CN109145878A - image extraction method and device - Google Patents
image extraction method and device Download PDFInfo
- Publication number
- CN109145878A CN109145878A CN201811159896.2A CN201811159896A CN109145878A CN 109145878 A CN109145878 A CN 109145878A CN 201811159896 A CN201811159896 A CN 201811159896A CN 109145878 A CN109145878 A CN 109145878A
- Authority
- CN
- China
- Prior art keywords
- video
- video frame
- extraction conditions
- face
- preset
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Studio Devices (AREA)
- Image Analysis (AREA)
Abstract
The disclosure is directed to a kind of image extraction method and device, disclosed method includes: to carry out image recognition in video call process to the video frame in video caused by video calling, obtain recognition result；According to the recognition result, judge whether the video frame meets preset extraction conditions；It is picture by the video frame extraction when the video frame meets the preset extraction conditions.The disclosure can be according to preset extraction conditions, it automatically is picture by the video frame extraction for meeting preset condition in video call process, video pictures are captured manually without user, it will not converse user video to form interference, be conducive to capture the state of user's natural relaxation, thus improve image zooming-out efficiency.
Description
Technical field
This disclosure relates to field of communication technology more particularly to a kind of image extraction method and device.
Background technique
Generally, video calling can be expressed as two or more terminal devices and be based on internet or mobile Internet,
A kind of communication mode of mutual real-time delivery of voice and video.User often has many when carrying out video calling with good friend
Interesting interaction.In the related technology, user can only be by calling the interface of screenshotss software intercepts video calling to recognize to capture manually
For excellent image, still, user's Manual interception often misses splendid moment, and interception will increase the cumbersome journey of operation by hand
Degree influences user video call, leads to image zooming-out low efficiency, of poor quality.
Summary of the invention
To overcome the problems in correlation technique, the disclosure provides a kind of image extraction method and device.
According to the first aspect of the embodiments of the present disclosure, a kind of image extraction method is provided, comprising:
In video call process, image recognition is carried out to the video frame in video caused by video calling, is known
Other result；
According to the recognition result, judge whether the video frame meets preset extraction conditions；
It is picture by the video frame extraction when the video frame meets the preset extraction conditions.
In one possible implementation, video caused by video calling includes either end or multiterminal in video calling
The video of shooting.
In one possible implementation, described image identification includes recognition of face,
The preset extraction conditions include any one or more in following:
Occurs face in video frame；
Face in video frame is in the designated position in video frame；
The ratio that the area of face accounts for video frame area is greater than first threshold；
The camera lens shooting angle of face meets angle conditions；
The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold；
Occurs specified expression in video frame.
In one possible implementation, described image identification includes recongnition of objects,
The preset extraction conditions include one of following or a variety of:
Clothing color and background color meet preset collocation condition in video frame, wherein the target object includes clothes
Dress；
Occurs target object in video frame.
In one possible implementation, the method also includes:
The option of extraction conditions is provided；
The extraction conditions selected are determined as preset extraction conditions.
In one possible implementation, the method also includes:
Authorization requests are sent to video calling opposite end, the authorization requests identify the video calling opposite end institute for requesting
The video of generation；
When receiving the authorization message that video calling opposite end is returned in response to the authorization requests, to video calling opposite end
Video frame in generated video carries out image recognition.
According to the second aspect of an embodiment of the present disclosure, a kind of image acquiring apparatus is provided, comprising:
Identification module, for carrying out figure to the video frame in video caused by video calling in video call process
As identification, recognition result is obtained；
Judgment module, for judging whether the video frame meets preset extraction conditions according to the recognition result；
Extraction module, for being by the video frame extraction when the video frame meets the preset extraction conditions
Picture.
In one possible implementation, video caused by video calling includes either end or multiterminal in video calling
The video of shooting.
In one possible implementation, described image identification includes recognition of face,
The preset extraction conditions include any one or more in following:
Occurs face in video frame；
Face in video frame is in the designated position in video frame；
The ratio that the area of face accounts for video frame area is greater than first threshold；
The camera lens shooting angle of face meets angle conditions；
The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold；
Occurs specified expression in video frame.
In one possible implementation, described image identification includes recongnition of objects,
The preset extraction conditions include one of following or a variety of:
Clothing color and background color meet preset collocation condition in video frame, wherein the target object includes clothes
Dress；
Occurs target object in video frame.
In one possible implementation, described device further include:
Display module, for providing the option of extraction conditions；
Determining module, for the extraction conditions selected to be determined as preset extraction conditions.
In one possible implementation, described device further include:
Sending module, for sending authorization requests to video calling opposite end, the authorization requests are for requesting described in identification
Video caused by video calling opposite end；
Receiving module, for when receiving the authorization message that video calling opposite end is returned in response to the authorization requests,
Image recognition is carried out to the video frame in video caused by video calling opposite end.
According to the third aspect of an embodiment of the present disclosure, a kind of image acquiring apparatus is provided, comprising: processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to: execute the above method.
According to a fourth aspect of embodiments of the present disclosure, a kind of non-transitorycomputer readable storage medium is provided, when described
When instruction in storage medium is executed by processor, enable a processor to execute the above method.
The technical scheme provided by this disclosed embodiment can include the following benefits: the disclosure passes through in video calling
In the process, image recognition is carried out to the video frame in video caused by video calling, recognition result is obtained, according to the identification knot
Fruit, judges whether the video frame meets preset extraction conditions, and when video frame meets preset extraction conditions, by video
Frame is extracted as picture.It is possible thereby to which the view of preset condition will be met in video call process automatically according to preset extraction conditions
Frequency frame is extracted as picture, captures video pictures manually without user, and seldom converse to form interference to user video, is conducive to
The state of user's natural relaxation is captured, image zooming-out efficiency and quality are thus effectively improved.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.
Fig. 1 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.
Fig. 2 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.
Fig. 3 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.
Fig. 4 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.
Fig. 6 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all implementations consistent with this disclosure.On the contrary, they be only with it is such as appended
The example of the consistent device and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.This method can be applied
In terminal devices such as desktop computer, laptop, tablet computer, mobile phones, it is not limited here.As shown in Figure 1, this method can
To include:
Step 100, in video call process, image knowledge is carried out to the video frame in video caused by video calling
Not, recognition result is obtained；
Step 101, according to the recognition result, judge whether the video frame meets preset extraction conditions；
It step 102, is picture by the video frame extraction when the video frame meets the preset extraction conditions.
In this example, generally, image recognition can be expressed as handling image using computer, analyze and
Understand, to identify the target of various different modes and to the technology of picture.
In one possible implementation, image recognition processes may include: sharp respectively according to different extraction conditions
Classifier (such as the classifier can be generated based on neural network) is obtained with different sample set training, video frame is inputted
To the classifier and corresponding output is obtained as a result, i.e. recognition result proposes the video frame when recognition result meets extraction conditions
It is taken as picture.It should be noted that those skilled in the art also can according to need choose other applicable recognition methods (such as
Clustering algorithm etc.) to video frame carry out image recognition, the disclosure to specific image recognition mode without limitation.
Video (Video) technology may generally be expressed as being captured dynamic image in a manner of electric signal, note down, locate
Reason, storage, transmission and the technology reappeared.One video may include a series of video frame.
As an example of the present embodiment, terminal device can obtain video in the case where detecting video calling
All or part of video frame (such as the available odd number of terminal device or even number order in communication process in generated video
Video frame, it is not limited here).For each video frame got, terminal device can carry out image knowledge to video frame
Not, recognition result is obtained.It, can when terminal device is according to the recognition result, judges that the video frame meets preset extraction conditions
Multiple of extraction as picture, can also be formed pictures by the video frame extraction.Terminal device can store the picture or figure
Piece collection, or the picture or pictures are sent to other terminals, or the picture or pictures are shared by internet platform.
As an example of the present embodiment, video caused by video calling may include in video calling either end or
The video of multiterminal shooting.For example, being generated in the video call process if thering is terminal A, terminal B and terminal C to participate in video calling
Video may include in terminal A, terminal B and terminal C any end or multiterminal shooting video.
The disclosure is by carrying out image knowledge to the video frame in video caused by video calling in video call process
Not, recognition result is obtained, according to the recognition result, judges whether the video frame meets preset extraction conditions, and regarding
It is picture by video frame extraction when frequency frame meets preset extraction conditions.It is possible thereby to automatically will according to preset extraction conditions
The video frame extraction for meeting preset condition in video call process is picture, captures video pictures, and pole manually without user
It is few to converse user video to form interference, be conducive to the state for capturing user's natural relaxation, thus effectively improve image zooming-out
Efficiency and quality.
As an example of the present embodiment, described image identification may include recognition of face, the preset extraction item
Part includes any one or more in following: occurring face in video frame；Face in video frame is in the finger in video frame
Positioning is set；The ratio that the area of face accounts for video frame area is greater than first threshold；The camera lens shooting angle of face meets angle item
Part；The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold；Occur in video frame
Specified expression.
Wherein, recognition of face can be expressed as obtaining face characteristic information for the face extraction in image, and according to this
Face characteristic information is identified, the process of recognition result is obtained.
For example, terminal device can detect extraction conditions are as follows: occur face in video frame；People in video frame
Face is in the designated position in video frame；The ratio that the area of face accounts for video frame area is greater than first threshold；The camera lens of face
Shooting angle meets angle conditions；The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second
Threshold value；And it in the case where occurring any one or more in specified expression in video frame, determines and face is carried out to video frame
Identification.
For example, the contour feature of video frame can be extracted if extraction conditions are face occur in video frame, and by video
The contour feature of frame carries out similarity comparison with the facial contour feature prestored, if the similarity that comparison obtains is greater than the first phase
Like degree threshold value, then it can determine that the video frame meets extraction conditions, and extracting the video frame is picture.The disclosure is it is possible thereby to root
The video frame for occurring face in video calling is automatically extracted according to the setting of user.
For example, if extraction conditions be video frame in face be in the designated position in video frame (such as video frame hit exactly
Between), then it first can determine whether occur face in video frame, then, in the case where can there is face in the video frame, determine
The coordinate range that face occurs in the video frame then can be true in the case where the coordinate range belongs to preset coordinate range
The fixed video frame meets extraction conditions, and extracting the video frame is picture.The disclosure is it is possible thereby to which the setting according to user is automatic
Video frame of the face in suitable position in extraction video calling.
For example, if the ratio that the area that extraction conditions are face accounts for video frame area is greater than first threshold, it can first really
Determine whether occur face in video frame, then, in the case where can there is face in the video frame, determines the area of human face region
With the ratio of video frame area, and the area of face account for video frame area ratio be greater than preset first threshold when, determine
The video frame meets extraction conditions, and extracting the video frame is picture.The disclosure it is possible thereby to mention automatically according to the setting of user
Take the sizeable video frame of face in video calling.
For example, can first be determined in video frame if the camera lens shooting angle that extraction conditions are face meets angle conditions
Whether there is face, then, in the case where can there is face in the video frame, determines the face position of face, and according to five
The position of official determines the camera lens shooting angle (such as can be 35 degree) of face in the video frame.If the face in the video frame
Camera lens shooting angle meet angle conditions (such as can for 30 degree to 45 degree), then can determine that the video frame meets extraction item
Part, and extracting the video frame is picture.The disclosure is clapped it is possible thereby to automatically extract face in video calling according to the setting of user
Take the photograph the video frame that angle meets predetermined angle.
For example, if extraction conditions are less than for the difference of the brightness of human face region and the brightness of the background area in addition to human face region
Second threshold then first can determine whether occur face in video frame, then, can occur the case where face in the video frame
Under, determining the difference of the brightness of human face region and the brightness of the background area in addition to human face region, (or human face region is bright
The ratio of degree and the brightness of the background area in addition to human face region), and in the brightness of human face region and the back in addition to human face region
When the difference of the brightness of scene area is less than second threshold, determine that the video frame meets extraction conditions, and extracting the video frame is picture.
The disclosure is it is possible thereby to automatically extract face and the suitable video frame of background luminance in video calling according to the setting of user.
For example, can occur the feelings of face in determining video frame if extraction conditions are the expression laughed at occur in video
Under condition, the characteristic information of face in video frame, and the characteristic information for the face that extraction is obtained and preset smiling face's feature are extracted
Information carries out similarity comparison, is greater than the in the similarity for extracting obtained face characteristic information and preset smiling face's characteristic information
When two similarity thresholds, it can determine occur the expression laughed in video frame, and extracting the video frame is picture.Thus the disclosure may be used
The video frame comprising specified expression in video calling is automatically extracted with the setting according to user.
As an example of the present embodiment, described image identification may include recongnition of objects, described preset to mention
It includes one of following or a variety of for taking condition: clothing color and background color meet preset collocation condition in video frame,
Described in target object include clothes；Occurs target object in video frame.
Wherein, recongnition of objects can be expressed as whether belonging to the object in video pictures the process of specified target
(for example, whether there is specified plant and animal species in video frame picture, specified natural feature, the appearance of specified people is specified
Colour match etc.).
For example, terminal device can detect extraction conditions are as follows: clothing color and background color accord in video frame
It closes in the case where there is target object in preset collocation condition or video frame, determines and recongnition of objects is carried out to video frame.
For example, if extraction conditions are that clothing color and background color meet preset collocation condition in video frame, and preset
Collocation condition include preset color color number range, then can during recongnition of objects, first determine video frame
In whether there are clothes, and in the case where there are clothes in the video frame, determine the color number of clothing color and background color.It is taking
When the color number of dress color and background color belongs to the range of preset color color number, clothing color and background face in video frame are determined
Color meets preset collocation condition, and extracting the video frame is picture.It is possible thereby to which the setting according to user automatically extracts video
The video frame of clothes and background color appropriate mix in call.
For example, if extraction conditions are to occur target object in video frame, and target object is specified people (for example, certain position
Certain kith and kin of star or user), then the facial feature information of specified people can be preset, and occur people in determining video frame
When face, the facial feature information of face in video frame is extracted, if there is the facial feature information phase with specified people in video frame
It is greater than the facial feature information of third similarity threshold like degree, it is determined that the video frame meets extraction conditions, and extracts the video
Frame is picture.It is possible thereby to which the setting according to user automatically extracts the video frame for occurring nominator in video calling.
For example, if extraction conditions are to occur target object in video frame, and target object is people's (example of specified Facial Features
Such as, women, male or beauty and ugliness etc.), then specified Facial Features information can be preset, and occur face in determining video frame
When, the Facial Features information of one or more faces in video frame is extracted, is believed if existing in video frame with specified Facial Features
Ceasing the Facial Features information that similarity is greater than the face of the 4th similarity threshold, it is determined that the video frame meets extraction conditions, and
Extracting the video frame is picture.It is possible thereby to automatically extract the video for occurring specified appearance in video calling according to the setting of user
Frame.Wherein, for specified Facial Features information, terminal device can also be according to the predetermined one group of user nominator of user
The picture of face appearance carries out sample training, so that obtaining the demand that specified Facial Features information more meets user.
For example, if extraction conditions are to occur target object in video frame, and target object is specified landscape (for example, sea
Shore, high mountain etc.), then the image feature information of specified landscape can be preset, and in the image feature information for determining video frame, if
The image feature information similarity of the image feature information of frequency frame and specified landscape is greater than the 5th similarity threshold, it is determined that should
Video frame meets extraction conditions, and extracting the video frame is picture.It is possible thereby to which it is logical to automatically extract video according to the setting of user
Occurs the video frame of specified landscape in words.
For example, if extraction conditions are to occur target object in video frame, and target object is specified animal (for example, bear
Cat, elephant etc.), then the image feature information of specified animal can be preset, and in the image feature information for determining video frame, if
The image feature information similarity of the image feature information of frequency frame and specified animal is greater than the 6th similarity threshold, it is determined that should
Video frame meets extraction conditions, and extracting the video frame is picture.It is possible thereby to which it is logical to automatically extract video according to the setting of user
Occurs the video frame of specified animal in words.
Fig. 2 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.As shown in Fig. 2, Fig. 2 with
Difference between Fig. 1 is that the method can also include:
Step 200, the option of extraction conditions is provided.
Step 201, the extraction conditions selected are determined as preset extraction conditions.
For example, terminal device can before being identified to the video frame of acquisition (or carry out video calling it
Before, it is not limited here), show selection interface, which may include multiple option (examples for selective extraction condition
Such as, smiling face identifies, seabeach identification, children's identification etc.), terminal can have detecting the one or more for the selection interface
When imitating selection operation (such as clicking operation, slide etc.), by extraction corresponding to the one or more effectively selection operation
Condition is as preset extraction conditions.In this way, the extraction conditions that the disclosure can be selected according to user, extract from video and meet
The picture that user requires, flexibly meets the different demands of user.In one possible implementation, default can also be preset
Extraction conditions, it is not limited here.
Fig. 3 is a kind of flow chart of image extraction method shown according to an exemplary embodiment.As shown in figure 3, Fig. 3 with
Difference between Fig. 1 is that the method can also include:
Step 300, authorization requests are sent to video calling opposite end, the authorization requests identify that the video is logical for requesting
Talk about video caused by opposite end；
Step 301, when receiving the authorization message that video calling opposite end is returned in response to the authorization requests, to video
Video frame in video caused by call opposite end carries out image recognition.
For example, terminal device can be sent out before the video frame of identification video calling opposite end to video calling opposite end
Authorization requests are sent, which can be used for requesting to identify the video frame in video caused by the video calling opposite end.Depending on
Frequency call opposite end can provide the option for allowing or terminal device not being allowed to identify video frame when receiving authorization requests, and
It can be when detecting that the option for the video frame for allowing terminal device to identify the video in video calling is triggered, to terminal device
Return to authorization message.Terminal device, can when receiving the authorization message that video calling opposite end is returned in response to the authorization requests
To obtain the video of video calling opposite end generation, and image recognition is carried out to the video frame in the video, and according to image recognition
Recognition result, the video frame extraction that will be deemed as meeting preset condition is image.In this way, terminal device is in identification video calling
Before video caused by opposite end, it is necessary to the authorization of video calling opposite end is obtained, so that terminal device is in the case where without permission
It can not identify the video of video calling opposite end, the video of video calling opposite end is effectively avoided arbitrarily to be intercepted, be conducive to ensure view
The privacy of frequency call peer user.
The disclosure can be before the video frame of identification video calling local terminal or video calling opposite end, to video calling opposite end
Authorization requests are sent, authorization requests can also be sent to video calling opposite end after the video frame of identification video calling local terminal.
In a kind of application example, carried out so that terminal device is mobile phone as an example set forth below.
Can be before video calling, user, which can be set, proposes the video progress video frame of oneself shooting or other side's shooting
It takes, the extraction conditions for needing to capture automatically from video call process can also be selected according to factors such as video calling environment.Example
Such as, the face in video frame is in the designated position in video frame；The ratio that the area of face accounts for video frame area is greater than first
Threshold value；The camera lens shooting angle of face meets angle conditions；The brightness of human face region and the background area in addition to human face region
The difference of brightness is less than second threshold.Occur in video frame clothing color in specified expression video frame meet with background color it is preset
Collocation condition；Occurs target object in video frame (for example, people, user that user specifies specify the people of beauty and ugliness degree, such as sea
Animals and plants that the landscape and user that the users such as beach, mountains and rivers specify are specified or article etc.).
In video call process, the extraction conditions that mobile phone can be selected according to user, automatic capture (extracts video frame as figure
The example of piece) meet the video frame formation picture of extraction conditions and is stored in photograph album.
For example, user passes through mobile phone indoors and good friend carries out video calling, user can set extraction conditions as video
Middle face is in picture middle, and face is in smile expression, and the shooting angle of face is 30 degree, then mobile phone can be by the view
In frequency communication process, face is in picture middle, face is in the video frame that smile expression and shooting angle are 30 degree and mentions
It is taken as picture, and is stored as photograph album.
For another example, user travels by the sea and carries out video calling by mobile phone and good friend, and user can set extraction conditions
To occur seabeach landscape in video, then the video frame extraction for seabeach landscape occur can be by mobile phone by video call process
Picture, and it is stored as photograph album.
In this way, can be carried out certainly according to the setting of user to the beautiful background occurred in video calling or interesting scene
It is dynamic efficiently and naturally to capture, it captures without user, the video calling of user is impacted manually seldom, flexibly meet and use
The candid photograph demand at family leaves fine memory for user.
Fig. 4 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.As shown in figure 4, the device
May include:
Identification module 41, for being carried out to the video frame in video caused by video calling in video call process
Image recognition obtains recognition result.
Judgment module 42, for judging whether the video frame meets preset extraction conditions according to the recognition result.
Extraction module 43, for when the video frame meets the preset extraction conditions, by the video frame extraction
For picture.
In one possible implementation, video caused by video calling includes either end or multiterminal in video calling
The video of shooting.
In one possible implementation, described image identification includes recognition of face,
The preset extraction conditions include any one or more in following:
Occurs face in video frame.
Face in video frame is in the designated position in video frame.
The ratio that the area of face accounts for video frame area is greater than first threshold.
The camera lens shooting angle of face meets angle conditions.
The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold.
Occurs specified expression in video frame.
In one possible implementation, described image identification includes recongnition of objects,
The preset extraction conditions include one of following or a variety of:
Clothing color and background color meet preset collocation condition in video frame, wherein the target object includes clothes
Dress.
Occurs target object in video frame.
The disclosure is by carrying out image knowledge to the video frame in video caused by video calling in video call process
Not, recognition result is obtained, according to the recognition result, judges whether the video frame meets preset extraction conditions, and regarding
It is picture by video frame extraction when frequency frame meets preset extraction conditions.It is possible thereby to automatically will according to preset extraction conditions
The video frame extraction for meeting preset condition in video call process is picture, captures video pictures manually without user, will not be right
User video is conversed to form interference, is conducive to the state for capturing user's natural relaxation, thus improves image zooming-out efficiency.
Fig. 5 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.For ease of description, scheming
Part related to the present embodiment is only illustrated in 5.Label component function having the same identical with Fig. 4 in Fig. 5, in order to
For the sake of simplicity, the detailed description to these components is omitted.As shown in Figure 5
In one possible implementation, described device further include:
Display module 44, for providing the option of extraction conditions.
Determining module 45, for the extraction conditions selected to be determined as preset extraction conditions.
In one possible implementation, described device can also include:
Sending module 46, for sending authorization requests to video calling opposite end, the authorization requests are for requesting identification institute
State video caused by video calling opposite end；
Receiving module 47, in the authorization message for receiving video calling opposite end and being returned in response to the authorization requests
When, image recognition is carried out to the video frame in video caused by video calling opposite end.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 6 is a kind of block diagram of image acquiring apparatus shown according to an exemplary embodiment.For example, device 800 can be with
It is mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, Medical Devices, body-building
Equipment, personal digital assistant etc..
Referring to Fig. 6, device 800 may include following one or more components: processing component 802, memory 804, power supply
Component 806, multimedia component 808, audio component 810, the interface 812 of input/output (I/O), sensor module 814, and
Communication component 816.
The integrated operation of the usual control device 800 of processing component 802, such as with display, telephone call, data communication, phase
Machine operation and record operate associated operation.Processing component 802 may include that one or more processors 820 refer to execute
It enables, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more modules, just
Interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, it is more to facilitate
Interaction between media component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in device 800.These data are shown
Example includes the instruction of any application or method for operating on device 800, contact data, and telephone book data disappears
Breath, picture, video etc..Memory 804 can be by any kind of volatibility or non-volatile memory device or their group
It closes and realizes, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable to compile
Journey read-only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, flash
Device, disk or CD.
Power supply module 806 provides electric power for the various assemblies of device 800.Power supply module 806 may include power management system
System, one or more power supplys and other with for device 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen of one output interface of offer between described device 800 and user.One
In a little embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, screen
Curtain may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touch sensings
Device is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding action
Boundary, but also detect duration and pressure associated with the touch or slide operation.In some embodiments, more matchmakers
Body component 808 includes a front camera and/or rear camera.When device 800 is in operation mode, such as screening-mode or
When video mode, front camera and/or rear camera can receive external multi-medium data.Each front camera and
Rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as output and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when device 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone is matched
It is set to reception external audio signal.The received audio signal can be further stored in memory 804 or via communication set
Part 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, is used for output audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, and the state for providing various aspects for device 800 is commented
Estimate.For example, sensor module 814 can detecte the state that opens/closes of device 800, and the relative positioning of component, for example, it is described
Component is the display and keypad of device 800, and sensor module 814 can be with 800 1 components of detection device 800 or device
Position change, the existence or non-existence that user contacts with device 800,800 orientation of device or acceleration/deceleration and device 800
Temperature change.Sensor module 814 may include proximity sensor, be configured to detect without any physical contact
Presence of nearby objects.Sensor module 814 can also include optical sensor, such as CMOS or ccd image sensor, at
As being used in application.In some embodiments, which can also include acceleration transducer, gyro sensors
Device, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between device 800 and other equipment.Device
800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.In an exemplary implementation
In example, communication component 816 receives broadcast singal or broadcast related information from external broadcasting management system via broadcast channel.
In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, to promote short range communication.Example
Such as, NFC module can be based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band (UWB) technology,
Bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 800 can be believed by one or more application specific integrated circuit (ASIC), number
Number processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 804 of instruction, above-metioned instruction can be executed by the processor 820 of device 800 to complete the above method.For example,
The non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk
With optical data storage devices etc..
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (14)
1. a kind of image extraction method characterized by comprising
In video call process, image recognition is carried out to the video frame in video caused by video calling, obtains identification knot
Fruit；
According to the recognition result, judge whether the video frame meets preset extraction conditions；
It is picture by the video frame extraction when the video frame meets the preset extraction conditions.
2. the method according to claim 1, wherein video caused by video calling includes appointing in video calling
The video of one end or multiterminal shooting.
3. method according to claim 1 or 2, which is characterized in that described image identification includes recognition of face, described default
Extraction conditions include any one or more in following:
Occurs face in video frame；
Face in video frame is in the designated position in video frame；
The ratio that the area of face accounts for video frame area is greater than first threshold；
The camera lens shooting angle of face meets angle conditions；
The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold；
Occurs specified expression in video frame.
4. method according to claim 1 or 2, which is characterized in that described image identification includes recongnition of objects,
The preset extraction conditions include one of following or a variety of:
Clothing color and background color meet preset collocation condition in video frame, wherein the target object includes clothes；
Occurs target object in video frame.
5. method according to claim 1 or 2, which is characterized in that the method also includes:
The option of extraction conditions is provided；
The extraction conditions selected are determined as preset extraction conditions.
6. method according to claim 1 or 2, which is characterized in that the method also includes:
Authorization requests are sent to video calling opposite end, the authorization requests are for requesting produced by identifying the video calling opposite end
Video；
When receiving the authorization message that video calling opposite end is returned in response to the authorization requests, is produced from video calling opposite end
Video frame in raw video carries out image recognition.
7. a kind of image acquiring apparatus characterized by comprising
Identification module, for carrying out image knowledge to the video frame in video caused by video calling in video call process
Not, recognition result is obtained；
Judgment module, for judging whether the video frame meets preset extraction conditions according to the recognition result；
Extraction module, for being picture by the video frame extraction when the video frame meets the preset extraction conditions.
8. device according to claim 7, which is characterized in that video caused by video calling includes appointing in video calling
The video of one end or multiterminal shooting.
9. device according to claim 7 or 8, which is characterized in that described image identification includes recognition of face, described default
Extraction conditions include any one or more in following:
Occurs face in video frame；
Face in video frame is in the designated position in video frame；
The ratio that the area of face accounts for video frame area is greater than first threshold；
The camera lens shooting angle of face meets angle conditions；
The difference of the brightness of human face region and the brightness of the background area in addition to human face region is less than second threshold；
Occurs specified expression in video frame.
10. device according to claim 7 or 8, which is characterized in that described image identification includes recongnition of objects,
The preset extraction conditions include one of following or a variety of:
Clothing color and background color meet preset collocation condition in video frame, wherein the target object includes clothes；
Occurs target object in video frame.
11. device according to claim 7 or 8, which is characterized in that described device further include:
Display module, for providing the option of extraction conditions；
Determining module, for the extraction conditions selected to be determined as preset extraction conditions.
12. device according to claim 7 or 8, which is characterized in that described device further include:
Sending module, for sending authorization requests to video calling opposite end, the authorization requests identify the video for requesting
Video caused by call opposite end；
Receiving module, for when receiving the authorization message that video calling opposite end is returned in response to the authorization requests, to view
Video frame in video caused by frequency call opposite end carries out image recognition.
13. a kind of image acquiring apparatus characterized by comprising
Processor；
Memory for storage processor executable instruction；
Wherein, the processor is configured to:
Execute method as claimed in any of claims 1 to 6.
14. a kind of non-transitorycomputer readable storage medium makes when the instruction in the storage medium is executed by processor
It obtains processor and is able to carry out method as claimed in any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811159896.2A CN109145878B (en) | 2018-09-30 | 2018-09-30 | Image extraction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811159896.2A CN109145878B (en) | 2018-09-30 | 2018-09-30 | Image extraction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109145878A true CN109145878A (en) | 2019-01-04 |
| CN109145878B CN109145878B (en) | 2022-02-15 |
Family
ID=64814238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811159896.2A Active CN109145878B (en) | 2018-09-30 | 2018-09-30 | Image extraction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109145878B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246243A (en) * | 2019-05-09 | 2019-09-17 | 厦门中控智慧信息技术有限公司 | Access control method, device and terminal device |
| CN110287949A (en) * | 2019-07-30 | 2019-09-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Video clip extracting method, device, equipment and storage medium |
| WO2021159609A1 (en) * | 2020-02-11 | 2021-08-19 | 深圳壹账通智能科技有限公司 | Video lag identification method and apparatus, and terminal device |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101018314A (en) * | 2006-02-07 | 2007-08-15 | Lg电子株式会社 | The apparatus and method for image communication of mobile communication terminal |
| CN101622871A (en) * | 2007-02-27 | 2010-01-06 | 埃森哲环球服务有限公司 | Video call device control |
| CN102098379A (en) * | 2010-12-17 | 2011-06-15 | 惠州Tcl移动通信有限公司 | Terminal as well as method and device for acquiring real-time video images of terminal |
| CN102752727A (en) * | 2012-05-30 | 2012-10-24 | 北京三星通信技术研究有限公司 | Terminal remote guide method and terminal remote guide device |
| CN103716227A (en) * | 2013-12-12 | 2014-04-09 | 北京京东尚科信息技术有限公司 | Method and device for performing information interaction in instant messenger |
| CN104869347A (en) * | 2015-05-18 | 2015-08-26 | 小米科技有限责任公司 | Video calling method and apparatus |
| CN105516883A (en) * | 2014-09-22 | 2016-04-20 | 中兴通讯股份有限公司 | Remote assistance method and device |
| CN105635567A (en) * | 2015-12-24 | 2016-06-01 | 小米科技有限责任公司 | Shooting method and device |
| CN105976444A (en) * | 2016-04-28 | 2016-09-28 | 信阳师范学院 | Video image processing method and apparatus |
| CN107506755A (en) * | 2017-09-26 | 2017-12-22 | 云丁网络技术(北京)有限公司 | Monitoring video recognition methods and device |
| CN107635110A (en) * | 2017-09-30 | 2018-01-26 | 维沃移动通信有限公司 | A kind of video interception method and terminal |
| US20180039845A1 (en) * | 2016-08-08 | 2018-02-08 | International Business Machines Corporation | Method and apparatus to identify a live face image using a thermal radiation sensor and a visual radiation sensor |
| CN107948506A (en) * | 2017-11-22 | 2018-04-20 | 珠海格力电器股份有限公司 | A kind of image processing method, device and electronic equipment |
| CN108471632A (en) * | 2018-03-01 | 2018-08-31 | 广东欧珀移动通信有限公司 | Information processing method, device, mobile terminal and computer readable storage medium |
-
2018
- 2018-09-30 CN CN201811159896.2A patent/CN109145878B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101018314A (en) * | 2006-02-07 | 2007-08-15 | Lg电子株式会社 | The apparatus and method for image communication of mobile communication terminal |
| CN101622871A (en) * | 2007-02-27 | 2010-01-06 | 埃森哲环球服务有限公司 | Video call device control |
| CN102098379A (en) * | 2010-12-17 | 2011-06-15 | 惠州Tcl移动通信有限公司 | Terminal as well as method and device for acquiring real-time video images of terminal |
| CN102752727A (en) * | 2012-05-30 | 2012-10-24 | 北京三星通信技术研究有限公司 | Terminal remote guide method and terminal remote guide device |
| CN103716227A (en) * | 2013-12-12 | 2014-04-09 | 北京京东尚科信息技术有限公司 | Method and device for performing information interaction in instant messenger |
| CN105516883A (en) * | 2014-09-22 | 2016-04-20 | 中兴通讯股份有限公司 | Remote assistance method and device |
| CN104869347A (en) * | 2015-05-18 | 2015-08-26 | 小米科技有限责任公司 | Video calling method and apparatus |
| CN105635567A (en) * | 2015-12-24 | 2016-06-01 | 小米科技有限责任公司 | Shooting method and device |
| CN105976444A (en) * | 2016-04-28 | 2016-09-28 | 信阳师范学院 | Video image processing method and apparatus |
| US20180039845A1 (en) * | 2016-08-08 | 2018-02-08 | International Business Machines Corporation | Method and apparatus to identify a live face image using a thermal radiation sensor and a visual radiation sensor |
| CN107506755A (en) * | 2017-09-26 | 2017-12-22 | 云丁网络技术(北京)有限公司 | Monitoring video recognition methods and device |
| CN107635110A (en) * | 2017-09-30 | 2018-01-26 | 维沃移动通信有限公司 | A kind of video interception method and terminal |
| CN107948506A (en) * | 2017-11-22 | 2018-04-20 | 珠海格力电器股份有限公司 | A kind of image processing method, device and electronic equipment |
| CN108471632A (en) * | 2018-03-01 | 2018-08-31 | 广东欧珀移动通信有限公司 | Information processing method, device, mobile terminal and computer readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 冯雪飞: "视频通话中隐私保护专利技术分析", 《HTTPS://T.CNKI.NET/KCMS/DETAIL/11.2739.N.20180912.1747.010.HTML》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110246243A (en) * | 2019-05-09 | 2019-09-17 | 厦门中控智慧信息技术有限公司 | Access control method, device and terminal device |
| CN110287949A (en) * | 2019-07-30 | 2019-09-27 | 腾讯音乐娱乐科技（深圳）有限公司 | Video clip extracting method, device, equipment and storage medium |
| WO2021159609A1 (en) * | 2020-02-11 | 2021-08-19 | 深圳壹账通智能科技有限公司 | Video lag identification method and apparatus, and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109145878B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104317932B (en) | Method for picture sharing and device | |
| KR101906827B1 (en) | Apparatus and method for taking a picture continously | |
| CN105528606B (en) | Area recognizing method and device | |
| CN105654039B (en) | The method and apparatus of image procossing | |
| JP2016531362A (en) | Skin color adjustment method, skin color adjustment device, program, and recording medium | |
| CN104700353B (en) | Image filters generation method and device | |
| CN105809174B (en) | Identify the method and device of image | |
| CN105302315A (en) | Image processing method and device | |
| CN105095873A (en) | Picture sharing method and apparatus | |
| AU2019418925A1 (en) | Photographing method and electronic device | |
| KR101170338B1 (en) | Method For Video Call And System thereof | |
| CN104850828A (en) | Person identification method and person identification device | |
| US20170161553A1 (en) | Method and electronic device for capturing photo | |
| CN105631804B (en) | Image processing method and device | |
| CN104933419B (en) | The method, apparatus and red film for obtaining iris image identify equipment | |
| CN105528078B (en) | The method and device of controlling electronic devices | |
| CN113727012A (en) | Shooting method and terminal | |
| CN106375782A (en) | Video playing method and device | |
| WO2017088257A1 (en) | Facial-album-based music playing method and apparatus, and terminal device | |
| CN105335714B (en) | Photo processing method, device and equipment | |
| CN109145878A (en) | image extraction method and device | |
| CN108898591A (en) | Methods of marking and device, electronic equipment, the readable storage medium storing program for executing of picture quality | |
| CN104408404A (en) | Face identification method and apparatus | |
| CN107426489A (en) | Processing method, device and terminal during shooting image | |
| CN109033991A (en) | A kind of image-recognizing method and device |
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 |