WO2021213249A1 - 面部图像的采集及面部识别 - Google Patents

面部图像的采集及面部识别 Download PDF

Info

Publication number
WO2021213249A1
WO2021213249A1 PCT/CN2021/087627 CN2021087627W WO2021213249A1 WO 2021213249 A1 WO2021213249 A1 WO 2021213249A1 CN 2021087627 W CN2021087627 W CN 2021087627W WO 2021213249 A1 WO2021213249 A1 WO 2021213249A1
Authority
WO
WIPO (PCT)
Prior art keywords
movable camera
target user
image
position information
reference part
Prior art date
Application number
PCT/CN2021/087627
Other languages
English (en)
French (fr)
Inventor
明泉水
Original Assignee
支付宝(杭州)信息技术有限公司
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 支付宝(杭州)信息技术有限公司 filed Critical 支付宝(杭州)信息技术有限公司
Publication of WO2021213249A1 publication Critical patent/WO2021213249A1/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
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements

Definitions

  • This specification relates to the field of computer technology, and in particular to a method, device, equipment and facial recognition equipment for acquiring facial images.
  • facial recognition equipment can be configured to obtain facial images of users who brush their faces.
  • the height of the facial recognition equipment is fixed, the height of the facial recognition equipment is not on the same level as the height of the facial recognition equipment.
  • the facial image of the facial recognition user collected by the facial device has the problem of inaccuracy, resulting in the unmanned sales device being unable to accurately provide the user with the facial payment service. Therefore, an accurate acquisition is required
  • the user’s facial image provides a timely and accurate solution to provide users with a facial payment service.
  • the purpose of the embodiments of this specification is to provide a facial image collection method, device, equipment, and facial recognition equipment, so as to provide a solution that can accurately obtain the user's facial image and provide the user with a facial payment service in a timely and accurate manner. plan.
  • an embodiment of the present specification provides a facial image collection method, the method includes: acquiring a target image including a facial image of a target user collected by a movable camera; The target user’s facial image is analyzed to determine the position information of the target user’s face and the image corresponding to the preset reference part in the target image; based on the position information, the current location of the movable camera is determined.
  • the position does not match the position corresponding to the reference part of the target user, adjust the shooting position of the movable camera based on the position information so that the shooting position of the movable camera is consistent with that of the target user. Match the position corresponding to the reference position.
  • a facial recognition device provided by an embodiment of this specification includes a movable camera and a controller, wherein: the movable camera is located on the back of the screen of the facial recognition device and is used to pass through the facial recognition device The screen to collect the target image including the face image of the target user; the controller is used to obtain the target image including the face image of the target user collected by the movable camera; The face image of the target user is analyzed to determine the position information in the target image of the image corresponding to the reference part preset in the face of the target user; and the current position of the movable camera is determined based on the position information.
  • the shooting position of the movable camera is adjusted based on the position information, so that the shooting position of the movable camera is the same as that of the target Match the position corresponding to the user's reference part.
  • an embodiment of the present specification provides a facial image acquisition device, the device includes: an image acquisition module for acquiring a target image including a facial image of a target user collected by a movable camera; position acquisition Module, used to analyze the face image of the target user in the target image, and determine the position information in the target image of the image corresponding to the reference part preset in the target user’s face; the position adjustment module uses In a case where it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the reference part of the target user, adjust the shooting of the movable camera based on the position information Position so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • an embodiment of the present specification provides a facial image acquisition device, the facial image acquisition device includes: a processor; and a memory arranged to store computer-executable instructions, the executable instructions being executed
  • the processor acquires the target image including the face image of the target user collected by the movable camera; analyzes the face image of the target user in the target image to determine the target user’s face Set the position information of the image corresponding to the reference part in the target image; when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the reference part of the target user Next, adjust the shooting position of the movable camera based on the position information so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • Fig. 1 is a flowchart of an embodiment of a method for acquiring facial images in this specification
  • Figure 2 is a schematic diagram of a method for acquiring a target image in this specification
  • Fig. 3 is a schematic diagram of a method for acquiring position information in this specification
  • FIG. 4 is a flowchart of another embodiment of a method for acquiring facial images in this specification.
  • FIG. 5 is a schematic diagram of a region division of a target image in this specification.
  • FIG. 6 is a schematic structural diagram of another embodiment of a facial image acquisition device in this specification.
  • Fig. 7 is a schematic structural diagram of another facial image acquisition device in this specification.
  • the embodiments of this specification provide a method, device, equipment and facial recognition equipment for acquiring facial images.
  • the embodiment of this specification provides a method for acquiring facial images.
  • the execution subject of the method may be an electronic device that can provide users with services such as facial payment.
  • the electronic device may be equipped with a movable camera.
  • the electronic device can be a face-swiping payment device, an unmanned sales device, etc.
  • the method may specifically include the following steps:
  • the target image including the facial image of the target user collected by the movable camera is acquired.
  • unmanned vending equipment has penetrated into people’s lives.
  • unmanned vending equipment has begun to provide users with facial payment services, but how to accurately collect users’ information? Facial images have become the focus of attention of equipment operators.
  • facial recognition equipment can be configured to obtain facial images of users who brush their faces.
  • the height of the facial recognition equipment is fixed, the height of the facial recognition equipment is not on the same level as the height of the facial recognition equipment.
  • the facial image of the facial recognition user collected by the facial device has the problem of inaccuracy, resulting in the unmanned sales device being unable to accurately provide the user with the facial payment service.
  • the user’s facial image provides a timely and accurate solution to provide users with a facial payment service.
  • the embodiments of the present specification provide a technical solution that can solve the above-mentioned problems. For details, refer to the following content.
  • the electronic device when the target user selects a product on the screen of the unmanned sales device and clicks to buy, the electronic device can collect the target image including the target user's facial image through the movable camera , wherein the movable camera may be preset at a designated position of the electronic device, and may be located at a preset initial position relative to the target user. For example, as shown in Figure 2, the movable camera in the unmanned vending device can be located at the initial position on the upper side of the screen. In the case that the unmanned vending device receives a purchase instruction from the target user for a certain product, the The position of the movable camera captures the target image including the target user's facial image.
  • the face image of the target user in the target image is analyzed, and the position information of the image corresponding to the preset reference part in the face of the target user in the target image is determined.
  • the preset reference part may be any preset part such as eyes, nose, and mouth.
  • the reference part can be used to enable the camera to collect more accurate and complete facial images of the user.
  • the target image can be analyzed based on a preset image analysis algorithm to determine the position information of the image corresponding to the preset reference part in the target user's face in the target image.
  • the target image When acquiring location information, the target image can be divided into multiple regions, and the corresponding location information can be determined according to the region information in the target image where the image corresponding to the reference part preset in the target user's face is located.
  • the image corresponding to the nose in the target user’s face is located in area 2 of the target image, and the corresponding position information can be the area 2 in the target image. Location information.
  • the above determination method of location information is an optional and achievable determination method, and there may also be multiple determination methods in actual application scenarios, which are not specifically limited in the embodiment of this specification.
  • multiple reference locations may be preset, and the corresponding location information may be determined according to the sub-location information of the image corresponding to each reference location in the target image.
  • the reference parts include eyes, nose, and ears
  • the images corresponding to the eyes and nose in the target user’s face are in area 1 in the target image
  • the image corresponding to the ears in the target user’s face is in area 2 in the target image
  • the location information of the image corresponding to the preset reference part on the target user's face in the target image is the location information of the area 1.
  • the shooting position of the movable camera is adjusted based on the position information to make the movable camera The shooting position of is matched with the position corresponding to the reference part of the target user.
  • the shooting position of the movable camera matches the position corresponding to the reference part of the target user. For example, if the current shooting position of the movable camera is on the same horizontal line as the position corresponding to the reference part of the target user, it can be considered that the shooting position of the movable camera matches the position corresponding to the reference part of the target user. Or, if the angle between the current shooting position of the movable camera and the position corresponding to the reference part of the target user is on the same horizontal plane and is within the preset angle range, then the shooting position of the movable camera can also be considered as Match the position corresponding to the reference part of the target user.
  • the target image can be divided into multiple regions (such as region 1, region 2, region 3). 2. It can be considered that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • the adjustment direction and adjustment distance for adjusting the shooting position of the movable camera can be determined based on the position information , And then the movable camera can be moved based on the adjustment direction, or the electronic device carrying the movable camera can also be moved based on the adjustment direction.
  • the electronic device is an unmanned device for sale
  • the image corresponding to the preset reference part of the target user’s face is in area 1 of the target image
  • the movable camera moves down.
  • the movable camera can be moved from the initial position to the back of the screen, that is, the movable camera can be moved downward.
  • the electronic device is a facial payment device that can provide users with facial payment
  • the image corresponding to the preset reference part of the target user’s face is in area 3 in the target image
  • Control the face brushing device to move up.
  • the above adjustment method for the shooting position of the movable camera is an optional and achievable adjustment method.
  • the embodiments of the specification do not specifically limit this.
  • the target image including the face image of the target user collected by the movable camera can be acquired based on the preset detection period, and then the target user’s image in the target image can be measured during the detection period.
  • the facial image is analyzed to determine the position information of the image corresponding to the reference part of the target user’s face in the target image, and then the current shooting position of the movable camera is determined based on the position information and the position corresponding to the target user’s reference part
  • the shooting position of the movable camera is adjusted based on the position information so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • the position information of the image corresponding to the preset reference part of the target user’s face in the target image can be detected in time, and timely Adjust the shooting position of the movable camera.
  • the embodiment of this specification provides a method for acquiring facial images.
  • the target image including the facial image of the target user collected by the movable camera the facial image of the target user in the target image is analyzed to determine the target user’s face.
  • the position information of the image corresponding to the preset reference part in the target image is adjusted based on the position information when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part
  • the shooting position of the movable camera may match the shooting position of the movable camera with the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiment of the present specification provides a method for acquiring facial images.
  • the execution subject of the method may be an electronic device that can provide users with services such as facial payment.
  • the electronic device may be equipped with a movable camera.
  • the electronic device can be a face-swiping payment device, an unmanned sales device, etc.
  • the method may specifically include the following steps:
  • the target image including the facial image of the target user collected by the movable camera is acquired.
  • the facial image of the target user in the target image is analyzed, and the position information of the image corresponding to the preset reference part in the target user's face is determined in the target image.
  • the preset center range may be a preset range area of any shape and size.
  • the preset center range may be a range area corresponding to a circle whose center point of the target image is a circle point and a preset distance is a radius.
  • the target image can be divided into 9 regions, where region 5 can be a preset center range. If the image corresponding to the preset reference part in the target user's face is not in region 5, The relative position information between the image corresponding to the preset reference part in the target user's face and the preset center range in the target image can be acquired. For example, if the image corresponding to the preset reference location in the target user's face is in area 3 in the target image, the relative position information may be the relative position information between the center point of area 5 and the center point of area 3.
  • the shooting position of the movable camera is adjusted so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • S410 may also have multiple implementation manners.
  • the first movement direction and the first movement distance may be determined based on relative position information.
  • the target image includes 9 regions. If the image corresponding to the preset reference part of the target user’s face is in region 2 in the target image, and the preset center range is the range where region 5 is located , It can be determined that the first moving direction is downward, and the first moving distance is the linear distance between the center points of the area 3 and the area 5.
  • the target user's reference position is located at point A, point A is in area 4, and is not on the same horizontal line as the center point B of area 5, then the first movement direction may include the first sub-movement direction
  • the second sub-movement direction can be determined according to the relative position information between point A and the center point B of area 5 to adjust the shooting position of the movable camera to the first on the same horizontal line as the center point B of area 5
  • a sub-movement direction ie downward
  • a second sub-movement direction ie to the right used to adjust the shooting position of the movable camera to the center point B of area 5 is determined.
  • the relative position information Determine the first sub-movement distance and the second sub-movement distance respectively.
  • the movable camera is controlled to move along the preset track.
  • the movable camera in the electronic device is a rotatable camera, or the lens in the movable camera can be rotated in the movable camera, if the image corresponding to the preset reference part in the target user’s face is located In the horizontal direction of the preset center range, the first rotation direction and the first rotation angle are determined based on the relative position information.
  • the first rotation direction and the first rotation angle may be determined based on the relative position information.
  • the movable camera or the lens of the movable camera is rotated.
  • the movable camera in the electronic device is a rotatable camera, or the lens in the movable camera can be rotated in the movable camera, if the image corresponding to the preset reference part in the target user’s face is located In a direction other than the horizontal direction of the preset center range, the second movement direction, the second movement distance, the second rotation direction, and the second rotation angle are determined based on the relative position information.
  • the target user's reference position is located at point C, and point C is in area 3.
  • the second moving direction may be downward, and the second moving distance may be between the center point of area 3 and The linear distance between the center points of the area 6, the second rotation direction may be left, and the second rotation angle may be determined by the distance between the center point of the area 4 and the center point of the area 5.
  • the movable camera is controlled to move along the track to the horizontal direction of the preset center range.
  • the movable camera or the lens of the movable camera is rotated.
  • the third movement direction and the third movement distance of the lens for moving the movable camera can be determined based on the relative position information .
  • the method for determining the third movement direction and the third movement distance can refer to the method for determining the first movement distance and the second movement distance described above, which will not be repeated here.
  • the lens of the movable camera is controlled to move along the preset track within the movable camera.
  • the embodiment of this specification provides a method for acquiring facial images.
  • the target image including the facial image of the target user collected by the movable camera the facial image of the target user in the target image is analyzed to determine the target user’s face.
  • the position information of the image corresponding to the preset reference part in the target image is adjusted based on the position information when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part
  • the shooting position of the movable camera may match the shooting position of the movable camera with the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiment of this specification provides a facial recognition device, including a movable camera and a controller, wherein:
  • the movable camera may be located on the back of the screen of the facial recognition device, and is used to collect the target image including the facial image of the target user through the screen of the facial recognition device.
  • the controller can be used to obtain the target image including the face image of the target user collected by the movable camera, analyze the face image of the target user in the target image, and determine the corresponding reference part in the face of the target user According to the position information of the image in the target image, if it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part, adjust the position of the movable camera based on the position information The shooting position, so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • the facial recognition device can be a facial recognition device that can be used independently to provide users with a facial recognition payment service, or the facial recognition device can also be configured in an unmanned sales device to provide users with facial recognition payment. Service equipment.
  • the embodiment of this specification provides a facial recognition device that acquires a target image including the target user's facial image collected by a movable camera, analyzes the target user's facial image in the target image, and determines the preset in the target user's face The position information of the image corresponding to the reference part of the target image in the target image. If it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part, adjust the movable based on the position information The shooting position of the camera so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiment of this specification provides yet another facial recognition device.
  • the facial recognition device includes all the functional units of the facial recognition device of the third embodiment, and on the basis of it, it has been improved.
  • the content of the improvements is as follows:
  • the controller is further configured to: based on the position information, determine whether the image corresponding to the preset reference part in the target user's face is within the preset center range of the target image, and the image corresponding to the preset reference part in the target user's face is not in the In the case of the preset center range of the target image, obtain the relative position information between the image corresponding to the preset reference part in the target user's face and the preset center range in the target image, and adjust the movable camera based on the relative position information Shooting location.
  • the controller is further configured to determine the first movement direction and the first movement distance based on the relative position information, and control the movable camera to move along the preset track based on the first movement direction and the first movement distance.
  • the controller is further configured to: if the image corresponding to the preset reference part in the target user’s face is located in the horizontal direction of the preset center range, determine the first rotation direction and the first rotation angle based on the relative position information, based on the first The rotation direction and the first rotation angle, rotate the movable camera or the lens of the movable camera.
  • the controller is further configured to: if the image corresponding to the preset reference part of the target user's face is located in a direction other than the horizontal direction of the preset center range, determine the second moving direction, the second moving distance, and the second moving distance based on the relative position information.
  • the second rotation direction and the second rotation angle based on the second movement direction and the second movement distance, control the movable camera to move along the track to the horizontal direction of the preset center range, and rotate based on the second rotation direction and the second rotation angle Movable camera or lens of movable camera.
  • the controller is also used for determining the third movement direction and the third movement distance of the lens of the movable camera based on the relative position information, and controlling the movement of the lens of the movable camera based on the third movement direction and the third movement distance
  • the movable camera can move along the preset track.
  • the controller is also used for determining the moving direction and moving distance for moving the facial recognition device based on the position information, and controlling the facial recognition device to move along a preset track based on the moving direction and the moving distance.
  • a preset track can be set, and the controller can control the facial device to move along the preset track according to the determined moving direction and moving distance, so that the shooting position of the movable camera is consistent with the target user's reference Match the positions corresponding to the parts.
  • the embodiment of this specification provides a facial recognition device that acquires a target image including the target user's facial image collected by a movable camera, analyzes the target user's facial image in the target image, and determines the preset in the target user's face The position information of the image corresponding to the reference part of the target image in the target image. If it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part, adjust the movable based on the position information The shooting position of the camera so that the shooting position of the movable camera matches the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiment of this specification also provides a facial image acquisition device, as shown in FIG. 6.
  • the facial image acquisition device includes: an image acquisition module 601, a position acquisition module 602, and a position adjustment module 603.
  • the image acquisition module 601 is used to acquire the target image including the facial image of the target user collected by the movable camera.
  • Position acquisition module 602 configured to analyze the target user's facial image in the target image, and determine the position information in the target image of the image corresponding to the reference part preset in the target user's face;
  • the adjustment module 603 is configured to adjust the position information based on the position information when it is determined that the current shooting position of the movable camera does not match the position corresponding to the reference part of the target user based on the position information.
  • the shooting position of the movable camera is adapted to match the shooting position of the movable camera with the position corresponding to the reference part of the target user.
  • the position adjustment module 603 is configured to: based on the position information, determine whether an image corresponding to a preset reference part in the target user's face is within a preset center range of the target image; In the case that the image corresponding to the preset reference part in the target user's face is not in the preset center range of the target image, the image corresponding to the preset reference part in the target user's face is acquired in the target image , Relative position information with the preset center range; based on the relative position information, adjusting the shooting position of the movable camera.
  • the position adjustment module 603 is configured to: determine a first movement direction and a first movement distance based on the relative position information; and control the first movement direction and a first movement distance based on the first movement direction and the first movement distance.
  • the movable camera moves along the preset track.
  • the position adjustment module 603 is configured to: if the image corresponding to the preset reference part in the target user's face is located in the horizontal direction of the preset center range, based on the relative position information , Determine a first rotation direction and a first rotation angle; based on the first rotation direction and the first rotation angle, rotate the movable camera or the lens of the movable camera.
  • the position adjustment module 603 is configured to: if the image corresponding to the preset reference part in the target user's face is located in a direction other than the horizontal direction of the preset center range, based on the Relative position information, determine the second movement direction, the second movement distance, the second rotation direction and the second rotation angle; based on the second movement direction and the second movement distance, control the movable camera to move along the track to the In the horizontal direction of the preset center range; based on the second rotation direction and the second rotation angle, rotate the movable camera or the lens of the movable camera.
  • the position adjustment module 603 is configured to: based on the relative position information, determine a third movement direction and a third movement distance for moving the lens of the movable camera;
  • the lens of the movable camera is controlled to move along a preset track within the movable camera.
  • the embodiment of this specification provides a facial image acquisition device, which acquires a target image including a target user’s facial image collected by a movable camera, analyzes the target user’s facial image in the target image, and determines the target user’s face.
  • the position information of the image corresponding to the preset reference part in the target image is adjusted based on the position information when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part
  • the shooting position of the movable camera may match the shooting position of the movable camera with the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiment of this specification also provides a facial image acquisition device, as shown in FIG. 7.
  • the facial image acquisition device may be the electronic device provided in the foregoing embodiment.
  • Facial image acquisition devices may have relatively large differences due to different configurations or performances, and may include one or more processors 701 and a memory 702, and the memory 702 may store one or more storage application programs or data. Among them, the memory 702 may be short-term storage or persistent storage.
  • the application program stored in the memory 702 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions in the facial image acquisition device.
  • the processor 701 may be configured to communicate with the memory 702, and execute a series of computer executable instructions in the memory 702 on the facial image acquisition device.
  • the facial image collection device may also include one or more power supplies 703, one or more wired or wireless network interfaces 704, one or more input and output interfaces 705, and one or more keyboards 706.
  • the facial image acquisition device includes a memory and one or more programs, one or more programs are stored in the memory, and one or more programs may include one or more modules, and Each module may include a series of computer-executable instructions in a facial image acquisition device, and the one or more programs configured to be executed by one or more processors include computer-executable instructions for performing the following: The target image including the face image of the target user collected by the mobile camera; the face image of the target user in the target image is analyzed, and the image corresponding to the preset reference part in the target user’s face is determined to be in the target image.
  • the position information in the target image if it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the reference part of the target user, adjust based on the position information
  • the shooting position of the movable camera is such that the shooting position of the movable camera matches the position corresponding to the reference part of the target user.
  • the adjustment is performed based on the position information.
  • the shooting position of the movable camera includes: determining, based on the position information, whether an image corresponding to a preset reference part in the target user's face is within a preset center range of the target image; in the target user's face When the image corresponding to the preset reference part is not in the preset center range of the target image, the image corresponding to the preset reference part in the target user’s face is acquired.
  • Relative position information between the center ranges based on the relative position information, adjust the shooting position of the movable camera.
  • the adjusting the shooting position of the movable camera based on the relative position information includes: determining a first movement direction and a first movement distance based on the relative position information; and based on the first movement direction And the first moving distance, controlling the movable camera to move along a preset track.
  • the adjusting the shooting position of the movable camera based on the relative position information includes: if the image corresponding to the preset reference part in the target user's face is located in the horizontal direction of the preset center range Above, the first rotation direction and the first rotation angle are determined based on the relative position information; based on the first rotation direction and the first rotation angle, the movable camera or the lens of the movable camera is rotated .
  • the adjusting the shooting position of the movable camera based on the relative position information includes: if the image corresponding to the preset reference part in the target user's face is located in the horizontal direction of the preset center range In other directions, based on the relative position information, determine the second movement direction, second movement distance, second rotation direction and second rotation angle; based on the second movement direction and second movement distance, control the The movable camera moves along the track to the horizontal direction of the preset center range; based on the second rotation direction and the second rotation angle, the movable camera or the lens of the movable camera is rotated.
  • the adjusting the shooting position of the movable camera based on the relative position information includes: determining, based on the relative position information, a third movement direction and a second movement direction for moving the lens of the movable camera. Three moving distances; based on the third moving direction and the third moving distance, controlling the lens of the movable camera to move along a preset track within the movable camera.
  • the embodiment of this specification provides a facial image acquisition device, which acquires a target image including the facial image of the target user collected by a movable camera, analyzes the facial image of the target user in the target image, and determines the target user’s face.
  • the position information of the image corresponding to the preset reference part in the target image is adjusted based on the position information when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part
  • the shooting position of the movable camera may match the shooting position of the movable camera with the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • the embodiments of this specification also provide a computer-readable storage medium, and a computer program is stored on the computer-readable storage medium. In order to avoid repetition, I won’t repeat them here.
  • the computer-readable storage medium such as read-only memory (Read-Only Memory, ROM for short), random access memory (Random Access Memory, RAM for short), magnetic disk, or optical disk, etc.
  • the embodiment of this specification provides a computer-readable storage medium that acquires a target image including the facial image of the target user collected by a movable camera, analyzes the target user’s facial image in the target image, and determines the target user’s face.
  • the position information of the image corresponding to the preset reference part in the target image is adjusted based on the position information when it is determined based on the position information that the current shooting position of the movable camera does not match the position corresponding to the target user's reference part
  • the shooting position of the movable camera may match the shooting position of the movable camera with the position corresponding to the reference part of the target user. In this way, the problem of inaccurate facial images of target users collected for target users of different heights caused by the fixed shooting position of the camera can be avoided, that is, the problem of poor facial image collection accuracy can be solved.
  • a technological improvement can be clearly distinguished between hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to method flow).
  • hardware improvements for example, improvements to the circuit structure of diodes, transistors, switches, etc.
  • software improvements improvements to method flow.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • the controller can be implemented in any suitable manner.
  • the controller can take the form of, for example, a microprocessor or a processor and a computer-readable medium storing computer-readable program codes (such as software or firmware) executable by the (micro)processor. , Logic gates, switches, application specific integrated circuits (ASICs), programmable logic controllers and embedded microcontrollers. Examples of controllers include but are not limited to the following microcontrollers: ARC625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicon Labs C8051F320, the memory controller can also be implemented as part of the memory control logic.
  • controllers in addition to implementing the controller in a purely computer-readable program code manner, it is entirely possible to program the method steps to make the controller use logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded logic.
  • the same function can be realized in the form of a microcontroller or the like. Therefore, such a controller can be regarded as a hardware component, and the devices included in it for realizing various functions can also be regarded as a structure within the hardware component. Or even, the device for realizing various functions can be regarded as both a software module for realizing the method and a structure within a hardware component.
  • a typical implementation device is a computer.
  • the computer may be, for example, a personal computer, a laptop computer, a cell phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or Any combination of these devices.
  • one or more embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification may adopt computer programs implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The form of the product.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction device.
  • the device implements the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so as to execute on the computer or other programmable equipment.
  • the instructions provide steps for implementing the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram.
  • the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-permanent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer readable media.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology.
  • the information can be computer-readable instructions, data structures, program modules, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disc (DVD) or other optical storage, Magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • one or more embodiments of this specification can be provided as a method, a system or a computer program product. Therefore, one or more embodiments of this specification may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification may adopt computer programs implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The form of the product.
  • computer-usable storage media including but not limited to disk storage, CD-ROM, optical storage, etc.
  • One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules.
  • program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types.
  • One or more embodiments of this specification can also be practiced in distributed computing environments. In these distributed computing environments, tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

Landscapes

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

Abstract

本说明书实施例公开了一种面部图像的采集方法、装置、设备及面部识别设备，所述方法包括：获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。

Description

面部图像的采集及面部识别 技术领域
本说明书涉及计算机技术领域，尤其涉及一种面部图像的采集方法、装置、设备及面部识别设备。
背景技术
随着物联网技术的飞速发展，无人售卖设备深入人们的生活，为提高用户支付的便捷性，无人售卖设备开始为用户提供刷脸支付的服务，但如何准确的采集用户的面部图像，成为设备运营商关注的焦点。
目前，在无人售卖设备中，可以配置有面部识别设备，用于获取刷脸用户的面部图像，但是由于面部识别设备的高度是固定的，所以，对于身高与面部识别设备高度不处于同一水平面的刷脸用户，面部设备采集到的该刷脸用户的面部图像就存在不准确的问题，导致无人售卖设备无法准确的为用户提供刷脸支付的服务，因此，需要一种能够准确的获取用户的面部图像，以及时准确的为用户提供刷脸支付服务的解决方案。
发明内容
本说明书实施例的目的是提供一种面部图像的采集方法、装置、设备及面部识别设备，以提供一种能够准确的获取用户的面部图像，以及时准确的为用户提供刷脸支付服务的解决方案。
为了实现上述技术方案，本说明书实施例是这样实现的：
第一方面，本说明书实施例提供的一种面部图像的采集方法，所述方法包括：获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部、预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
第二方面，本说明书实施例提供的一种面部识别设备，包括可移动摄像头和控制器，其中：所述可移动摄像头位于所述面部识别设备屏幕的背面，用于透过所述面部识别设备的屏幕，采集包括目标用户的面部图像在内的目标图像；所述控制器，用于获取可移动摄像头采集到的包括所述目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的 拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
第三方面，本说明书实施例提供了一种面部图像的采集装置，所述装置包括：图像获取模块，用于获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；位置获取模块，用于对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；位置调整模块，用于在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
第四方面，本说明书实施例提供了一种面部图像的采集设备，所述面部图像的采集设备包括：处理器；以及被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
附图说明
为了更清楚地说明本说明书实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本说明书中记载的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本说明书一种面部图像的采集方法实施例的流程图；
图2为本说明书一种目标图像的采集方法的示意图；
图3为本说明书一种位置信息的获取方法的示意图；
图4为本说明书又一种面部图像的采集方法实施例的流程图；
图5为本说明书一种目标图像的区域划分的示意图；
图6为本说明书又一种面部图像的采集装置实施例的结构示意图；
图7为本说明书另一种面部图像的采集设备的结构示意图。
具体实施方式
本说明书实施例提供一种面部图像的采集方法、装置、设备及面部识别设备。
为了使本技术领域的人员更好地理解本说明书中的技术方案，下面将结合本说明书实施例中的附图，对本说明书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说明书一部分实施例，而不是全部的实施例。基于本说明书中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本说明书保护的范围。
实施例一
如图1所示，本说明书实施例提供一种面部图像的采集方法，该方法的执行主体可以为能够为用户提供刷脸支付等服务的电子设备，其中，该电子设备可以配置有可移动摄像头，例如，该电子设备可以为刷脸支付设备、无人售卖设备等。该方法具体可以包括以下步骤：
在S102中，获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像。
在实施中，随着物联网技术的飞速发展，无人售卖设备深入人们的生活，为提高用户支付的便捷性，无人售卖设备开始为用户提供刷脸支付的服务，但如何准确的采集用户的面部图像，成为设备运营商关注的焦点。目前，在无人售卖设备中，可以配置有面部识别设备，用于获取刷脸用户的面部图像，但是由于面部识别设备的高度是固定的，所以，对于身高与面部识别设备高度不处于同一水平面的刷脸用户，面部设备采集到的该刷脸用户的面部图像就存在不准确的问题，导致无人售卖设备无法准确的为用户提供刷脸支付的服务，因此，需要一种能够准确的获取用户的面部图像，以及时准确的为用户提供刷脸支付服务的解决方案。为此，本说明书实施例提供一种可以解决上述问题的技术方案，具体可以参见下述内容。
以电子设备为无人售卖设备为例，当目标用户在该无人售卖设备的屏幕中选定商品并点击购买时，电子设备可以通过可移动摄像头采集包括目标用户的面部图像在内的目标图像，其中，可移动摄像头可预先设置于电子设备的指定位置，且可以位于与目标用户相对的预设初始位置。例如，如图2所示，无人售卖设备中的可移动摄像头可以位于屏幕上侧的初始位置，在无人售卖设备接收到目标用户针对某一商品的购买指令的情况下，可以通过在初始位置的可移动摄像头获取包括目标用户的面部图像在内的目标图像。
在S104中，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息。
其中，预设的基准部位可以是眼睛、鼻子、嘴巴等任意预设部位。该基准部位可以用于使得摄像头能够采集到用户更准确更完整的面部图像。
在实施中，可以基于预设图像分析算法，对目标图像进行分析，确定目标用户面部 中预设的基准部位对应的图像在目标图像中的位置信息。
在获取位置信息时，可以将目标图像划分为多个区域，并根据目标用户面部中预设的基准部位对应的图像在目标图像中所处的区域信息，确定对应的位置信息。
例如，以预设的基准部位为鼻子为例，假设获取的目标图像如图3所示，目标用户面部中鼻子对应的图像位于目标图像中的区域2，则对应的位置信息可以为区域2所处的位置信息。
此外，上述位置信息的确定方法是一种可选地、可实现的确定方法，在实际应用场景中还可以有多种确定方法，本说明书实施例对此不作具体限定。
另外，为保证确定的位置信息的准确性，可以预设多个基准部位，并根据每个基准部位对应的图像在目标图像中的子位置信息，确定对应的位置信息。例如，假设基准部位包括眼睛、鼻子和耳朵，如果目标用户面部中眼睛和鼻子对应的图像在目标图像中都处于区域1，而目标用户面部中的耳朵对应的图像在目标图像中位于区域2，则可以确定目标用户面部中预设的基准部位对应的图像在目标图像中所处的位置信息为区域1所在的位置信息。
在S106中，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
在实施中，基于位置信息，可以确定可移动摄像头当前所处的拍摄位置，是否与目标用户的基准部位对应的位置相匹配。例如，如果可移动摄像头当前所处的拍摄位置，与目标用户的基准部位对应的位置处于同一水平线上，则可以认为可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。或者，如果可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置之间在同一水平面上的夹角，处于预设夹角范围内，则也可以认为可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
又或者，如图3所示，可以将目标图像划分为多个区域(如区域1、区域2、区域3)，如果目标用户面部中预设的基准部位对应的位置，处于目标图像中的区域2，则可以认为可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，可以基于位置信息，确定用于调整可移动摄像头的拍摄位置的调整方向和调整距离，然后可以将可移动摄像头基于调整方向进行移动，或者，还可以将承载可移动摄像头的电子设备基于调整方向进行移动。
例如，假设电子设备为无人售卖设备，获取的目标图像中，目标用户面部中预设的基准部位对应的图像在目标图像中处于区域1，则可以确定调整方向为向下，此时可以控制可移动摄像头向下移动。如图2所示的无人售卖设备，可以将可移动摄像头从初始 位置移动到屏幕的背侧，即向下移动可移动摄像头。
或者，假设电子设备为能够为用户提供刷脸支付的刷脸支付设备，目标用户面部中预设的基准部位对应的图像在目标图像中处于区域3，则可以确定调整方向为向上，此时可以控制刷脸设备向上移动。
上述可移动摄像头的拍摄位置的调整方法是一种可选地、可实现的调整方法，在实际应用场景中，还可以有多种调整方法，可以根据实际应用场景的不同而有所不同，本说明书实施例对此不做具体限定。
此外，在调整可移动摄像头的过程中，可以基于预设检测周期，获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，然后在检测周期内，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，然后在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，即使目标用户在可移动摄像头的拍摄位置的调整过程中，发生了位置的改变，也可以及时检测到目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，并及时对可移动摄像头的拍摄位置进行调整。
本说明书实施例提供一种面部图像的采集方法，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例二
如图4所示，本说明书实施例提供一种面部图像的采集方法，该方法的执行主体可以为能够为用户提供刷脸支付等服务的电子设备，其中，该电子设备可以配置有可移动摄像头，例如，该电子设备可以为刷脸支付设备、无人售卖设备等。该方法具体可以包括以下步骤：
在S402中，获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像。
在S404中，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息。
上述S402～S404的具体处理过程可以参见上述实施例一中S102～S104的相关内容， 在此不再赘述。
在S406中，基于位置信息，确定目标用户面部中预设的基准部位对应的图像是否处于目标图像的预设中心范围内。
其中，预设中心范围可以是任意形状和大小的预设范围区域，例如，预设中心范围可以是以目标图像的中心点为圆点，预设距离为半径的圆所对应的范围区域。
在S408中，在目标用户面部中预设的基准部位对应的图像未处于目标图像的预设中心范围的情况下，获取目标用户面部中预设的基准部位对应的图像在目标图像中，与预设中心范围之间的相对位置信息。
在实施中，如图5为例，目标图像可以被划分为9个区域，其中，区域5可以为预设中心范围，如果目标用户面部中预设的基准部位对应的图像未处于区域5，则可以获取目标用户面部中预设的基准部位对应的图像在目标图像中，与预设中心范围之间的相对位置信息。例如，如果目标用户面部中预设的基准部位对应的图像在目标图像中处于区域3，则相对位置信息可以为区域5的中心点和区域3的中心点之间的相对位置信息。
在S410中，基于相对位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
上述S410的具体处理过程可以参见上述实施例一中S106的相关内容，在此不再赘述。
此外，在实际应用场景中，S410还可以有多种实现方式，例如，可以基于相对位置信息，确定第一移动方向和第一移动距离。
在实施中，假设如图5所示，目标图像包括9个区域，如果目标用户面部中预设的基准部位对应的图像在目标图像中处于区域2，且预设中心范围为区域5所在的范围，则可以确定第一移动方向为向下，第一移动距离为区域3与区域5的中心点之间的直线距离。
或者，如图5所示，目标用户的基准部位位于点A，点A处于区域4内，且与区域5的中心点B不处于同一水平线上，则第一移动方向可以包括第一子移动方向和第二子移动方向，可以根据点A与区域5的中心点B之间的相对位置信息，确定用于将可移动摄像头的拍摄位置调整到与区域5的中心点B处于同一水平线上的第一子移动方向(即向下)，然后在确定用于将可移动摄像头的拍摄位置调整到区域5的中心点B的第二子移动方向(即向右)，同时，可以根据相对位置信息，分别确定第一子移动距离和第二子移动距离。
基于第一移动方向和第一移动距离，控制可移动摄像头沿预设轨道进行移动。
另外，在电子设备中的可移动摄像头为可旋转的摄像头，或者，可移动摄像头内的镜头可以在可移动摄像头内进行旋转的情况下，如果目标用户面部中预设的基准部位对 应的图像位于预设中心范围的水平方向上，则基于相对位置信息，确定第一旋转方向和第一旋转角度。
在实施中，如图5所示，如果目标用户的基准部位对应的图像位于区域4或区域6，则可以基于相对位置信息，确定第一旋转方向和第一旋转角度。
基于第一旋转方向和第一旋转角度，旋转可移动摄像头或可移动摄像头的镜头。
另外，在电子设备中的可移动摄像头为可旋转的摄像头，或者，可移动摄像头内的镜头可以在可移动摄像头内进行旋转的情况下，如果目标用户面部中预设的基准部位对应的图像位于预设中心范围的水平方向以外的方向上，则基于相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度。
在实施中，例如，如图5所示，目标用户的基准部位位于点C，点C处于区域3内，则第二移动方向可以为向下，第二移动距离可以为区域3的中心点与区域6的中心点之间的直线距离，第二旋转方向可以为向左，第二旋转角度可以由区域4的中心点与区域5的中心点之间的距离确定。
基于第二移动方向和第二移动距离，控制可移动摄像头沿轨道移动到预设中心范围的水平方向上。
基于第二旋转方向和第二旋转角度，旋转可移动摄像头或可移动摄像头的镜头。
此外，在电子设备中的可移动摄像头内的镜头可以在可移动摄像头内进行移动的情况下，可以基于相对位置信息，确定用于移动可移动摄像头的镜头的第三移动方向和第三移动距离。其中，第三移动方向和第三移动距离的确定方法可以参见上述第一移动距离和第二移动距离的确定方法，在此不再赘述。
基于第三移动方向和第三移动距离，控制可移动摄像头的镜头在可移动摄像头内沿预设轨道进行移动。
本说明书实施例提供一种面部图像的采集方法，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例三
本说明书实施例提供一种面部识别设备，包括可移动摄像头和控制器，其中：
可移动摄像头可以位于面部识别设备屏幕的背面，用于透过面部识别设备的屏幕，采集包括目标用户的面部图像在内的目标图像。
控制器，可以用于获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中所述目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
面部识别设备可以是能够独立进行使用的，用于为用户提供刷脸支付服务的刷脸支付设备，或者，面部识别设备还可以是配置于无人售卖设备中，用于为用户提供刷脸支付服务的设备。
本说明书实施例提供一种面部识别设备，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例四
本说明书实施例提供又一种面部识别设备。该面部识别设备包含了上述实施例三的面部识别设备的全部功能单元，并在其基础上，对其进行了改进，改进内容如下：
控制器，还用于：基于位置信息，确定目标用户面部中预设的基准部位对应的图像是否处于目标图像的预设中心范围内，在目标用户面部中预设的基准部位对应的图像未处于目标图像的预设中心范围的情况下，获取目标用户面部中预设的基准部位对应的图像在目标图像中，与预设中心范围之间的相对位置信息，基于相对位置信息，调整可移动摄像头的拍摄位置。
控制器，还用于：基于相对位置信息，确定第一移动方向和第一移动距离，基于第一移动方向和第一移动距离，控制可移动摄像头沿预设轨道进行移动。
控制器，还用于：如果目标用户面部中预设的基准部位对应的图像位于预设中心范围的水平方向上，则基于相对位置信息，确定第一旋转方向和第一旋转角度，基于第一旋转方向和第一旋转角度，旋转可移动摄像头或可移动摄像头的镜头。
控制器，还用于：如果目标用户面部中预设的基准部位对应的图像位于预设中心范 围的水平方向以外的方向上，则基于相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度，基于第二移动方向和第二移动距离，控制可移动摄像头沿轨道移动到预设中心范围的水平方向上，基于第二旋转方向和第二旋转角度，旋转可移动摄像头或可移动摄像头的镜头。
控制器，还用于：基于相对位置信息，确定用于移动可移动摄像头的镜头的第三移动方向和第三移动距离，基于第三移动方向和第三移动距离，控制可移动摄像头的镜头在可移动摄像头内沿预设轨道进行移动。
控制器，还用于：基于位置信息，确定用于移动面部识别设备的移动方向和移动距离，基于移动方向和移动距离，控制面部识别设备沿预设轨道进行移动。
在面部识别设备的背侧，可以设置有预设轨道，控制器可以根据确定的移动方向和移动距离，控制面部设备沿预设轨道进行移动，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。
本说明书实施例提供一种面部识别设备，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例五
以上为本说明书实施例提供的面部图像的采集方法，基于同样的思路，本说明书实施例还提供一种面部图像的采集装置，如图6所示。
该面部图像的采集装置包括：图像获取模块601、位置获取模块602和位置调整模块603，其中：图像获取模块601，用于获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；位置获取模块602，用于对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；位置调整模块603，用于在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
本说明书实施例中，所述位置调整模块603，用于：基于所述位置信息，确定所述目标用户面部中预设的基准部位对应的图像是否处于所述目标图像的预设中心范围内；在所述目标用户面部中预设的基准部位对应的图像未处于所述目标图像的预设中心范 围的情况下，获取所述目标用户面部中预设的基准部位对应的图像在所述目标图像中，与所述预设中心范围之间的相对位置信息；基于所述相对位置信息，调整所述可移动摄像头的拍摄位置。
本说明书实施例中，所述位置调整模块603，用于：基于所述相对位置信息，确定第一移动方向和第一移动距离；基于所述第一移动方向和第一移动距离，控制所述可移动摄像头沿预设轨道进行移动。
本说明书实施例中，所述位置调整模块603，用于：如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向上，则基于所述相对位置信息，确定第一旋转方向和第一旋转角度；基于所述第一旋转方向和所述第一旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
本说明书实施例中，所述位置调整模块603，用于：如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向以外的方向上，则基于所述相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度；基于所述第二移动方向和第二移动距离，控制所述可移动摄像头沿轨道移动到所述预设中心范围的水平方向上；基于所述第二旋转方向和第二旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
本说明书实施例中，所述位置调整模块603，用于：基于所述相对位置信息，确定用于移动所述可移动摄像头的镜头的第三移动方向和第三移动距离；
基于所述第三移动方向和第三移动距离，控制所述可移动摄像头的镜头在所述可移动摄像头内沿预设轨道进行移动。
本说明书实施例提供一种面部图像的采集装置，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例六
基于同样的思路，本说明书实施例还提供一种面部图像的采集设备，如图7所示。
所述面部图像的采集设备可以为上述实施例提供的电子设备。
面部图像的采集设备可因配置或性能不同而产生比较大的差异，可以包括一个或一个以上的处理器701和存储器702，存储器702中可以存储有一个或一个以上存储应用 程序或数据。其中，存储器702可以是短暂存储或持久存储。存储在存储器702的应用程序可以包括一个或一个以上模块(图示未示出)，每个模块可以包括对面部图像的采集设备中的一系列计算机可执行指令。更进一步地，处理器701可以设置为与存储器702通信，在面部图像的采集设备上执行存储器702中的一系列计算机可执行指令。面部图像的采集设备还可以包括一个或一个以上电源703，一个或一个以上有线或无线网络接口704，一个或一个以上输入输出接口705，一个或一个以上键盘706。
具体在本实施例中，面部图像的采集设备包括有存储器，以及一个或一个以上的程序，其中一个或者一个以上程序存储于存储器中，且一个或者一个以上程序可以包括一个或一个以上模块，且每个模块可以包括对面部图像的采集设备中的一系列计算机可执行指令，且经配置以由一个或者一个以上处理器执行该一个或者一个以上程序包含用于进行以下计算机可执行指令：获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
可选地，所述在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，包括：基于所述位置信息，确定所述目标用户面部中预设的基准部位对应的图像是否处于所述目标图像的预设中心范围内；在所述目标用户面部中预设的基准部位对应的图像未处于所述目标图像的预设中心范围的情况下，获取所述目标用户面部中预设的基准部位对应的图像在所述目标图像中，与所述预设中心范围之间的相对位置信息；基于所述相对位置信息，调整所述可移动摄像头的拍摄位置。
可选地，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：基于所述相对位置信息，确定第一移动方向和第一移动距离；基于所述第一移动方向和第一移动距离，控制所述可移动摄像头沿预设轨道进行移动。
可选地，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向上，则基于所述相对位置信息，确定第一旋转方向和第一旋转角度；基于所述第一旋转方向和所述第一旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
可选地，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向以外的方向上，则基于所述相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度；基于所述第二移动方向和第二移动距离，控制所述可移动摄 像头沿轨道移动到所述预设中心范围的水平方向上；基于所述第二旋转方向和第二旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
可选地，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：基于所述相对位置信息，确定用于移动所述可移动摄像头的镜头的第三移动方向和第三移动距离；基于所述第三移动方向和第三移动距离，控制所述可移动摄像头的镜头在所述可移动摄像头内沿预设轨道进行移动。
本说明书实施例提供一种面部图像的采集设备，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
实施例七
本说明书实施例还提供一种计算机可读存储介质，计算机可读存储介质上存储有计算机程序，该计算机程序被处理器执行时实现上述面部图像的采集方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。其中，所述的计算机可读存储介质，如只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、磁碟或者光盘等。
本说明书实施例提供一种计算机可读存储介质，通过获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像，对目标图像中目标用户的面部图像进行分析，确定目标用户面部中预设的基准部位对应的图像在目标图像中的位置信息，在基于位置信息确定可移动摄像头当前所处的拍摄位置与目标用户的基准部位对应的位置不匹配的情况下，基于位置信息，调整可移动摄像头的拍摄位置，以使可移动摄像头的拍摄位置与目标用户的基准部位对应的位置相匹配。这样，可以避免由于摄像头的拍摄位置的固定，而导致的对于不同身高的目标用户，所采集到的目标用户的面部图像不准确的问题，即可以解决面部图像采集准确性差的问题。
上述对本说明书特定实施例进行了描述。其它实施例在所附权利要求书的范围内。在一些情况下，在权利要求书中记载的动作或步骤可以按照不同于实施例中的顺序来执行并且仍然可以实现期望的结果。另外，在附图中描绘的过程不一定要求示出的特定顺序或者连续顺序才能实现期望的结果。在某些实施方式中，多任务处理和并行处理也是可以的或者可能是有利的。
在20世纪90年代，对于一个技术的改进可以很明显地区分是硬件上的改进(例 如，对二极管、晶体管、开关等电路结构的改进)还是软件上的改进(对于方法流程的改进)。然而，随着技术的发展，当今的很多方法流程的改进已经可以视为硬件电路结构的直接改进。设计人员几乎都通过将改进的方法流程编程到硬件电路中来得到相应的硬件电路结构。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device，PLD)(例如现场可编程门阵列(Field Programmable Gate Array，FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片PLD上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今，取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compiler)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language，HDL)，而HDL也并非仅有一种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
控制器可以按任何适当的方式实现，例如，控制器可以采取例如微处理器或处理器以及存储可由该(微)处理器执行的计算机可读程序代码(例如软件或固件)的计算机可读介质、逻辑门、开关、专用集成电路(Application Specific Integrated Circuit，ASIC)、可编程逻辑控制器和嵌入微控制器的形式，控制器的例子包括但不限于以下微控制器：ARC 625D、Atmel AT91SAM、Microchip PIC18F26K20以及Silicone Labs C8051F320，存储器控制器还可以被实现为存储器的控制逻辑的一部分。本领域技术人员也知道，除了以纯计算机可读程序代码方式实现控制器以外，完全可以通过将方法步骤进行逻辑编程来使得控制器以逻辑门、开关、专用集成电路、可编程逻辑控制器和嵌入微控制器等的形式来实现相同功能。因此这种控制器可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置也可以视为硬件部件内的结构。或者甚至，可以将用于实现各种功能的装置视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
上述实施例阐明的系统、装置、模块或单元，具体可以由计算机芯片或实体实现，或者由具有某种功能的产品来实现。一种典型的实现设备为计算机。具体的，计算机例如可以为个人计算机、膝上型计算机、蜂窝电话、相机电话、智能电话、个人数字助理、媒体播放器、导航设备、电子邮件设备、游戏控制台、平板计算机、可穿戴设备或者这些设备中的任何设备的组合。
为了描述的方便，描述以上装置时以功能分为各种单元分别描述。当然，在实施本说明书一个或多个实施例时可以把各单元的功能在同一个或多个软件和/或硬件中实现。
本领域内的技术人员应明白，本说明书的实施例可提供为方法、系统、或计算机程序产品。因此，本说明书一个或多个实施例可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本说明书一个或多个实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书的实施例是参照根据本说明书实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存 储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括所述要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本说明书的实施例可提供为方法、系统或计算机程序产品。因此，本说明书一个或多个实施例可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本说明书一个或多个实施例可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本说明书一个或多个实施例可以在由计算机执行的计算机可执行指令的一般上下文中描述，例如程序模块。一般地，程序模块包括执行特定任务或实现特定抽象数据类型的例程、程序、对象、组件、数据结构等等。也可以在分布式计算环境中实践本说明书一个或多个实施例，在这些分布式计算环境中，由通过通信网络而被连接的远程处理设备来执行任务。在分布式计算环境中，程序模块可以位于包括存储设备在内的本地和远程计算机存储介质中。
本说明书中的各个实施例均采用递进的方式描述，各个实施例之间相同相似的部分互相参见即可，每个实施例重点说明的都是与其他实施例的不同之处。尤其，对于系统实施例而言，由于其基本相似于方法实施例，所以描述的比较简单，相关之处参见方法实施例的部分说明即可。
以上所述仅为本说明书的实施例而已，并不用于限制本说明书。对于本领域技术人员来说，本说明书可以有各种更改和变化。凡在本说明书的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本说明书的权利要求范围之内。

Claims (15)

  1. 一种面部图像的采集方法，所述方法包括：
    获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；
    对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；
    在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
  2. 根据权利要求1所述的方法，所述在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，包括：
    基于所述位置信息，确定所述目标用户面部中预设的基准部位对应的图像是否处于所述目标图像的预设中心范围内；
    在所述目标用户面部中预设的基准部位对应的图像未处于所述目标图像的预设中心范围的情况下，获取所述目标用户面部中预设的基准部位对应的图像在所述目标图像中，与所述预设中心范围之间的相对位置信息；
    基于所述相对位置信息，调整所述可移动摄像头的拍摄位置。
  3. 根据权利要求2所述的方法，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：
    基于所述相对位置信息，确定第一移动方向和第一移动距离；
    基于所述第一移动方向和第一移动距离，控制所述可移动摄像头沿预设轨道进行移动。
  4. 根据权利要求2所述的方法，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：
    如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向上，则基于所述相对位置信息，确定第一旋转方向和第一旋转角度；
    基于所述第一旋转方向和所述第一旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
  5. 根据权利要求3所述的方法，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：
    如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向以外的方向上，则基于所述相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度；
    基于所述第二移动方向和第二移动距离，控制所述可移动摄像头沿轨道移动到所述预设中心范围的水平方向上；
    基于所述第二旋转方向和第二旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
  6. 根据权利要求2所述的方法，所述基于所述相对位置信息，调整所述可移动摄像头的拍摄位置，包括：
    基于所述相对位置信息，确定用于移动所述可移动摄像头的镜头的第三移动方向和第三移动距离；
    基于所述第三移动方向和第三移动距离，控制所述可移动摄像头的镜头在所述可移动摄像头内沿预设轨道进行移动。
  7. 一种面部识别设备，包括可移动摄像头和控制器，其中：
    所述可移动摄像头位于所述面部识别设备屏幕的背面，用于透过所述面部识别设备的屏幕，采集包括目标用户的面部图像在内的目标图像；
    所述控制器，用于获取可移动摄像头采集到的包括所述目标用户的面部图像在内的目标图像；对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
  8. 根据权利要求7所述的面部识别设备，所述控制器，还用于：
    基于所述位置信息，确定用于移动所述面部识别设备的移动方向和移动距离；
    基于所述移动方向和移动距离，控制所述面部识别设备沿预设轨道进行移动。
  9. 一种面部图像的采集装置，所述装置包括：
    图像获取模块，用于获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；
    位置获取模块，用于对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；
    位置调整模块，用于在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
  10. 根据权利要求9所述的装置，所述位置调整模块，用于：
    基于所述位置信息，确定所述目标用户面部中预设的基准部位对应的图像是否处于所述目标图像的预设中心范围内；
    在所述目标用户面部中预设的基准部位对应的图像未处于所述目标图像的预设中心范围的情况下，获取所述目标用户面部中预设的基准部位对应的图像在所述目标图像中，与所述预设中心范围之间的相对位置信息；
    基于所述相对位置信息，调整所述可移动摄像头的拍摄位置。
  11. 根据权利要求10所述的装置，所述位置调整模块，用于：
    基于所述相对位置信息，确定第一移动方向和第一移动距离；
    基于所述第一移动方向和第一移动距离，控制所述可移动摄像头沿预设轨道进行移动。
  12. 根据权利要求10所述的装置，所述位置调整模块，用于：
    如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向上，则基于所述相对位置信息，确定第一旋转方向和第一旋转角度；
    基于所述第一旋转方向和所述第一旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
  13. 根据权利要求11所述的装置，所述位置调整模块，用于：
    如果所述目标用户面部中预设的基准部位对应的图像位于所述预设中心范围的水平方向以外的方向上，则基于所述相对位置信息，确定第二移动方向、第二移动距离、第二旋转方向和第二旋转角度；
    基于所述第二移动方向和第二移动距离，控制所述可移动摄像头沿轨道移动到所述预设中心范围的水平方向上；
    基于所述第二旋转方向和第二旋转角度，旋转所述可移动摄像头或所述可移动摄像头的镜头。
  14. 根据权利要求10所述的装置，所述位置调整模块，用于：
    基于所述相对位置信息，确定用于移动所述可移动摄像头的镜头的第三移动方向和第三移动距离；
    基于所述第三移动方向和第三移动距离，控制所述可移动摄像头的镜头在所述可移动摄像头内沿预设轨道进行移动。
  15. 一种面部图像的采集设备，所述面部图像的采集设备包括：
    处理器；以及
    被安排成存储计算机可执行指令的存储器，所述可执行指令在被执行时使所述处理器：
    获取可移动摄像头采集到的包括目标用户的面部图像在内的目标图像；
    对所述目标图像中所述目标用户的面部图像进行分析，确定所述目标用户面部中预设的基准部位对应的图像在所述目标图像中的位置信息；
    在基于所述位置信息确定所述可移动摄像头当前所处的拍摄位置与所述目标用户的基准部位对应的位置不匹配的情况下，基于所述位置信息，调整所述可移动摄像头的拍摄位置，以使所述可移动摄像头的拍摄位置与所述目标用户的基准部位对应的位置相匹配。
PCT/CN2021/087627 2020-04-24 2021-04-16 面部图像的采集及面部识别 WO2021213249A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010332373.4A CN111242106A (zh) 2020-04-24 2020-04-24 一种面部图像的采集方法、装置、设备及面部识别设备
CN202010332373.4 2020-04-24

Publications (1)

Publication Number Publication Date
WO2021213249A1 true WO2021213249A1 (zh) 2021-10-28

Family

ID=70880824

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/087627 WO2021213249A1 (zh) 2020-04-24 2021-04-16 面部图像的采集及面部识别

Country Status (2)

Country Link
CN (1) CN111242106A (zh)
WO (1) WO2021213249A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111242106A (zh) * 2020-04-24 2020-06-05 支付宝(杭州)信息技术有限公司 一种面部图像的采集方法、装置、设备及面部识别设备
CN112560598B (zh) * 2020-12-02 2022-04-08 支付宝(杭州)信息技术有限公司 一种活体检测方法、装置及设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100061586A1 (en) * 2008-09-10 2010-03-11 Sony Corporation Tv with viewer-adapted height and angle adjustment
CN108965713A (zh) * 2018-08-01 2018-12-07 上海小蚁科技有限公司 图像采集方法、装置以及计算机可读存储介质
CN209265605U (zh) * 2018-12-28 2019-08-16 广州利肯电子科技有限公司 一种可检测活体人脸识别摄像头的自助收款机
CN110460772A (zh) * 2019-08-14 2019-11-15 广州织点智能科技有限公司 摄像头自动调节方法、装置、设备和存储介质
CN111242106A (zh) * 2020-04-24 2020-06-05 支付宝(杭州)信息技术有限公司 一种面部图像的采集方法、装置、设备及面部识别设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100061586A1 (en) * 2008-09-10 2010-03-11 Sony Corporation Tv with viewer-adapted height and angle adjustment
CN108965713A (zh) * 2018-08-01 2018-12-07 上海小蚁科技有限公司 图像采集方法、装置以及计算机可读存储介质
CN209265605U (zh) * 2018-12-28 2019-08-16 广州利肯电子科技有限公司 一种可检测活体人脸识别摄像头的自助收款机
CN110460772A (zh) * 2019-08-14 2019-11-15 广州织点智能科技有限公司 摄像头自动调节方法、装置、设备和存储介质
CN111242106A (zh) * 2020-04-24 2020-06-05 支付宝(杭州)信息技术有限公司 一种面部图像的采集方法、装置、设备及面部识别设备

Also Published As

Publication number Publication date
CN111242106A (zh) 2020-06-05

Similar Documents

Publication Publication Date Title
WO2021213249A1 (zh) 面部图像的采集及面部识别
TWI754818B (zh) 支付方法、裝置及系統
KR102316230B1 (ko) 이미지 처리 방법 및 장치
WO2021135867A1 (zh) 一种镜头模组的对焦方法、装置及设备
CN108629220A (zh) 一种二维码识读方法、装置及设备
TW201911173A (zh) 一種指標異常檢測方法、裝置以及電子設備
WO2021223675A1 (zh) 风险检测
WO2021169420A1 (zh) 基于多个图像帧的视觉定位
CN109034183A (zh) 一种目标检测方法、装置及设备
TWI729675B (zh) 互動界面的顯示方法、裝置及設備
US11036967B2 (en) Method and device for face selection, recognition and comparison
KR20210145723A (ko) 렌즈의 하나 이상의 파라미터를 결정하는 장치, 시스템 및 방법
US11543299B2 (en) Method, apparatus, touch chip and electronic device for determining temperature status of touch screen
CN110032328A (zh) 一种操作对象的尺寸调节方法及装置
WO2021056450A1 (zh) 图像模板的更新方法、设备及存储介质
US11222125B1 (en) Biometric recognition attack test methods, apparatuses, and devices
US9536298B2 (en) Electronic device and method for detecting surface flaw of object
EP3940588A1 (en) Fingerprint image processing methods and apparatuses
CN110530398A (zh) 一种电子地图精度检测的方法及装置
WO2020244234A1 (zh) 图形码的展示方法及装置
JP2019186698A (ja) 情報処理装置、処理方法、及びプログラム
US20230145987A1 (en) Processing method and electronic device
TW202203028A (zh) 生物特徵識別的攻擊測試方法、裝置及設備
CN114706048A (zh) 雷达和摄像头联合标定的校准方法及装置
CN116246325A (zh) 人脸关键点的检测方法、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: 21792560

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: 21792560

Country of ref document: EP

Kind code of ref document: A1