以及用于选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述处理单元402具体用于：获取上述特征点集合中的任意两个特征点；以及用于确定上述任意两个特征点之间的第一相对参考值；以及用于在上述第一相对参考值大于第一预设阈值时，确定上述拍摄范围内的用户为真实用户。
在一个可能的示例中，在上述根据上述获取的特征点集合确定上述拍摄范围内的用户是否为真实用户方面，上述处理单元402具体用于：获取上述多帧的参考图像中任意两帧参考图像的特征点集合；以及用于确定上述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；以及用于在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户。
在一个可能的示例中，在上述第二相对参考值大于第二预设阈值时，确定上述拍摄范围内的用户为真实用户方面，上述处理单元402具体用于：确定上 述第二相对参考值大于第二预设阈值的特征点组数；以及用于在上述特征点组数大于第三预设阈值时，确定上述拍摄范围内的用户为真实用户。
其中，处理单元402可以是处理器或控制器，采集单元403可以是生物信息采集装置，如虹膜信息采集装置、面部信息采集装置、指纹信息采集装置等，存储单元401可以是存储器。
本发明实施例还提供一种计算机存储介质，其中，该计算机存储介质存储用于电子数据交换的计算机程序，该计算机程序使得计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤，上述计算机包括移动终端。
本发明实施例还提供一种计算机程序产品，上述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，上述计算机程序可操作来使计算机执行如上述方法实施例中记载的任一方法的部分或全部步骤。该计算机程序产品可以为一个软件安装包，上述计算机包括移动终端。
需要说明的是，对于前述的各方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本发明并不受所描述的动作顺序的限制，因为依据本发明，某些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本发明所必须的。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置，可通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者 也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
上述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储器中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储器中，包括若干指令用以使得一台计算机设备(可为个人计算机、服务器或者网络设备等)执行本发明各个实施例上述方法的全部或部分步骤。而前述的存储器包括：U盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储器中，存储器可以包括：闪存盘、只读存储器(英文：Read-Only Memory，简称：ROM)、随机存取器(英文：Random Access Memory，简称：RAM)、磁盘或光盘等。
以上对本发明实施例进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。

Claims (20)

  1. 一种移动终端，其特征在于，包括生物信息采集装置、处理器，所述生物信息采集装置连接所述处理器，其中，
    所述处理器，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，通过所述生物信息采集装置连续采集当前拍摄范围内的多帧的参考图像；
    所述处理器，还用于预处理所述多帧的参考图像；
    所述处理器，还用于获取所述预处理后的每帧参考图像的特征点集合；
    所述处理器，还用于根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户。
  2. 根据权利要求1所述的移动终端，其特征在于，在所述预处理所述多帧的参考图像方面，所述处理器具体用于：检测所述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；以及用于在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小。
  3. 根据权利要求2所述的方法，其特征在于，在所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小方面，所述处理器具体用于：对缩放后的每帧参考图像中的人脸清晰度进行检测；以及用于选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
  4. 根据权利要求1或2所述的移动终端，其特征在于，在所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户方面，所述处理器具体用于：获取所述特征点集合中的任意两个特征点；以及用于确定所述任意两个特征点之间的第一相对参考值；以及用于在所述第一相对参考值大于第一预设阈值时，确定所述拍摄范围内的用户为真实用户。
  5. 根据权利要求1或2所述的移动终端，其特征在于，在所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户方面，所述处理器具体用于：获取所述多帧的参考图像中任意两帧参考图像的特征点集合；以 及用于确定所述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；以及用于在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户。
  6. 根据权利要求5所述的移动终端，其特征在于，在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户方面，所述处理器具体用于：确定所述第二相对参考值大于第二预设阈值的特征点组数；以及用于在所述特征点组数大于第三预设阈值时，确定所述拍摄范围内的用户为真实用户。
  7. 一种人脸活体检测方法，其特征在于，包括：
    在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，连续采集当前拍摄范围内的多帧的参考图像；
    预处理所述多帧的参考图像；
    获取所述预处理后的每帧参考图像的特征点集合；
    根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户。
  8. 根据权利要求7所述的方法，其特征在于，所述预处理所述多帧的参考图像，包括：
    检测所述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；
    在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小。
  9. 根据权利要求8所述的方法，其特征在于，所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小，包括：
    对缩放后的每帧参考图像中的人脸清晰度进行检测；
    选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
  10. 根据权利要求7或8所述的方法，其特征在于，所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户，包括：
    获取所述特征点集合中的任意两个特征点；
    确定所述任意两个特征点之间的第一相对参考值；
    在所述第一相对参考值大于第一预设阈值时，确定所述拍摄范围内的用户为真实用户。
  11. 根据权利要求7或8所述的方法，其特征在于，所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户，包括：
    获取所述多帧的参考图像中任意两帧参考图像的特征点集合；
    确定所述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；
    在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户。
  12. 根据权利要求11所述的方法，其特征在于，所述在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户，包括：
    确定所述第二相对参考值大于第二预设阈值的特征点组数；
    在所述特征点组数大于第三预设阈值时，确定所述拍摄范围内的用户为真实用户。
  13. 一种移动终端，其特征在于，包括处理单元和采集单元，
    所述处理单元，用于在检测到当前拍摄范围内包含完整度大于预设阈值的预设图像时，通过所述采集单元连续采集当前拍摄范围内的多帧的参考图像；
    所述处理单元，还用于预处理所述多帧的参考图像；
    所述处理单元，还用于获取所述预处理后的每帧参考图像的特征点集合；
    所述处理单元，还用于根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户。
  14. 根据权利要求13所述的移动终端，其特征在于，在所述预处理所述多帧的参考图像方面，所述处理单元具体用于：检测所述多帧的参考图像中每帧参考图像中的人脸面积大小是否等于预设面积大小；以及用于在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每 帧参考图像中的人脸面积大小等于预设面积大小。
  15. 根据权利要求14所述的方法，其特征在于，在所述在检测到所述人脸面积大小不等于预设面积大小时，对所述参考图像进行缩放，使得所述每帧参考图像中的人脸面积大小等于预设面积大小方面，所述处理单元具体用于：对缩放后的每帧参考图像中的人脸清晰度进行检测；以及用于选取人脸清晰度大于预设清晰度阈值的至少一帧参考图像。
  16. 根据权利要求13或14所述的方法，其特征在于，在所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户方面，所述处理单元具体用于：获取所述特征点集合中的任意两个特征点；以及用于确定所述任意两个特征点之间的第一相对参考值；以及用于在所述第一相对参考值大于第一预设阈值时，确定所述拍摄范围内的用户为真实用户。
  17. 根据权利要求13或14所述的方法，其特征在于，在所述根据所述获取的特征点集合确定所述拍摄范围内的用户是否为真实用户方面，所述处理单元具体用于：获取所述多帧的参考图像中任意两帧参考图像的特征点集合；以及用于确定所述任意两帧参考图像的特征点集合中对应的特征点之间的第二相对参考值；以及用于在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户。
  18. 根据权利要求17所述的方法，其特征在于，在所述第二相对参考值大于第二预设阈值时，确定所述拍摄范围内的用户为真实用户方面，所述处理单元具体用于：确定所述第二相对参考值大于第二预设阈值的特征点组数；以及用于在所述特征点组数大于第三预设阈值时，确定所述拍摄范围内的用户为真实用户。
  19. 一种移动终端，其特征在于，包括处理器、存储器、通信接口以及一个或多个程序，其中，所述一个或多个程序被存储在所述存储器中，并且被配置由所述处理器执行，所述程序包括用于执行权利要求7-12任一项方法中的步骤的指令。
  20. 一种计算机可读存储介质，其特征在于，其存储用于电子数据交换的 计算机程序，其中，所述计算机程序使得计算机执行如权利要求7-12任一项所述的方法，所述计算机包括移动终端。
PCT/CN2018/088896 2017-07-11 2018-05-29 人脸活体检测方法及相关产品 WO2019011073A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710560789.XA CN107437067A (zh) 2017-07-11 2017-07-11 人脸活体检测方法及相关产品
CN201710560789.X 2017-07-11

Publications (1)

Publication Number Publication Date
WO2019011073A1 true WO2019011073A1 (zh) 2019-01-17

Family

ID=60461267

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/088896 WO2019011073A1 (zh) 2017-07-11 2018-05-29 人脸活体检测方法及相关产品

Country Status (2)

Country Link
CN (1) CN107437067A (zh)
WO (1) WO2019011073A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111179234A (zh) * 2019-12-20 2020-05-19 珠海格力智能装备有限公司 压缩机的孔位信息确定方法及装置
CN111860057A (zh) * 2019-04-29 2020-10-30 北京眼神智能科技有限公司 人脸图像模糊和活体检测方法、装置、存储介质及设备
CN113128288A (zh) * 2019-12-31 2021-07-16 深圳云天励飞技术有限公司 监控方法及相关产品
CN115174138A (zh) * 2022-05-25 2022-10-11 北京旷视科技有限公司 摄像头攻击检测方法、系统、设备、存储介质及程序产品

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
CN110688878B (zh) * 2018-07-06 2021-05-04 北京三快在线科技有限公司 活体识别检测方法、装置、介质及电子设备
CN109086691B (zh) * 2018-07-16 2020-02-21 阿里巴巴集团控股有限公司 一种三维脸部活体检测方法、脸部认证识别方法及装置
CN109614910B (zh) * 2018-12-04 2020-11-20 青岛小鸟看看科技有限公司 一种人脸识别方法和装置
CN111432279A (zh) * 2019-01-10 2020-07-17 青岛海尔多媒体有限公司 一种用于智能电视控制的方法、装置及智能电视
CN110199296A (zh) * 2019-04-25 2019-09-03 深圳市汇顶科技股份有限公司 人脸识别方法、处理芯片以及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102654903A (zh) * 2011-03-04 2012-09-05 井维兰 一种人脸比对方法
CN104361326A (zh) * 2014-11-18 2015-02-18 新开普电子股份有限公司 一种判别活体人脸的方法
CN104751110A (zh) * 2013-12-31 2015-07-01 汉王科技股份有限公司 一种活体检测方法和装置
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

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102654903A (zh) * 2011-03-04 2012-09-05 井维兰 一种人脸比对方法
CN104751110A (zh) * 2013-12-31 2015-07-01 汉王科技股份有限公司 一种活体检测方法和装置
CN104361326A (zh) * 2014-11-18 2015-02-18 新开普电子股份有限公司 一种判别活体人脸的方法
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 (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111860057A (zh) * 2019-04-29 2020-10-30 北京眼神智能科技有限公司 人脸图像模糊和活体检测方法、装置、存储介质及设备
CN111179234A (zh) * 2019-12-20 2020-05-19 珠海格力智能装备有限公司 压缩机的孔位信息确定方法及装置
CN111179234B (zh) * 2019-12-20 2023-08-25 珠海格力智能装备有限公司 压缩机的孔位信息确定方法及装置
CN113128288A (zh) * 2019-12-31 2021-07-16 深圳云天励飞技术有限公司 监控方法及相关产品
CN113128288B (zh) * 2019-12-31 2024-06-11 深圳云天励飞技术有限公司 监控方法及相关产品
CN115174138A (zh) * 2022-05-25 2022-10-11 北京旷视科技有限公司 摄像头攻击检测方法、系统、设备、存储介质及程序产品
CN115174138B (zh) * 2022-05-25 2024-06-07 北京旷视科技有限公司 摄像头攻击检测方法、系统、设备、存储介质及程序产品

Also Published As

Publication number Publication date
CN107437067A (zh) 2017-12-05

Similar Documents

Publication Publication Date Title
WO2019011073A1 (zh) 人脸活体检测方法及相关产品
CN106446873B (zh) 人脸检测方法及装置
US10616475B2 (en) Photo-taking prompting method and apparatus, an apparatus and non-volatile computer storage medium
CN105335722B (zh) 一种基于深度图像信息的检测系统及方法
US20210248356A1 (en) Method and apparatus for face recognition
US8866931B2 (en) Apparatus and method for image recognition of facial areas in photographic images from a digital camera
US10423848B2 (en) Method, system, and computer-readable recording medium for long-distance person identification
EP2164027B1 (en) Object detecting device, imaging apparatus, object detecting method, and program
CN106372629B (zh) 一种活体检测方法和装置
US20220309836A1 (en) Ai-based face recognition method and apparatus, device, and medium
WO2019033569A1 (zh) 眼球动作分析方法、装置及存储介质
CN105740778B (zh) 一种改进的三维人脸活体检测方法及其装置
WO2019011072A1 (zh) 虹膜活体检测方法及相关产品
Arcoverde Neto et al. Enhanced real-time head pose estimation system for mobile device
JP6157165B2 (ja) 視線検出装置及び撮像装置
EP2336949A1 (en) Apparatus and method for registering plurality of facial images for face recognition
CN109937434B (zh) 图像处理方法、装置、终端和存储介质
WO2016165107A1 (zh) 一种采集指纹的方法、指纹采集器以及终端
CN107346419B (zh) 虹膜识别方法、电子装置和计算机可读存储介质
CN112446322B (zh) 眼球特征检测方法、装置、设备及计算机可读存储介质
Ghani et al. GazePointer: A real time mouse pointer control implementation based on eye gaze tracking
CN107977636B (zh) 人脸检测方法及装置、终端、存储介质
EP3200092A1 (en) Method and terminal for implementing image sequencing
CN106648042A (zh) 一种识别控制方法以及装置
CN108875488B (zh) 对象跟踪方法、对象跟踪装置以及计算机可读存储介质

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: 18831116

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: 18831116

Country of ref document: EP

Kind code of ref document: A1