CN110245561B - Face recognition method and device - Google Patents
Face recognition method and device Download PDFInfo
- Publication number
- CN110245561B CN110245561B CN201910385798.9A CN201910385798A CN110245561B CN 110245561 B CN110245561 B CN 110245561B CN 201910385798 A CN201910385798 A CN 201910385798A CN 110245561 B CN110245561 B CN 110245561B
- Authority
- CN
- China
- Prior art keywords
- picture
- face
- camera lens
- area
- real
- 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.)
- Active
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The application is applicable to the technical field of computer application, and provides a face recognition method and a face recognition device, wherein the face recognition method comprises the following steps: acquiring a face picture of a person to be detected; identifying a real-time section of a face area in the face picture in a picture display area; when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. The shot height of the lens is adjusted according to the real-time zones, so that the accuracy of face image acquisition in the face recognition process is ensured, the face is recognized by calculating the feature similarity between the face image and the pre-stored image, and the success rate of face recognition is improved.
Description
Technical Field
The application belongs to the technical field of computer application, and particularly relates to a face recognition method and device.
Background
Face recognition is a biometric technology for identity recognition based on facial feature information of a person. A series of related technologies, also commonly called face recognition and face recognition, are used to collect images or video streams containing faces by using a camera or a video camera, automatically detect and track the faces in the images, and then perform face recognition on the detected faces.
When people use face recognition, due to the fact that different people and heights are different, when the face recognition camera is fixed at one position, people with different heights cannot be considered, the height of the people is too high, the feet of the people with different heights are padded for face collection, when the height of the people is too low, the head of the people with different heights is lowered for overlooking for face collection, and due to the fact that angles are not ideal, the image effect of face collection is poor, and the number of video image interference factors is large. Therefore, the problem of inaccurate face recognition is caused by incomplete face images acquired during face recognition in the prior art.
Disclosure of Invention
In view of this, embodiments of the present application provide a face recognition method and apparatus, so as to solve the problem in the prior art that face recognition is inaccurate due to incomplete face images acquired when a face is recognized.
A first aspect of an embodiment of the present application provides a face recognition method, including:
acquiring a face picture of a person to be detected;
identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode;
when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area;
and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
A second aspect of an embodiment of the present application provides a face recognition apparatus, including:
the acquisition unit is used for acquiring a face picture of a person to be detected;
the positioning unit is used for identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode;
the adjusting unit is used for adjusting the position of a preset camera lens to a target height when the real-time section is not in the middle section of the picture display area; the target height is used for focusing the face area on the middle section of the picture display area;
and the identification unit is used for acquiring the shot target picture after the height is adjusted and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
A third aspect of an embodiment of the present application provides a face recognition apparatus, including: the device comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are connected with each other, the memory is used for storing a computer program for supporting an apparatus to execute the method, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method of the first aspect.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium having stored thereon a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of the first aspect described above.
Compared with the prior art, the embodiment of the application has the advantages that: acquiring a face picture of a person to be detected; identifying a real-time section of a face area in the face picture in a picture display area; when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. The shot height of the lens is adjusted according to the real-time zones, so that the accuracy of face image acquisition in the face recognition process is ensured, the face is recognized by calculating the feature similarity between the face image and the pre-stored image, and the success rate of face recognition is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a flowchart of a face recognition method according to an embodiment of the present application;
fig. 2 is a flowchart of a face recognition method according to a second embodiment of the present application;
fig. 3 is a schematic diagram of a face recognition apparatus according to a third embodiment of the present application;
fig. 4 is a schematic diagram of a face recognition apparatus according to a fourth embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
In order to explain the technical solution described in the present application, the following description will be given by way of specific examples.
Referring to fig. 1, fig. 1 is a flowchart of a face recognition method according to an embodiment of the present application. The main execution body of the face recognition method in this embodiment is a device with a face recognition function, including but not limited to a computer, a server, a tablet computer, or a terminal. The face recognition method as shown in the figure may include the steps of:
s101: and acquiring a face picture of the person to be detected.
When people use face identification, because different people, the height difference, when face identification camera is fixed in a position, can't take into account the crowd of different heights, adorn too high, the foot that will fill up of sub short point carries out the face collection, when adorning too low, the sub high head that will hang down overlooks and carries out the face collection, because of the unsatisfactory of angle for the image effect of face collection is poor, video image interference factor is many, the qualification rate is low, influence the collection effect, the experience of giving the user simultaneously is very poor.
Firstly, a human face picture of a person to be detected is obtained. The device for acquiring the face picture in this embodiment may be a camera device, and the face picture in this embodiment may be in a video form or an image form, which is not limited herein.
Meanwhile, it should be noted that, due to the difference in height, distance, and shooting angle of the person to be detected, the shot face picture may include part of or all of the face region, if all of the face regions are included, the positions of the face regions may be higher or lower, the face regions may be clear or blurred, and the size of the face region should be too small or too large, which is the distance between the person to be detected and the camera device.
Further, before step S102, steps S1021 to S1022 may be further included:
s1021: the area ratio of the section width corresponding to each section in the screen display area is set.
In this embodiment, in order to determine the position of the person to be measured in the image display area, different display sections are set in the image display area, and the different display sections are used to measure the position of the face area obtained by real-time shooting in the image display area.
First, we set at least three sections and an area ratio of a section width of each section in the screen display area to divide an area included in the screen display area of each section by the area ratio.
Preferably, in this embodiment, five sections may be set, and in the screen display area, from top to bottom: the upper zone, the upper two zones, the middle zone, the lower two zones and the next zone. Wherein the segment width of each segment may be the same, i.e. evenly distributed, or may be different. For example, the area occupation ratio of the middle area is set to 0.6, and the remaining screen display areas are equally allocated among the remaining areas outside the middle area. By the distribution mode of the picture display area, the occupied area of the middle area can be increased, the probability of the portrait area in the picture display area is increased, and the face recognition efficiency is improved.
S1022: and determining the corresponding division boundary of each section in the picture display area according to the area ratio and the size of the face picture.
After the area proportion of each section in the picture display area is determined, the division boundary corresponding to each section in the picture display area is determined according to the area proportion and the size of the face picture, and each section in the picture display area is determined in this way.
Further, besides the way of dividing the sections according to the width of the sections transversely and averagely, we can also divide the sections according to different directions and angles, such as upper left, upper right, middle, lower left, lower right, etc., which are only examples here, and the division of the sections can be determined according to the actual use environment.
S102: identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode.
After the picture sections are divided, the real-time sections of the face areas in the face pictures in the picture display areas are identified according to the dividing mode of the picture sections.
Illustratively, a face picture is displayed in a picture display area, the face picture includes a face area, and the position of a section of the face area in the picture display area is determined, so that the position of the section can be used as a real-time section of the current face area.
It should be noted that, in this embodiment, the face region in step S102 may be a complete face region, or may be an incomplete face region. When the face region is complete, normal processing is performed. When the face area is incomplete, the face features in the current face area can be identified, and the real-time section is determined according to the face features contained in the face area.
S103: when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area.
After the real-time zone is determined, the position of a preset camera lens is adjusted to a target height according to the real-time zone so as to focus the human face area on the middle zone of the picture display area.
Illustratively, if the human face is located in the first zone or the second zone of the five zones, the control signal controls the electric lifting mechanism to drive the human face collecting camera to move upwards to a corresponding height, and the height of the human face collecting camera is finely adjusted according to the position of the human face shot by the human face collecting camera until the human face to be detected is located in the shooting center of the collecting camera. Similarly, if the face is positioned in the next zone or the next two zones of the five zones, the control signal controls the electric lifting mechanism to drive the face acquisition camera to move downwards to the corresponding height, and the height is finely adjusted according to the face position shot by the face acquisition camera until the face to be detected is positioned in the shooting center of the acquisition camera.
S104: and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
And after the shooting height is adjusted, acquiring a target picture shot after the height is adjusted so as to identify the identity of the person to be detected according to the pre-stored identity information and the target picture. Before application, the face recognition system needs to collect face samples of related personnel in advance, and the collected samples are recorded into an intelligent analysis memory database. And the identity information photos stored in a specific server can be called through the wide area network to be compared in real time.
Further, step S104 in this embodiment may specifically include steps S1041 to S1044:
s1041: and acquiring a target picture shot after the height is adjusted, and extracting real-time portrait characteristics in the target picture.
After the height is adjusted, a target picture shot after the height is adjusted is obtained, and real-time portrait features are extracted from the target picture. The portrait features in this embodiment may include facial shapes, shapes of five sense organs, positions of five sense organs, etc., and are not limited herein.
Specifically, the features available for the face recognition system are generally classified into visual features, pixel statistical features, face image transformation coefficient features, face image algebraic features, and the like. The face feature extraction is performed on some features of the face. Optionally, the method for extracting the face features in this embodiment may be a knowledge-based characterization method, or a characterization method based on algebraic features or statistical learning, and is not limited herein. The knowledge-based characterization method mainly obtains feature data which is helpful for face classification according to shape description of face organs and distance characteristics between the face organs, and feature components of the feature data generally comprise Euclidean distance, curvature, angle and the like between feature points. The human face is composed of parts such as eyes, a nose, a mouth, a chin and the like, and geometric description of the parts and the structural relationship among the parts can be used as important features for recognizing the human face.
S1042: and extracting the pre-stored portrait characteristics corresponding to the pre-stored identity information from a database.
In this embodiment, the identity information of the compliance personnel is pre-stored, wherein the identity information may include portrait characteristics. Optionally, the manner of extracting the portrait features in this embodiment may include:
reading local identity information prestored in the local area, and extracting the prestored portrait characteristics from the local identity information; or the like, or, alternatively,
and acquiring cloud identity information prestored in a preset server, and extracting the prestored portrait characteristics from the cloud identity information.
Specifically, the pre-stored local identity information can be read through the memory database stored locally, namely the intelligent analysis box, and the pre-stored portrait characteristics can be extracted from the local identity information. Or the cloud identity information stored in the specific server is called from the wide area network, which is not limited herein, and the manner of extracting the portrait features from the two kinds of identity information is the same as the manner of extracting in step S1041, which is not described herein in detail.
S1043: and calculating the similarity between the pre-stored portrait characteristics and the real-time portrait characteristics.
After extracting the pre-stored portrait features and the real-time portrait features, determining whether the face image acquired in real time can be verified through face recognition or not by calculating the similarity between the pre-stored portrait features and the real-time portrait features.
The face features can be compared to obtain the similarity, so that the two features are judged to correspond to different people. Because the features are modeled data, the comparison of two features can be very time consuming. In some application scenes, the human face pictures to be compared can be subjected to feature extraction in advance, and then the human face pictures are only taken for use. The method for calculating the similarity in this embodiment may be through a euclidean distance or a cosine distance, and the like, which is not limited herein.
S1044: and when the similarity is greater than or equal to a preset threshold value, playing the voice passing the identity recognition.
And when the similarity is greater than or equal to the preset threshold, outputting a qualified detection result audio to inform the identified person, restoring the default position to the middle height by the electric lifting mechanism, and finishing the detection. And when the similarity is smaller than the threshold value, the identified person is informed of passing of the detection by the audio frequency, repeated detection is required, when the three times of detection are unqualified, the detection is finished, and the identified person is informed of passing of the detection and the detection is finished by the audio frequency.
According to the scheme, the face picture of the person to be detected is obtained; identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area; and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. The shot height of the lens is adjusted according to the real-time zones, so that the accuracy of face image acquisition in the face recognition process is ensured, the face is recognized by calculating the feature similarity between the face image and the pre-stored image, and the success rate of face recognition is improved.
Referring to fig. 2, fig. 2 is a flowchart of a face recognition method according to a second embodiment of the present application. The main execution body of the face recognition method in this embodiment is a device with a face recognition function, including but not limited to a computer, a server, a tablet computer, or a terminal. The face recognition method as shown in the figure may include the steps of:
s201: acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens.
The camera device in the embodiment comprises two types, namely a first camera lens and a second camera lens, wherein the first camera lens is used for shooting a face picture under a wide-angle lens, the upper shooting angle and the lower shooting angle are larger than 120 degrees, and the first camera lens is fixed on a support with no activity and used for collecting videos in a large-range area in front of a camera and detecting the position of the face. The image interface of the wide-angle camera is divided into five areas from top to bottom, namely an upper area, an upper two areas, a middle area, a lower two areas and a next area in sequence.
S202: identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode.
In this embodiment, the implementation manner of S202 is completely the same as that of S101 in the embodiment corresponding to fig. 1, and reference may be specifically made to the related description of S101 in the embodiment corresponding to fig. 1, which is not repeated herein.
S203: when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a face picture focused accurately.
In this embodiment, a second camera lens, also called a narrow-angle camera, is preset for capturing a fine face, the viewing angle is selectable as narrow as possible, for example, less than 50 degrees, and the shooting direction of the face capturing camera is the same as that of the wide-angle camera, and the face capturing camera is fixed on a movable shaft of the lifting mechanical module and can be adjusted up and down along with the lifting support. In this embodiment, a set of electric lifting accessories is also preset, including a lifting rod and a motor assembly, to perform the actions of lifting and lowering the face-capturing camera, i.e., the second camera lens.
After a face picture is acquired through a first camera and a real-time zone of a face area in the face picture in a picture display area is determined through recognition of the face picture, due to the standing position, the height of a detected person, the shooting angle of a first camera lens and other reasons, the real-time zone can be in a middle zone of the picture display area and can also be in other zones such as an upper zone and a lower zone, and therefore the height of a second camera lens needs to be adjusted according to different real-time zones to acquire a clear, complete and balanced target picture.
Further, step S203 may specifically include:
if the face area is identified to be in the first area or the second area of the face picture, controlling the second camera lens to move upwards to a target height;
and if the face area is identified to be in the next area or the next two areas of the face picture, controlling the second camera lens to move downwards to the target height.
Specifically, if the face is located in the first zone or the second zone of the five zones, the control signal controls the electric lifting mechanism to drive the face collecting camera to move upwards to a corresponding height, and the height of the face collecting camera is finely adjusted according to the face position shot by the face collecting camera until the face to be detected is located in the shooting center of the face collecting camera. Similarly, if the face is positioned in the next zone or the next two zones of the five zones, the control signal controls the electric lifting mechanism to drive the face acquisition camera to move downwards to the corresponding height, and the height is finely adjusted according to the face position shot by the face acquisition camera until the face to be detected is positioned in the shooting center of the acquisition camera.
In addition, if the face is located in the middle area of the five sections, the second camera lens is controlled to focus on the face area to finely adjust the shooting angle, namely the height of the face acquisition camera is directly and finely adjusted until the face to be detected is located in the shooting center of the acquisition camera.
S204: and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
And after the shooting height is adjusted, acquiring a target picture shot after the height is adjusted so as to identify the identity of the person to be detected according to the pre-stored identity information and the target picture. After the height of the face camera is reasonably adjusted, the intelligent analysis box carries out a link of comparing the faces, and the method comprises two steps:
the first one is off-line comparison, the human face shot by a collecting camera is compared with the human face library of the memory database of the intelligent analysis box in terms of features, the comparison features comprise the face shape, the shape of five sense organs and the position of the five sense organs, the similarity is calculated, when the similarity is greater than a threshold value, qualified detection results are output to inform an identified person through audio frequency, the electric lifting mechanism restores the default position to the middle height, the detection is finished, when the similarity is less than the threshold value, the audio frequency informs that the identified person does not pass the detection, repeated detection is required, when the detection is unqualified for three times, the detection is finished, and the audio frequency informs the identified person that the person does not pass the detection and the detection is finished.
The second type is online comparison, the face shot by the collecting camera is compared with the identity information picture stored in the specific server called by the wide area network in real time, the comparison characteristics comprise the face shape, the shape of five sense organs and the position of the five sense organs, the similarity is calculated, when the similarity is greater than a threshold value, the qualified result of detection is output and is informed to the identified person, the electric lifting mechanism restores the default position to the middle height, the detection is finished, when the similarity is less than the threshold value, the audio is informed that the identified person does not pass the detection, the repeated detection is required, when the three times of detection are unqualified, the detection is finished, and the audio is informed that the identified person does not pass the detection and the detection is finished.
According to the scheme, the face picture of the person to be detected shot in real time by the first camera lens is obtained; the first camera lens is used for shooting a human face picture under the wide-angle lens; identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; adjusting the second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. In the embodiment, the wide-angle portrait picture is shot through the preset first camera lens, the shooting height of the second camera lens is adjusted through the face position in the portrait picture, a face image with moderate size and clear display is obtained, the face is identified by calculating the feature similarity between the face image and the pre-stored image, and the accuracy of face identification is improved.
Referring to fig. 3, fig. 3 is a schematic view of a face recognition apparatus according to a third embodiment of the present application. The face recognition apparatus 300 may be an apparatus having a face recognition function. The units included in the face recognition apparatus 300 of the present embodiment are used to execute the steps in the embodiment corresponding to fig. 1, please refer to fig. 1 and the related description in the embodiment corresponding to fig. 1, which are not repeated herein. The face recognition apparatus 300 of the present embodiment includes:
an acquiring unit 301, configured to acquire a face image of a person to be detected;
a positioning unit 302, configured to identify a real-time segment where a face area in the face picture is located in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode;
an adjusting unit 303, configured to adjust a position of a preset camera lens to a target height when the real-time segment is not in the middle segment of the screen display area; the target height is used for focusing the face area on the middle section of the picture display area;
the identification unit 304 is configured to acquire a target picture photographed after the height is adjusted, and identify the identity of the person to be tested according to the pre-stored identity information and the target picture.
Further, the obtaining unit 301 is further configured to: acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens;
further, the adjusting unit 303 is further configured to: when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture;
further, the identifying unit 304 is further configured to: and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
Further, the face recognition apparatus further includes:
a ratio setting unit for setting an area ratio of a section width corresponding to each section in the screen display area;
and the area setting unit is used for determining the corresponding dividing boundary of each section in the picture display area according to the area ratio and the size of the face picture.
Further, the adjusting unit further includes:
the upward moving unit is used for controlling the second camera lens to move upward to a target height if the face area is identified to be in the first area or the second area of the face picture;
and the downward moving unit is used for controlling the second camera lens to move downward to a target height if the face area is identified to be in the next area or the next two areas of the face picture.
Further, the identification unit further includes:
the first characteristic unit is used for acquiring a target picture shot after the height is adjusted and extracting real-time portrait characteristics in the target picture;
the second characteristic unit is used for extracting the pre-stored portrait characteristics corresponding to the pre-stored identity information from the database;
the calculating unit is used for calculating the similarity between the pre-stored portrait characteristics and the real-time portrait characteristics;
and the identity recognition unit is used for playing the voice passing the identity recognition when the similarity is greater than or equal to a preset threshold value.
Further, the second feature unit further includes:
the first reading unit is used for reading local identity information prestored in a local database and extracting the prestored portrait characteristics from the local identity information; or the like, or, alternatively,
and the second reading unit is used for acquiring cloud identity information prestored in a preset server database and extracting the prestored portrait features from the cloud identity information.
According to the scheme, the face picture of the person to be detected shot in real time by the first camera lens is obtained; the first camera lens is used for shooting a human face picture under the wide-angle lens; identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; adjusting the second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. In the embodiment, the wide-angle portrait picture is shot through the preset first camera lens, the shooting height of the second camera lens is adjusted through the face position in the portrait picture, a face image with moderate size and clear display is obtained, the face is identified by calculating the feature similarity between the face image and the pre-stored image, and the accuracy of face identification is improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Referring to fig. 4, fig. 4 is a schematic view of a face recognition apparatus according to a fourth embodiment of the present application. The face recognition apparatus 400 in the present embodiment as shown in fig. 4 may include: a processor 401, a memory 402, and a computer program 403 stored in the memory 402 and executable on the processor 401. The steps in the various embodiments of face recognition methods described above are implemented when the processor 401 executes the computer program 403. The memory 402 is used to store a computer program comprising program instructions. Processor 401 is operative to execute program instructions stored in memory 402. Wherein the processor 401 is configured to call the program instruction to perform the following operations:
the processor 401 is configured to:
acquiring a face picture of a person to be detected;
identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode;
when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area;
and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
Further, the processor 401 is specifically configured to
Acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens;
when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture;
and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
Further, the processor 401 is specifically configured to
Setting the area ratio of the section width corresponding to each section in the screen display area;
and determining the corresponding division boundary of each section in the picture display area according to the area ratio and the size of the face picture.
Further, the processor 401 is specifically configured to
If the face area is identified to be in the first area or the second area of the face picture, controlling the second camera lens to move upwards to a target height;
and if the face area is identified to be in the next area or the next two areas of the face picture, controlling the second camera lens to move downwards to the target height.
Further, the processor 401 is specifically configured to
Acquiring a target picture shot after the height is adjusted, and extracting real-time portrait characteristics in the target picture;
pre-stored portrait characteristics corresponding to the pre-stored identity information are extracted from a database;
calculating the similarity between the pre-stored portrait characteristics and the real-time portrait characteristics;
and when the similarity is greater than or equal to a preset threshold value, playing the voice passing the identity recognition.
Further, the processor 401 is specifically configured to
Reading local identity information prestored in a local database, and extracting the prestored portrait characteristics from the local identity information; or the like, or, alternatively,
the method comprises the steps of obtaining cloud identity information pre-stored in a preset server database, and extracting pre-stored portrait features from the cloud identity information.
According to the scheme, the face picture of the person to be detected shot in real time by the first camera lens is obtained; the first camera lens is used for shooting a human face picture under the wide-angle lens; identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; adjusting the second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. In the embodiment, the wide-angle portrait picture is shot through the preset first camera lens, the shooting height of the second camera lens is adjusted through the face position in the portrait picture, a face image with moderate size and clear display is obtained, the face is identified by calculating the feature similarity between the face image and the pre-stored image, and the accuracy of face identification is improved.
It should be understood that, in the embodiment of the present Application, the Processor 401 may be a Central Processing Unit (CPU), and the Processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 402 may include both read-only memory and random access memory, and provides instructions and data to the processor 401. A portion of the memory 402 may also include non-volatile random access memory. For example, the memory 402 may also store device type information.
In a specific implementation, the processor 401, the memory 402, and the computer program 403 described in this embodiment may execute the implementation manners described in the first embodiment and the second embodiment of the face recognition method provided in this embodiment, and may also execute the implementation manners of the terminal described in this embodiment, which is not described herein again.
In another embodiment of the present application, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program comprising program instructions that when executed by a processor implement:
acquiring a face picture of a person to be detected;
identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode;
when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area;
and acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
Further, the computer program when executed by the processor further implements:
acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens;
when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture;
and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture.
Further, the computer program when executed by the processor further implements:
setting the area ratio of the section width corresponding to each section in the screen display area;
and determining the corresponding division boundary of each section in the picture display area according to the area ratio and the size of the face picture.
Further, the computer program when executed by the processor further implements:
if the face area is identified to be in the first area or the second area of the face picture, controlling the second camera lens to move upwards to a target height;
and if the face area is identified to be in the next area or the next two areas of the face picture, controlling the second camera lens to move downwards to the target height.
Further, the computer program when executed by the processor further implements:
acquiring a target picture shot after the height is adjusted, and extracting real-time portrait characteristics in the target picture;
pre-stored portrait characteristics corresponding to the pre-stored identity information are extracted from a database;
calculating the similarity between the pre-stored portrait characteristics and the real-time portrait characteristics;
and when the similarity is greater than or equal to a preset threshold value, playing the voice passing the identity recognition.
Further, the computer program when executed by the processor further implements:
reading local identity information prestored in a local database, and extracting the prestored portrait characteristics from the local identity information; or the like, or, alternatively,
the method comprises the steps of obtaining cloud identity information pre-stored in a preset server database, and extracting pre-stored portrait features from the cloud identity information.
According to the scheme, the face picture of the person to be detected shot in real time by the first camera lens is obtained; the first camera lens is used for shooting a human face picture under the wide-angle lens; identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; adjusting the second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; and acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture. In the embodiment, the wide-angle portrait picture is shot through the preset first camera lens, the shooting height of the second camera lens is adjusted through the face position in the portrait picture, a face image with moderate size and clear display is obtained, the face is identified by calculating the feature similarity between the face image and the pre-stored image, and the accuracy of face identification is improved.
The computer readable storage medium may be an internal storage unit of the terminal according to any of the foregoing embodiments, for example, a hard disk or a memory of the terminal. The computer readable storage medium may also be an external storage device of the terminal, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal. Further, the computer-readable storage medium may also include both an internal storage unit and an external storage device of the terminal. The computer-readable storage medium is used for storing the computer program and other programs and data required by the terminal. The computer readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the terminal and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed terminal and method can be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially or partially contributed by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. A face recognition method, comprising:
acquiring a face picture of a person to be detected;
identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; wherein, in addition to the manner of dividing the sections transversely according to the section width, the sections are divided according to different directions and angles, and the sections comprise an upper left, an upper right, a middle, a lower left and a lower right;
when the real-time section is not in the middle section of the picture display area, adjusting the position of a preset camera lens to a target height; the target height is used for focusing the face area on the middle section of the picture display area;
acquiring a target picture shot after the height is adjusted, and identifying the identity of the person to be detected according to prestored identity information and the target picture;
the method for acquiring the face picture of the person to be detected comprises the following steps: acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens; the first camera lens is fixed on a bracket which is not movable;
when the real-time zone is not in the middle zone of the picture display area, adjusting the position of a preset camera lens to a target height, comprising: when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; the second camera lens is fixed on a movable shaft of the lifting mechanical module and can be adjusted up and down along with the lifting support; a set of electric lifting accessories comprising a lifting rod and a motor assembly is also preset, and the electric lifting accessories are used for executing the lifting and descending actions of the second camera lens; the shooting directions of the first camera lens and the second camera lens are consistent;
the acquiring of the target picture shot after the height adjustment, according to the pre-stored identity information and the target picture, identifying the identity of the person to be tested, includes: acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to prestored identity information and the target picture;
the identifying the real-time section of the face area in the face picture in the picture display area further comprises:
setting the area ratio of the section width corresponding to each section in the screen display area; wherein, the area proportion of the middle area is set as 0.6, and the rest picture display areas are evenly distributed among the rest areas except the middle area;
and determining the corresponding division boundary of each section in the picture display area according to the area ratio and the size of the face picture.
2. The face recognition method of claim 1, wherein the segments comprise a previous region, a previous two regions, a middle region, a next region, and a next two regions; when the real-time zone is not in the middle zone of the picture display area, adjusting the position of a preset camera lens to a target height, comprising:
if the face area is identified to be in the first area or the second area of the face picture, controlling the second camera lens to move upwards to a target height;
and if the face area is identified to be in the next area or the next two areas of the face picture, controlling the second camera lens to move downwards to the target height.
3. The face recognition method according to claim 1-or 2, wherein the acquiring of the target picture photographed after the height adjustment and the recognizing of the identity of the person to be tested according to the pre-stored identity information and the target picture comprise:
acquiring a target picture shot after the height is adjusted, and extracting real-time portrait characteristics in the target picture;
pre-stored portrait characteristics corresponding to the pre-stored identity information are extracted from a database;
calculating the similarity between the pre-stored portrait characteristics and the real-time portrait characteristics;
and when the similarity is greater than or equal to a preset threshold value, playing the voice passing the identity recognition.
4. The method of claim 3, wherein the extracting the pre-stored portrait characteristics corresponding to the pre-stored identity information from the database comprises:
reading local identity information prestored in a local database, and extracting the prestored portrait characteristics from the local identity information; or the like, or, alternatively,
the method comprises the steps of obtaining cloud identity information pre-stored in a preset server database, and extracting pre-stored portrait features from the cloud identity information.
5. A face recognition apparatus, comprising:
the acquisition unit is used for acquiring a face picture of a person to be detected;
the positioning unit is used for identifying a real-time section of a face area in the face picture in a picture display area; the picture display area is divided into a plurality of sections according to a preset picture section dividing mode; wherein, in addition to the manner of dividing the sections transversely according to the section width, the sections are divided according to different directions and angles, and the sections comprise an upper left, an upper right, a middle, a lower left and a lower right; the adjusting unit is used for adjusting the position of a preset camera lens to a target height when the real-time section is not in the middle section of the picture display area; the target height is used for focusing the face area on the middle section of the picture display area;
the identification unit is used for acquiring a shot target picture after the height is adjusted and identifying the identity of the person to be detected according to the pre-stored identity information and the target picture;
the acquisition unit is further configured to: acquiring a human face picture of a person to be detected shot by a first camera lens in real time; the first camera lens is used for shooting a human face picture under the wide-angle lens; the first camera lens is fixed on a bracket which is not movable;
the adjustment unit is further configured to: when the real-time section is not in the middle section of the picture display area, adjusting a second camera lens to a target height according to the real-time section; the second camera lens is used for shooting a precisely focused human face picture; the second camera lens is fixed on a movable shaft of the lifting mechanical module and can be adjusted up and down along with the lifting support; a set of electric lifting accessories comprising a lifting rod and a motor assembly is also preset, and the electric lifting accessories are used for executing the lifting and descending actions of the second camera lens; the shooting directions of the first camera lens and the second camera lens are consistent;
the identification unit is further configured to: acquiring a target picture shot by the second camera lens after the height is adjusted, and identifying the identity of the person to be detected according to prestored identity information and the target picture;
the face recognition apparatus further includes:
a ratio setting unit for setting an area ratio of a section width corresponding to each section in the screen display area; wherein, the area proportion of the middle area is set as 0.6, and the rest picture display areas are evenly distributed among the rest areas except the middle area;
and the area setting unit is used for determining the corresponding dividing boundary of each section in the picture display area according to the area ratio and the size of the face picture.
6. A face recognition apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 4 when executing the computer program.
7. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910385798.9A CN110245561B (en) | 2019-05-09 | 2019-05-09 | Face recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910385798.9A CN110245561B (en) | 2019-05-09 | 2019-05-09 | Face recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110245561A CN110245561A (en) | 2019-09-17 |
| CN110245561B true CN110245561B (en) | 2021-11-09 |
Family
ID=67883975
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910385798.9A Active CN110245561B (en) | 2019-05-09 | 2019-05-09 | Face recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245561B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111131701B (en) * | 2019-12-25 | 2022-10-04 | 航天信息股份有限公司 | Intelligent head portrait tracking system and method |
| CN111681344A (en) * | 2020-04-17 | 2020-09-18 | 深圳市华正联实业有限公司 | Method and system for checking information of person getting-on/off vehicle |
| CN111539295A (en) * | 2020-04-17 | 2020-08-14 | 中移（杭州）信息技术有限公司 | Face recognition method, device, system, network equipment and storage medium |
| CN111783592B (en) * | 2020-06-24 | 2022-07-08 | 杭州十域科技有限公司 | Face recognition method combining incomplete face information with position data |
| CN112614160B (en) * | 2020-12-24 | 2021-08-31 | 中标慧安信息技术股份有限公司 | Multi-object face tracking method and system |
| CN114765659B (en) * | 2020-12-30 | 2024-02-27 | 浙江宇视科技有限公司 | Method, device, equipment and medium for expanding face detection range of intelligent camera |
| CN112800866B (en) * | 2021-01-13 | 2022-05-06 | 深圳市小兵智能科技有限公司 | Face recognition device, application system, method, computer equipment and storage medium |
| CN114241182A (en) * | 2021-12-21 | 2022-03-25 | 上海帝图信息科技有限公司 | Body language recognition system and method |
| CN114419698A (en) * | 2021-12-27 | 2022-04-29 | 天津天地伟业信息系统集成有限公司 | Control method of face recognition camera and computer readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN105718887A (en) * | 2016-01-21 | 2016-06-29 | 惠州Tcl移动通信有限公司 | Shooting method and shooting system capable of realizing dynamic capturing of human faces based on mobile terminal |
| CN108696641A (en) * | 2018-05-15 | 2018-10-23 | Oppo（重庆）智能科技有限公司 | Call reminding method, device, storage medium and mobile terminal |
| CN109086692A (en) * | 2018-07-16 | 2018-12-25 | 北京建筑大学 | A kind of face identification device and method |
| CN109729268A (en) * | 2018-12-26 | 2019-05-07 | 武汉市澜创信息科技有限公司 | A kind of face image pickup method, device, equipment and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10169671B2 (en) * | 2017-02-17 | 2019-01-01 | Motorola Mobility Llc | Face detection with temperature and distance validation |
| US10380444B2 (en) * | 2017-07-14 | 2019-08-13 | Hong Kong Baptist University | 3D mask face anti-spoofing with remote photoplethysmography |
| CN108921055A (en) * | 2018-06-15 | 2018-11-30 | 北京蜂盒科技有限公司 | Personal identification method, device, storage medium and electronic equipment |
| CN109614881B (en) * | 2018-11-19 | 2021-04-27 | 中国地质大学（武汉） | Biometric authentication method and device capable of adaptively adjusting threshold value and storage device |
-
2019
- 2019-05-09 CN CN201910385798.9A patent/CN110245561B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504321A (en) * | 2015-01-05 | 2015-04-08 | 湖北微模式科技发展有限公司 | Method and system for authenticating remote user based on camera |
| CN105718887A (en) * | 2016-01-21 | 2016-06-29 | 惠州Tcl移动通信有限公司 | Shooting method and shooting system capable of realizing dynamic capturing of human faces based on mobile terminal |
| CN108696641A (en) * | 2018-05-15 | 2018-10-23 | Oppo（重庆）智能科技有限公司 | Call reminding method, device, storage medium and mobile terminal |
| CN109086692A (en) * | 2018-07-16 | 2018-12-25 | 北京建筑大学 | A kind of face identification device and method |
| CN109729268A (en) * | 2018-12-26 | 2019-05-07 | 武汉市澜创信息科技有限公司 | A kind of face image pickup method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245561A (en) | 2019-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245561B (en) | Face recognition method and device | |
| US9619708B2 (en) | Method of detecting a main subject in an image | |
| CN107886484B (en) | Beautifying method, beautifying device, computer-readable storage medium and electronic equipment | |
| KR101731771B1 (en) | Automated selection of keeper images from a burst photo captured set | |
| US8836777B2 (en) | Automatic detection of vertical gaze using an embedded imaging device | |
| JP6550094B2 (en) | Authentication device and authentication method | |
| CN111027504A (en) | Face key point detection method, device, equipment and storage medium | |
| US20180075593A1 (en) | Automatic scene calibration method for video analytics | |
| CN116132786A (en) | Camera angle adjusting method and system of image pickup device | |
| CN109325933A (en) | A kind of reproduction image-recognizing method and device | |
| EP2866170A2 (en) | Image processing device and image processing method | |
| KR20170134256A (en) | Method and apparatus for correcting face shape | |
| CN110390229B (en) | Face picture screening method and device, electronic equipment and storage medium | |
| CN109299658B (en) | Face detection method, face image rendering device and storage medium | |
| CN107368806B (en) | Image rectification method, image rectification device, computer-readable storage medium and computer equipment | |
| US8903139B2 (en) | Method of reconstructing three-dimensional facial shape | |
| CN109791615A (en) | For detecting and tracking the method, target object tracking equipment and computer program product of target object | |
| CN111263955A (en) | Method and device for determining movement track of target object | |
| CN113887387A (en) | Ski field target image generation method, system and server | |
| CN105095853A (en) | Image processing apparatus and image processing method | |
| CN112017210A (en) | Target object tracking method and device | |
| CN112036209A (en) | Portrait photo processing method and terminal | |
| CN113313626A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN110516572B (en) | Method for identifying sports event video clip, electronic equipment and storage medium | |
| CN112153269B (en) | Picture display method, device and medium applied to electronic equipment and electronic 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |