CN112215084A - Identification object determination method, device, equipment and storage medium - Google Patents

Identification object determination method, device, equipment and storage medium Download PDF

Info

Publication number
CN112215084A
CN112215084A CN202010983486.0A CN202010983486A CN112215084A CN 112215084 A CN112215084 A CN 112215084A CN 202010983486 A CN202010983486 A CN 202010983486A CN 112215084 A CN112215084 A CN 112215084A
Authority
CN
China
Prior art keywords
face
size value
determining
preset
face size
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010983486.0A
Other languages
Chinese (zh)
Inventor
康家梁
吴文川
傅宜生
沈玺
卞凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Unionpay Co Ltd
Original Assignee
China Unionpay Co Ltd
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 China Unionpay Co Ltd filed Critical China Unionpay Co Ltd
Priority to CN202010983486.0A priority Critical patent/CN112215084A/en
Publication of CN112215084A publication Critical patent/CN112215084A/en
Priority to PCT/CN2021/117383 priority patent/WO2022057719A1/en
Priority to TW110134673A priority patent/TWI804988B/en
Pending legal-status Critical Current

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Image Analysis (AREA)
  • Geophysics And Detection Of Objects (AREA)
  • Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
  • Automatic Analysis And Handling Materials Therefor (AREA)

Abstract

The embodiment of the application provides a method, a device, equipment and a storage medium for determining an identification object. The method comprises the following steps: acquiring a shooting preview image, wherein the shooting preview image comprises at least two human faces; extracting feature information of each face of at least two faces in a shot preview image, wherein the feature information comprises a face size value; and determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face. According to the embodiment of the application, the appropriate target face can be selected from at least two faces as the recognition object in the face acquisition process, and the accuracy rate of determining the recognition object is improved.

Description

Identification object determination method, device, equipment and storage medium
Technical Field
The present application relates to the field of computer vision technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining an identification object.
Background
At present, the face recognition is widely applied to the fields of production, finance, safety, traffic and the like due to the characteristics of accuracy, safety, convenience and the like. Such as attendance machines, unmanned retail machines, access control systems, and the like.
However, because the use environment of face recognition is open, a plurality of faces often appear in the process of face acquisition, and are particularly obvious in queuing scenes, such as face brushing payment, gate stop, personnel check-in and other scenes. Therefore, an error in determination of the recognition target is easily caused, and the accuracy of determination of the recognition target is poor.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for determining an identification object, which can improve the accuracy of determining the identification object.
In a first aspect, an embodiment of the present application provides an identification object determining method, where the method includes:
acquiring a shooting preview image, wherein the shooting preview image comprises at least two human faces;
extracting feature information of each face of at least two faces in a shot preview image, wherein the feature information comprises a face size value;
and determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face.
In a second aspect, an embodiment of the present application provides an identification object determining apparatus, including:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a shooting preview image, and the shooting preview image comprises at least two human faces;
the device comprises an extraction module, a preview module and a display module, wherein the extraction module is used for extracting the characteristic information of each face in at least two faces in a shot preview image, and the characteristic information comprises a face size value;
and the determining module is used for determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face.
In a third aspect, an embodiment of the present application provides an identification object determining apparatus, including: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the method of identifying an object as described in the first aspect or any of the realizable forms of the first aspect.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, where computer program instructions are stored on the computer-readable storage medium, and when executed by a processor, the computer program instructions implement the identification object determination method described in the first aspect or any of the realizable manners of the first aspect.
According to the method, the device, the equipment and the storage medium for determining the recognition object, the face size value of each face in the shot preview image is extracted, and the face with the face size value meeting the preset recognition condition is determined to be the recognition object according to the face size value of each face. The method can select a proper target face as the recognition object in the face acquisition process, realize the accurate determination of the recognition object and improve the accuracy of the determination of the recognition object.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments of the present application will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic architecture diagram of an identification object determination system according to an embodiment of the present application;
fig. 2 is a schematic flowchart of an identification object determination method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of another identification object determination method provided in an embodiment of the present application;
fig. 4 is a schematic diagram of region division provided in an embodiment of the present application;
FIG. 5 is a schematic diagram of a relative position provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of an identification object determination apparatus according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an identification object determination device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the application and do not limit the application. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
At present, in a conventional identification object determination scheme, strategies such as optimizing a service flow and adjusting a layout angle of a shooting device are mainly used to reduce the occurrence of multiple faces in a display screen, and a first face appearing in the screen is generally obtained and used as an identification object in a subsequent service execution process. However, in a face recognition scene with a large pedestrian volume, such as a face brushing payment scene, a face brushing station entering scene, a face brushing gate crossing scene, a plurality of faces often appear on a display screen. Therefore, a misrecognition phenomenon may occur, that is, a "bystander" or "behind the body" face is taken as a recognition object, which affects the user experience.
Therefore, in order to solve the problems in the prior art, embodiments of the present application provide a method, an apparatus, a device, and a storage medium for determining an identification object. The method comprises the steps of extracting a face size value of each face in a shot preview image, and determining the face with the face size value meeting a preset identification condition as an identification object according to the face size value of each face. The method can select a proper target face as the recognition object in the face acquisition process, realize the accurate determination of the recognition object and improve the accuracy of the determination of the recognition object.
The following describes in detail a recognition object determination method, a recognition object determination apparatus, a recognition object determination device, and a recognition object determination storage medium according to embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a schematic architecture diagram of an identification object determination system provided in an embodiment of the present application, and as shown in fig. 1, the identification object determination system may include a shooting device 110 and an electronic device 120. The shooting device 110 may be a camera, a device with a camera module, or the like. The electronic device 120 may be a mobile electronic device or a non-mobile electronic device. For example, the Mobile electronic device may be a Mobile phone, a tablet Computer, a notebook Computer, a palm top Computer, an Ultra-Mobile Personal Computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-Mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a teller machine, a self-service machine, and the like. A communication connection exists between the photographing apparatus 110 and the electronic apparatus 120. For example, by a network, which may be a wired communication network or a wireless communication network. Illustratively, the photographing apparatus 110 may be integrated as one module in the electronic apparatus 120.
As one example, the recognition object determination system may be applied to face recognition scenarios such as face-swiped payment, face-swiped inbound, face-swiped check-in, and the like. Under these scenes, the phenomenon of aggregation of multiple faces is likely to occur on the display screen due to the rapid acquisition of faces and the large traffic of people.
Referring to fig. 1, the electronic device 120 may acquire a shooting preview image of the shooting device 110 for a user, wherein the shooting preview image includes at least two users, i.e., at least two faces. And then extracting the characteristic information of each face in the shot preview image, wherein the characteristic information comprises a face size value. And then according to the face size value of each face, determining the face with the face size value meeting the preset recognition condition as a recognition object so as to execute the subsequent face recognition service.
The identification object determination method provided by the embodiment of the present application will be described below. The execution subject of the identification object determination method may be the electronic device 120 in the identification object determination system shown in fig. 1, or a module in the electronic device 120.
Fig. 2 is a schematic flowchart of an identification object determining method provided in an embodiment of the present application, and as shown in fig. 2, the identification object determining method may include the following steps:
and S210, acquiring the shooting preview image.
The shooting preview image comprises at least two human faces and can be collected by shooting equipment on site. For example, the photographing preview image may be a picture input frame of a preview, i.e., an image displayed on a display screen when the photographing apparatus photographs.
And S220, extracting the characteristic information of each face in at least two faces in the shot preview image.
Wherein the feature information comprises a face size value. Illustratively, the face size value may include a face-eye distance value or a face pixel number, and the like, wherein the face size value is characterized by the face-eye distance value, and noise of the face size difference can be reduced.
In one embodiment, a face recognition algorithm may be used to perform preliminary face recognition on the captured preview image to identify a face therein. And then, carrying out feature extraction on the recognized human faces to obtain feature information of each human face.
And S230, determining the face with the face size value meeting the preset identification condition as an identification object according to the face size value of each face.
The recognition object is used as a main body for executing subsequent face recognition service and is used for face recognition.
The face as a recognition target is generally closest to the photographing apparatus than other faces photographed. Therefore, in one embodiment, the face with the largest face size value can be determined as the recognition object, and accurate determination of the recognition object is achieved.
In addition, a face to be recognized has a size advantage over other faces. In another embodiment, the ratio of the face size value of each face to the maximum face size value, except for the face with the largest face size value, of the at least two faces may be calculated respectively. When at least one ratio is smaller than or equal to a first preset ratio threshold, the face corresponding to the maximum face size value is determined as the recognition object, and accuracy of determination of the recognition object is improved. It is understood that the first preset ratio threshold can be flexibly set according to actual situations, and can be 60% for example.
It can be known that, in general, a user does not leave the current position during recognition and use, and a human face always appears in a screen. Therefore, in one example, when at least one ratio is less than or equal to the first preset ratio threshold, the time length of the face corresponding to the maximum face size value displayed on the display screen may be obtained. And when the display time length of the face corresponding to the maximum face size value is greater than or equal to a preset time length threshold value, determining the face corresponding to the maximum face size value as an identification object. By introducing the display duration as a judgment factor on the basis of the face size value, the accurate determination of the identification object can be further improved.
As a specific example, the face tracking of consecutive frames may be performed on the face corresponding to the maximum face size value. For example, a unique face identifier may be assigned to the face corresponding to the maximum face size value, and in the face tracking process of consecutive frames, the face identifier remains unchanged when the same face is not left, so that the duration of the continuous display of the face corresponding to the maximum face size value may be counted. And when the continuous display duration is greater than or equal to T, the face corresponding to the maximum face size value is taken as an identification object. Where T represents a preset duration threshold, which may be an absolute duration, e.g., 800 ms. Or may be a relative time duration, such as the time to complete a transaction. For example, in a face-brushing inbound scene, the time length of passing through a channel of a specified shooting area, namely the time length from entering to leaving a specific shooting area (not leaving the coverage of the shooting device) of a user; for another example, the time for acquiring a certain number (e.g., 5) of continuous frame images; for example, the transaction response time (the time for acquiring a transaction result of recognition), that is, when the face corresponding to the maximum face size value starts to be tracked, the recognition is initiated until the duration of the response result is received, and during the period, the face corresponding to the maximum face size value is always displayed in the display screen.
In another embodiment, a first position of the face corresponding to the maximum face size value may be obtained. When the first position meets the preset position condition, the face corresponding to the maximum face size value is determined as the recognition object, namely, the position is introduced as a judgment factor on the basis of the face size value, and the accurate determination of the recognition object is improved. Wherein the preset position condition may include: the first position matches the preset position, or the first position is located in a preset area. It is understood that the preset position and the preset area can be flexibly set according to actual situations, and for example, can be pre-selected according to debugging experience when the scene arrangement is implemented.
In the embodiment of the application, the face size value of each face in the shot preview image is extracted, and the face of which the face size value meets the preset recognition condition is determined as the recognition object according to the face size value of each face. The method can select a proper target face as the recognition object in the face acquisition process, and improve the accuracy of the determination of the recognition object.
In one embodiment, when any one of the at least one ratio is greater than the first preset ratio threshold, the method may further include:
firstly, when at least one ratio is smaller than or equal to a second preset ratio threshold, a first position of the face corresponding to the maximum face size value is obtained. The second preset ratio threshold is greater than the first preset ratio threshold, for example, the first preset ratio threshold is 60%, and the second preset ratio threshold is 80%. And the first preset ratio threshold value and the second preset ratio threshold value can be adjusted according to the accuracy rate determined by the identification object after a period of time. For example, a face picture for completing a business process, i.e., identifying an object to determine a correct face, may be selected as a forward sample. And selecting a human face picture with an erroneous recognition object, which is obtained by manually canceling the service process by the user, as a negative sample. And counting the accuracy rate determined by the identification object according to the proportion of the positive and negative samples in the total sample, and adjusting the first preset ratio threshold value and the second preset ratio threshold value according to the accuracy rate to realize the dynamic adjustment of the threshold values.
And then, when the first position meets a preset position condition, determining the face corresponding to the maximum face size value as an identification object. In the embodiment, a second preset ratio threshold and the position are introduced for further judgment, the condition for determining the identification object is refined, and the accuracy for determining the identification object can be further improved.
It can be understood that in a face recognition scenario, a user as a recognition object usually approaches the shooting device actively, and the face of the user is opposite on the display screen and generally has the characteristics of being clearly visible, having no occlusion, having no eye closed, and the like. In one embodiment, the feature information may further include face angles, face occlusion information, face eye information, and the like. And then at least two faces can be screened according to the face angle, the face shielding information and the face eye information, namely, the faces in the shot preview image are screened by taking the face angle, the face shielding information and the face eye information as judgment factors, and the faces meeting corresponding conditions are reserved.
Furthermore, at least two faces can be screened according to the face size value, the face angle, the face shielding information and the face eye information. And determining the face with the face size value meeting the preset identification condition as an identification object according to the face size value of the screened face. In this example, the accuracy of the determination of the recognition object can be improved by screening faces in multiple dimensions and selecting an appropriate face from the screened faces as the recognition object.
The following describes in detail the identification object determination method provided in the embodiment of the present application, taking an example that the identification object determination method is applied to a face-brushing payment scenario, as shown in fig. 3, the method may include the following steps:
s301, acquiring a shooting preview image of a user shot on site by the shooting device.
And S302, recognizing the face in the shot preview image according to a face recognition algorithm.
And S303, screening the human face in the shot preview image.
Specifically, first, feature information of each face may be extracted. The characteristic information comprises a face size value, a face angle, face shielding information and face eye information.
Secondly, the size value of each face can be judged, and the faces with the size values larger than or equal to the preset size threshold value are reserved. As an example, the face size value is characterized by the number of face pixels, and the preset size threshold may be set to 100 × 100, where 100 × 100 represents the width and height of the face pixels.
And then, judging the face angle, and reserving the face with the face angle smaller than or equal to a preset angle threshold value. As an example, the face angles include a roll angle (roll), a pitch angle (pitch), and a yaw angle (yaw), the preset angle thresholds corresponding to the three types of angles may all be ± 20 °, and faces with all three types of angles smaller than or equal to ± 20 ° are retained.
Then, the face shielding information can be judged, and the face shielding information is kept to meet the face shielding condition. As an example, the face occlusion condition can be flexibly set according to the business requirement, such as no occlusion at all, no occlusion of a key point, no occlusion area exceeding a certain proportion, and the like.
Moreover, the information of the eyes of the human face can be judged, whether the eyes of the human face are closed or not is judged, and the human face without the eyes closed is reserved. It should be noted that the above determining steps can be flexibly adjusted according to the service requirement, for example, the order can be appropriately increased or decreased, changed, and the like, which is not limited herein.
And S304, judging whether the screened face is unique.
If so, S305 is performed, otherwise, S308 is performed.
S305, acquiring the time length of the unique face displayed on the display screen.
S306, judging whether the display time length of the unique face is larger than or equal to a preset time length threshold value.
If so, S307 is executed, otherwise, S317 is executed.
And S307, determining the unique face as an identification object.
And S308, respectively calculating the ratio of the face size value of each face to the maximum face size value except the face with the maximum face size value.
S309, judging whether the ratios are all smaller than or equal to a first preset ratio threshold value.
If so, S310 is performed, otherwise, S313 is performed.
S310, acquiring the time length of the face corresponding to the maximum face size value displayed on the display screen.
S311, judging whether the display time length is larger than or equal to a preset time length threshold value.
If so, S312 is performed, otherwise, S317 is performed.
And S312, determining the face corresponding to the maximum face size value as an identification object.
S313, whether the ratios are all smaller than or equal to a second preset ratio threshold value is judged.
If so, S314 is performed, otherwise, S317 is performed.
And S314, acquiring a first position of the face corresponding to the maximum face size value.
The first position may include an absolute position of the face corresponding to the maximum face size value and a relative position using the face corresponding to the second maximum face size value as a reference point.
Specifically, the shot preview image may be divided according to a preset region division rule, a position mark of the face is determined according to the divided region, and the position mark represents an absolute position of the face. Referring to fig. 4, the area division rule may be that the photographed preview image is divided into 4 quadrants, namely a first quadrant, a second quadrant, a third quadrant and a fourth quadrant, according to a mathematical plane coordinate system, according to a central point. Meanwhile, the center point is used as the origin, half of the width of the shooting preview image is wide, and half of the height of the shooting preview image is high, and the center area is used as the center area C. Wherein the central region C coincides with the quadrant region.
As an example, a plane coordinate system may be constructed with the center point as the origin (0, 0). And calculating the coordinates (x, y) of the center point of the face of the person in the shot preview image, and determining the position mark of the face according to the coordinates of the center point of the face and the divided area. The location marker may be LG. Wherein, L represents the quadrant in which the face center point coordinate is located, takes the value of 1, 2, 3 or 4, and represents that L is located in the first quadrant when L is 1. G represents whether the coordinates of the center point of the face are located in the center area C or not, and takes a value of 0 or 1, wherein G is 0 and represents that the coordinates are not located in the center area C, and G is 1 and represents that the coordinates are located in the center area C. Wherein the location here includes the center point coordinates on the boundary. Specifically, the position markers may be as follows: not located in the central region C: a first quadrant: 10, second quadrant: 20, third quadrant: 30, fourth quadrant: 40; located in the central region C: a first quadrant: 11, second quadrant: 21, third quadrant: 31, fourth quadrant: 41. specifically, taking the position mark 10 as an example, it indicates that the coordinates of the center point of the face are located in the first quadrant, and are not located in the center area. Taking the position mark 11 as an example, it indicates that the coordinates of the center point of the face are located in the center area and the first quadrant. As shown in fig. 4, the center coordinate of the face 1 is located in the third quadrant and is not located in the center area C, and the position is marked as 30. The coordinates of the center of the face 2 are in the first and second quadrants and in the center area C, the positions are marked 11 and 21. The coordinates of the center of the face 3 are in the first quadrant and in the center area C, the position is marked 11. It can be understood that the region division rule can be flexibly adjusted according to actual needs, and is not limited herein.
The relative position may be calculated using a relative position calculation formula, which may be shown as follows in conjunction with fig. 5:
A(X，Y)＝O1(x1，y1)-O2(x2，y2) (1)
wherein A (X, Y) represents a vector, O1(x1，y1) Face center point coordinates, O, representing the second large face2(x2，y2) Face center point coordinates representing the largest face. Wherein, X>0 represents that the maximum face is on the left side of the second large face in the direction of the horizontal axis, otherwise, the maximum face is on the right side; y is>0 means that the largest face is on the vertical axis, below the second largest face, and vice versa, above.
S315, judging whether the first position meets a preset position condition.
Wherein the preset position condition comprises: the first position matches the preset position, or the first position is located in a preset area. In a certain fixed scene, the absolute position and the relative position of the recognition object appearing in the display screen often have certain aggregative property. It will be appreciated that the location of the focus may vary from scene to scene or from camera angle to camera angle. In a scene application, a certain number (for example, 10 ten thousand) of face recognition scene images with multiple faces are selected, data processing is performed on the face recognition scene images, a recognition object and a second large face are marked, the relative position and the absolute position of the recognition object are counted, that is, each image is classified, the LC value of the absolute position and the relative position a (X, Y) are counted, according to the statistical result, the LC value or the LC value combination with the largest number and the relative position in the scene are selected, the absolute position and the relative position where the recognition object frequently appears in the scene are confirmed, and the absolute position and the relative position are used as a preset position, or a preset area is determined according to the absolute position and the relative position where the recognition object frequently appears. The accuracy of object identification determination can be improved by setting a preset position or a preset area through a scene of practical application. On the basis, it is determined whether the first position satisfies the predetermined position condition, if so, S316 is executed, otherwise, S317 is executed.
And S316, determining the face corresponding to the maximum face size value as an identification object.
And S317, prompting that the identification object cannot be determined.
Specifically, a voice prompt like "the recognition object cannot be determined, please look aside the user to go backwards" may be issued.
In another example, S308 may be to calculate a first product of the maximum face size value and a first preset ratio threshold, and take the first product as the first size threshold.
S309 may be to determine whether the face size value of each face is smaller than or equal to the first size threshold, except for the face with the largest face size value. If so, S310 is performed, otherwise, S313 is performed.
S313 may be to calculate a second product of the maximum face size value and a second preset ratio threshold, and determine whether the face size value of each face is smaller than or equal to the second size threshold, except for the face with the maximum face size value, by using the second product as the second size threshold, if so, perform S314, otherwise, perform S317.
Based on the identification object determination method provided in the embodiment of the present application, an identification object determination apparatus is further provided in the embodiment of the present application, and as shown in fig. 6, the identification object determination apparatus 600 may include: an acquisition module 610, an extraction module 620, and a determination module 630.
The obtaining module 610 is configured to obtain a shooting preview image, where the shooting preview image includes at least two faces.
And an extracting module 620, configured to extract feature information of each of at least two faces in the captured preview image, where the feature information includes a face size value.
The determining module 630 is configured to determine, according to the face size value of each face, a face whose face size value meets a preset recognition condition as a recognition object.
In one embodiment, the determining module includes: and the first determining unit is used for determining the face with the largest face size value as the recognition object.
In one embodiment, the determining module includes: and the calculating unit is used for respectively calculating the ratio of the face size value of each face to the maximum face size value except the face with the maximum face size value in the at least two faces.
And the second determining unit is used for determining the face corresponding to the maximum face size value as the recognition object when at least one ratio is less than or equal to the first preset ratio threshold.
In one embodiment, the second determination unit includes: and the obtaining subunit is configured to, when at least one of the ratios is smaller than or equal to a first preset ratio threshold, obtain a duration of display of the face corresponding to the maximum face size value on the display screen.
And the determining subunit is configured to determine, when the display duration of the face corresponding to the maximum face size value is greater than or equal to a preset duration threshold, the face corresponding to the maximum face size value as the recognition object.
In an embodiment, the obtaining module is further configured to obtain a first position of the face corresponding to the maximum face size value when any one of the at least one ratio is greater than a first preset ratio threshold and the at least one ratio is less than or equal to a second preset ratio threshold, where the second preset ratio threshold is greater than the first preset ratio threshold.
And the determining module is further used for determining the face corresponding to the maximum face size value as the recognition object when the first position meets the preset position condition.
In one embodiment, the determining module includes: and the acquisition unit is used for acquiring a first position of the face corresponding to the maximum face size value.
And the third determining unit is used for determining the face corresponding to the maximum face size value as the recognition object when the first position meets the preset position condition.
In one embodiment, the preset position conditions include: the first position matches the preset position, or the first position is located in a preset area.
In one embodiment, the feature information further includes face angle, face occlusion information, and face eye information.
The determining module comprises: and the screening unit is used for screening at least two faces according to the face angle, the face shielding information and the face eye information.
And the fourth determining unit is used for determining the face with the face size value meeting the preset identification condition as the identification object according to the face size value of the screened face.
In one embodiment, the face size value comprises a face-eye spacing value or a number of face pixels.
It can be understood that each module/unit in the identification object determining apparatus 600 shown in fig. 6 has a function of implementing each step in the identification object determining method provided in the embodiment of the present application, and can achieve the corresponding technical effect, and for brevity, no further description is provided here.
Fig. 7 is a schematic structural diagram of an identification object determination device according to an embodiment of the present application.
As shown in fig. 7, the recognition object determining apparatus 700 in the present embodiment includes an input device 701, an input interface 702, a central processing unit 703, a memory 704, an output interface 705, and an output device 706. The input interface 702, the central processing unit 703, the memory 704, and the output interface 705 are connected to each other via a bus 710, and the input device 701 and the output device 706 are connected to the bus 710 via the input interface 702 and the output interface 705, respectively, and further connected to other components of the identification object determining device 700.
Specifically, the input device 701 receives input information from the outside, and transmits the input information to the central processor 703 through the input interface 702; the central processor 703 processes input information based on computer-executable instructions stored in the memory 704 to generate output information, stores the output information temporarily or permanently in the memory 704, and then transmits the output information to the output device 706 through the output interface 705; the output device 706 outputs the output information to the outside of the recognition object determining device 700 for use by the user.
In one embodiment, the recognition object determining apparatus 700 shown in fig. 7 includes: a memory 704 for storing programs; the processor 703 is configured to run a program stored in the memory to implement the identification object determination method provided in the embodiment of the present application.
Embodiments of the present application further provide a computer-readable storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement the identification object determination method provided by the embodiments of the present application.
It should be clear that each embodiment in this specification is described in a progressive manner, and the same or similar parts among the embodiments may be referred to each other, and for brevity, the description is omitted. The present application is not limited to the specific configurations and processes described above and shown in the figures. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions or change the order between the steps after comprehending the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuits, semiconductor Memory devices, Read-Only memories (ROMs), flash memories, erasable ROMs (eroms), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware for performing the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.

Claims (20)

1. A method for identifying an object, the method comprising:
acquiring a shooting preview image, wherein the shooting preview image comprises at least two human faces;
extracting feature information of each face of the at least two faces in the shot preview image, wherein the feature information comprises a face size value;
and determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face.
2. The method according to claim 1, wherein the determining, according to the face size value of each face, a face whose face size value satisfies a preset recognition condition as a recognition object comprises:
and determining the face with the largest face size value as an identification object.
3. The method according to claim 1, wherein the determining, according to the face size value of each face, a face whose face size value satisfies a preset recognition condition as a recognition object comprises:
respectively calculating the ratio of the face size value of each face to the maximum face size value except the face with the maximum face size value in the at least two faces;
and when at least one of the ratios is smaller than or equal to a first preset ratio threshold, determining the face corresponding to the maximum face size value as the identification object.
4. The method according to claim 3, wherein when at least one of the ratios is smaller than or equal to a first preset ratio threshold, determining that the face corresponding to the maximum face size value is the recognition object comprises:
when at least one of the ratios is smaller than or equal to a first preset ratio threshold, acquiring the time length of the face corresponding to the maximum face size value displayed on a display screen;
and when the display time length of the face corresponding to the maximum face size value is greater than or equal to a preset time length threshold value, determining the face corresponding to the maximum face size value as the identification object.
5. The method of claim 3, wherein when any one of the at least one ratio is greater than a first preset ratio threshold, the method further comprises:
when at least one of the ratios is smaller than or equal to a second preset ratio threshold, acquiring a first position of the face corresponding to the maximum face size value, wherein the second preset ratio threshold is larger than the first preset ratio threshold;
and when the first position meets a preset position condition, determining the face corresponding to the maximum face size value as the identification object.
6. The method according to claim 1, wherein the determining, according to the face size value of each face, a face whose face size value satisfies a preset recognition condition as a recognition object comprises:
acquiring a first position of a face corresponding to the maximum face size value;
and when the first position meets a preset position condition, determining the face corresponding to the maximum face size value as the identification object.
7. The method according to claim 5 or 6, wherein the preset position condition comprises:
the first position is matched with a preset position, or the first position is located in a preset area.
8. The method of claim 1, wherein the feature information further comprises face angle, face occlusion information, face eye information;
determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face, wherein the method comprises the following steps:
screening the at least two faces according to the face angle, the face shielding information and the face eye information;
and determining the face with the face size value meeting the preset identification condition as an identification object according to the face size value of the screened face.
9. The method of claim 1, wherein the face size value comprises a face eye distance value or a number of face pixels.
10. An identified object determining apparatus, characterized in that the apparatus comprises:
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a shooting preview image, and the shooting preview image comprises at least two human faces;
the extraction module is used for extracting the feature information of each face in the at least two faces in the shooting preview image, wherein the feature information comprises a face size value;
and the determining module is used for determining the face with the face size value meeting the preset recognition condition as a recognition object according to the face size value of each face.
11. The apparatus of claim 10, wherein the determining module comprises:
and the first determining unit is used for determining the face with the largest face size value as the recognition object.
12. The apparatus of claim 10, wherein the determining module comprises:
the calculating unit is used for respectively calculating the ratio of the face size value of each face to the maximum face size value except the face with the maximum face size value in the at least two faces;
and the second determining unit is used for determining the face corresponding to the maximum face size value as the identification object when at least one ratio is smaller than or equal to a first preset ratio threshold.
13. The apparatus of claim 12, wherein the second determining unit comprises:
the obtaining subunit is configured to, when at least one of the ratios is smaller than or equal to a first preset ratio threshold, obtain a duration of display of a face corresponding to the maximum face size value on a display screen;
and the determining subunit is configured to determine, when the display duration of the face corresponding to the maximum face size value is greater than or equal to a preset duration threshold, that the face corresponding to the maximum face size value is the identification object.
14. The apparatus of claim 12,
the obtaining module is further configured to obtain a first position of the face corresponding to the maximum face size value when any one of the at least one ratio is greater than a first preset ratio threshold and the at least one ratio is less than or equal to a second preset ratio threshold, where the second preset ratio threshold is greater than the first preset ratio threshold;
the determining module is further configured to determine, when the first position meets a preset position condition, that the face corresponding to the maximum face size value is the recognition object.
15. The apparatus of claim 10, wherein the determining module comprises:
the acquiring unit is used for acquiring a first position of the face corresponding to the maximum face size value;
and the third determining unit is used for determining the face corresponding to the maximum face size value as the identification object when the first position meets a preset position condition.
16. The apparatus of claim 14 or 15, wherein the preset position condition comprises:
the first position is matched with a preset position, or the first position is located in a preset area.
17. The apparatus of claim 10, wherein the feature information further comprises face angle, face occlusion information, face eye information;
the determining module comprises: the screening unit is used for screening the at least two faces according to the face angle, the face shielding information and the face eye information;
and the fourth determining unit is used for determining the face with the face size value meeting the preset identification condition as the identification object according to the face size value of the screened face.
18. The apparatus of claim 10, wherein the face size value comprises a face eye distance value or a number of face pixels.
19. An identification object determination apparatus, characterized in that the apparatus comprises: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the method of identifying an object as claimed in any of claims 1-9.
20. A computer-readable storage medium, having stored thereon computer program instructions, which, when executed by a processor, implement the method of identifying an object according to any one of claims 1-9.
CN202010983486.0A 2020-09-17 2020-09-17 Identification object determination method, device, equipment and storage medium Pending CN112215084A (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN202010983486.0A CN112215084A (en) 2020-09-17 2020-09-17 Identification object determination method, device, equipment and storage medium
PCT/CN2021/117383 WO2022057719A1 (en) 2020-09-17 2021-09-09 Method, apparatus and device for identifying recognition object, and storage medium
TW110134673A TWI804988B (en) 2020-09-17 2021-09-16 Identification object determination method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010983486.0A CN112215084A (en) 2020-09-17 2020-09-17 Identification object determination method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112215084A true CN112215084A (en) 2021-01-12

Family

ID=74050043

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010983486.0A Pending CN112215084A (en) 2020-09-17 2020-09-17 Identification object determination method, device, equipment and storage medium

Country Status (3)

Country Link
CN (1) CN112215084A (en)
TW (1) TWI804988B (en)
WO (1) WO2022057719A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022057719A1 (en) * 2020-09-17 2022-03-24 中国银联股份有限公司 Method, apparatus and device for identifying recognition object, and storage medium
CN117079378A (en) * 2023-10-16 2023-11-17 八维通科技有限公司 Multi-face passing gate processing method and system in site traffic and computer program medium

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115035578A (en) * 2022-06-20 2022-09-09 支付宝(杭州)信息技术有限公司 Payment method, device and equipment
CN117421729B (en) * 2023-12-18 2024-04-26 湖南森鹰科技有限公司 Automatic program attack detection method, device, system and medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109948586A (en) * 2019-03-29 2019-06-28 北京三快在线科技有限公司 Method, apparatus, equipment and the storage medium of face verification
CN110166696A (en) * 2019-06-28 2019-08-23 Oppo广东移动通信有限公司 Image pickup method, device, terminal device and computer readable storage medium
US20200177797A1 (en) * 2017-01-26 2020-06-04 Huawei Technologies Co., Ltd. Photographing Method and Photographing Apparatus for Terminal, and Terminal

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103824068B (en) * 2014-03-19 2018-06-01 上海看看智能科技有限公司 Face payment authentication system and method
US10532268B2 (en) * 2016-05-02 2020-01-14 Bao Tran Smart device
CN108229120B (en) * 2017-09-07 2020-07-24 北京市商汤科技开发有限公司 Face unlocking method, face unlocking information registration device, face unlocking information registration equipment, face unlocking program and face unlocking information registration medium
TWI760525B (en) * 2018-07-10 2022-04-11 鴻發國際科技股份有限公司 Cash handling system and cash transaction method
CN111435504A (en) * 2019-01-13 2020-07-21 潘连香 Payment password extraction method based on facial recognition
CN112258193B (en) * 2019-08-16 2024-01-30 创新先进技术有限公司 Payment method and device
CN111274965A (en) * 2020-01-20 2020-06-12 上海眼控科技股份有限公司 Face recognition method and device, computer equipment and storage medium
CN112215084A (en) * 2020-09-17 2021-01-12 中国银联股份有限公司 Identification object determination method, device, equipment and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200177797A1 (en) * 2017-01-26 2020-06-04 Huawei Technologies Co., Ltd. Photographing Method and Photographing Apparatus for Terminal, and Terminal
CN109948586A (en) * 2019-03-29 2019-06-28 北京三快在线科技有限公司 Method, apparatus, equipment and the storage medium of face verification
CN110166696A (en) * 2019-06-28 2019-08-23 Oppo广东移动通信有限公司 Image pickup method, device, terminal device and computer readable storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022057719A1 (en) * 2020-09-17 2022-03-24 中国银联股份有限公司 Method, apparatus and device for identifying recognition object, and storage medium
CN117079378A (en) * 2023-10-16 2023-11-17 八维通科技有限公司 Multi-face passing gate processing method and system in site traffic and computer program medium
CN117079378B (en) * 2023-10-16 2024-01-09 八维通科技有限公司 Multi-face passing gate processing method and system in site traffic and computer program medium

Also Published As

Publication number Publication date
TWI804988B (en) 2023-06-11
TW202213169A (en) 2022-04-01
WO2022057719A1 (en) 2022-03-24

Similar Documents

Publication Publication Date Title
CN112215084A (en) Identification object determination method, device, equipment and storage medium
CN107292287B (en) Face identification method, device, electronic equipment and storage medium
CN108038176B (en) Method and device for establishing passerby library, electronic equipment and medium
US11321575B2 (en) Method, apparatus and system for liveness detection, electronic device, and storage medium
US11093737B2 (en) Gesture recognition method and apparatus, electronic device, and computer-readable storage medium
CN106295638A (en) Certificate image sloped correcting method and device
CN108108711B (en) Face control method, electronic device and storage medium
CN111160175A (en) Intelligent pedestrian violation behavior management method and related product
EP3282387A1 (en) Fire detection method, fire detection apparatus and electronic equipment
CN112016353A (en) Method and device for carrying out identity recognition on face image based on video
CN112330715A (en) Tracking method, tracking device, terminal equipment and readable storage medium
CN111401315A (en) Face recognition method, recognition device and storage device based on video
CN110175553B (en) Method and device for establishing feature library based on gait recognition and face recognition
CN112149601A (en) Occlusion-compatible face attribute identification method and device and electronic equipment
CN111881740A (en) Face recognition method, face recognition device, electronic equipment and medium
CN114998955A (en) Face recognition method and device, storage medium and electronic equipment
CN107992816B (en) Photographing search method and device, electronic equipment and computer readable storage medium
CN116958795A (en) Method and device for identifying flip image, electronic equipment and storage medium
CN116434556A (en) Vehicle information acquisition method, device, equipment and medium thereof
TWI789128B (en) Face recognition method, device, equipment and storage medium
CN116403302A (en) Construction inspection system, construction inspection method and inspection equipment
CN116258881A (en) Image clustering method, device, terminal and computer readable storage medium
KR101757682B1 (en) Outside diversion preventing method of security image and system therof
CN113947795A (en) Mask wearing detection method, device, equipment and storage medium
CN110956098B (en) Image processing method and related equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination