CN108259769A - Image processing method, device, storage medium and electronic equipment - Google Patents
Image processing method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN108259769A CN108259769A CN201810277051.7A CN201810277051A CN108259769A CN 108259769 A CN108259769 A CN 108259769A CN 201810277051 A CN201810277051 A CN 201810277051A CN 108259769 A CN108259769 A CN 108259769A
- Authority
- CN
- China
- Prior art keywords
- image
- frame
- picture frame
- facial image
- preset condition
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Studio Devices (AREA)
Abstract
This application discloses a kind of image processing method, device, storage medium and electronic equipments.The image processing method includes:Receive image acquisition instruction;It is instructed in response to image acquisition, cached picture frame is obtained from caching sequence according to caching sequencing, wherein, an identifiable face is included at least in picture frame;Judge whether the eye areas of all persons in acquired current image frame meets preset condition;If so, stop obtaining picture frame;If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding with the picture frame that an at least frame eye areas meets preset condition.Whether this programme meets condition by eye areas in the determining picture frame obtained in real time, carrys out the quantity that dynamic adjusts the picture frame that need to be obtained, improves the flexibility of picture frame acquisition;Meanwhile can reduce to a certain extent and grab frame time, improve image taking speed.
Description
Technical field
The application belongs to image technique field more particularly to a kind of image processing method, device, storage medium and electronics are set
It is standby.
Background technology
It takes pictures and also known as photographs, takes a picture, refer generally to the process for exposing light-sensitive medium by the light that object is reflected, lead to
Often use mechanical camera or digital camera.With the universal of intelligent electronic device, the diversification of function, intelligent electricity is used
The drop that sub- equipment photographs to record life becomes popular.
After the shooting preview interface of electronic equipment camera is entered, electronic equipment can acquire image and be shown on interface
For user's preview.Electronic equipment the image collected can be stored in caching sequence, i.e., be stored in the caching sequence more
Frame image.In the related art, when needing to carry out certain processing to the image collected, electronic equipment can be from caching sequence
Collected multiple image recently is obtained in row.However, this image acquisition mode is grabbed, frame time is longer, leads to electronic equipment
Image taking speed is slower.
Invention content
The embodiment of the present application provides a kind of image processing method, device, storage medium and electronic equipment, can promote image
Shooting quality.
The embodiment of the present application provides a kind of image processing method, applied to electronic equipment, including:
Receive image acquisition instruction;
In response to described image acquisition instruction, cached image is obtained from caching sequence according to caching sequencing
Frame, wherein, an identifiable face is included at least in picture frame;
Judge whether the eye areas of all persons in acquired current image frame meets preset condition;
If so, stop obtaining picture frame;
If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding with an at least frame eye
Eyeball region meets the picture frame of preset condition.
The embodiment of the present application provides a kind of image processing apparatus, applied to electronic equipment, including:
Receiving module, for receiving image acquisition instruction;
Respond module, in response to described image acquisition instruction, being obtained from caching sequence according to caching sequencing
The picture frame cached, wherein, an identifiable face is included at least in picture frame;
Whether judgment module, the eye areas for judging all persons in acquired current image frame meet default item
Part;
Control module, for the respond module when the judgment module is judged to being, to be controlled to stop obtaining picture frame;
The respond module, for when the judgment module is determined as no, continuing to obtain picture frame, until acquired
In picture frame, each personage is corresponding with the picture frame that an at least frame eye areas meets preset condition.
The embodiment of the present application provides a kind of storage medium, computer program is stored thereon with, when the computer program exists
When being performed on computer so that the computer performs the step in image processing method provided by the embodiments of the present application.
The embodiment of the present application also provides a kind of electronic equipment, and including memory, processor, the processor is by calling
The computer program stored in memory is stated, for performing the step in image processing method provided by the embodiments of the present application.
In the embodiment of the present application, instructed by receiving image acquisition;It is instructed in response to image acquisition, it is successively suitable according to caching
Sequence obtains cached picture frame from caching sequence, wherein, an identifiable face is included at least in picture frame;Judge institute
Whether the eye areas of all persons meets preset condition in the current image frame of acquisition;If so, stop obtaining picture frame;If
It is no, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding at least frame eye areas satisfaction
The picture frame of preset condition.Whether this programme meets condition by eye areas in the determining picture frame obtained in real time, carrys out dynamic
The quantity of picture frame that need to be obtained is adjusted, improves the flexibility of picture frame acquisition;Meanwhile it can reduce to a certain extent and grab frame
Time improves image taking speed.
Description of the drawings
Below in conjunction with the accompanying drawings, it is described in detail by the specific embodiment to the present invention, technical scheme of the present invention will be made
And advantage is apparent.
Fig. 1 is the flow diagram of image processing method provided by the embodiments of the present application.
Fig. 2 is another flow diagram of image processing method provided by the embodiments of the present application.
Fig. 3 is an application example schematic diagram of image processing method provided by the embodiments of the present application.
Fig. 4 is the structure diagram of image processing apparatus provided by the embodiments of the present application.
Fig. 5 is another structure diagram of image processing apparatus provided by the embodiments of the present application.
Fig. 6 is the another structure diagram of image processing apparatus provided by the embodiments of the present application.
Fig. 7 is the structure diagram of electronic equipment provided by the embodiments of the present application.
Fig. 8 is the structure diagram of the image processing circuit of electronic equipment provided by the embodiments of the present application.
Specific embodiment
Schema is please referred to, wherein identical element numbers represent identical component, the principle of the present invention is to implement one
It is illustrated in appropriate computing environment.The following description be based on the illustrated specific embodiment of the invention, should not be by
It is considered as the limitation present invention other specific embodiments not detailed herein.
It is understood that the executive agent of the embodiment of the present application can be the electricity of smart mobile phone or tablet computer etc.
Sub- equipment.
Referring to Fig. 1, Fig. 1 is the flow diagram of image processing method provided by the embodiments of the present application, flow can wrap
It includes:
101 receive image acquisition instruction.
User often needs to use electronic equipment camera and is shot.In the shooting preview interface for entering electronic equipment camera
Afterwards, electronic equipment, which can be acquired image by the imaging sensor built in it and is shown on interface, supplies user's preview.However
In image acquisition process, since user is accustomed to, eyes are easily influenced by outside environmental elements (such as illumination), too strong in illumination
In the case of easily blink or close one's eyes.Especially when more people take a group photo, since the relationship of erect-position also needs to carry out position adjustment, movement etc.,
Easily because face shaking causes facial image unstable, shaking is more serious, it is more to shake number, and the stability for leading to image is got over
Difference.Based on these factors, in the related art, all larger image of all human eyes is synthesized using spininess image is obtained.However,
If all human eyes are all bigger in the first frame image grabbed at the beginning, then just It is not necessary to continue crawl figure backward again
As if continuing to capture the waste it will cause resource.Therefore, by the way of this crawl multiple image, on the one hand easily
It is longer to lead to grab frame time, reduces image taking speed;On the other hand it be easy to cause the waste of electronic equipment resource.
Wherein, image acquisition instruction can be after camera of electronic equipment is opened, and user is by pressing electronic equipment
On physical shutter key triggered;In addition, image acquisition instruction can also be after camera of electronic equipment is opened, user
It is triggered by the virtual shutter control touched on electronic equipment display interface, this is not specifically limited.
102nd, it is instructed in response to the image acquisition, cached image is obtained from caching sequence according to caching sequencing
Frame, wherein, an identifiable face is included at least in picture frame.
In some embodiments, it can be passed by the image that electronic equipment internal is set to cache the picture frame in sequence
Sensor is acquired and is cached to obtained from temporary storage in real time.After image acquisition instruction is received, electronic equipment can
It responds the instruction and captures corresponding picture frame from caching sequence.
In specific implementation process, it can successively capture and delay from the caching sequence according to the caching sequence after arriving first
Deposit picture frame, with ensure crawl image continuity.Wherein, grasp speed can be according to the shutter parameter of electronic equipment camera
And it determines.It can include one or more personages in acquired picture frame, and including at least a recognizable face, with after an action of the bowels
Continuous image processing operations.
103rd, judge whether the eye areas of all persons in acquired current image frame meets preset condition;If so,
Step 105 is performed, if it is not, performing step 104.
Specifically, whenever the picture frame in a frame buffer sequence is obtained, to the eye areas of personage in current image frame
Relevant detection, judgement processing are carried out, to determine whether all eye areas in the current image frame meet preset condition.
It in some embodiments, can be by the facial image of personage each in current image frame, mark corresponding with each personage
The facial image of quasi- state is compared, to judge whether the eye areas of each personage in current image frame meets preset condition.
That is, step " judging whether the eye areas of all persons in acquired current image frame meets preset condition ", can wrap
Include below scheme:
Facial image is extracted from acquired current image frame;
Target sample facial image is matched from presetting database according to facial image;
It is compared by facial image, with target sample facial image, obtains comparison result;
According to comparison result, judge whether the eye areas of all persons in current image frame meets preset condition.
Specifically, since the original image that directly acquires is due to the limitation by various conditions and random disturbances, often not
It can directly use, which can be pre-processed, such as gray correction, noise filtering pretreatment operation.Then,
Image recognition algorithm can be based on, the extraction of characteristics of image is carried out to pretreated current image frame, therefrom to extract color spy
Sign, textural characteristics, shape feature and spatial relation feature etc..So as to which current image frame is dropped to low-dimensional from high latitude,
To obtain most reflecting the low-dimensional sample characteristics of image essence.Based on this, it detected from current image frame, recognize face spy
Sign, such as eyes, nose, face face feature, so that it is determined that go out including facial image, and therefrom extraction is recognized
One or more facial images.
In practical application, need first to build the database for including all persons' face in the picture frame.That is, it needs advance
The human face image information of all persons in current image frame is acquired, to obtain the sample facial image of each personage, and by gained
To sample facial image be added in database, to build presetting database.In this way, it can be chosen from the preset data
With the matched sample facial image of facial image extracted.By by facial image, with the sample facial image that matches
It is compared, judges whether the eye areas of all persons in current image frame meets preset condition.
In some embodiments, step " matches corresponding sample face figure according to facial image from presetting database
Picture " can include below scheme:
Facial image is identified, obtains face recognition result;
According to face recognition result, obtained and the matched target sample facial image of facial image from presetting database.
Specifically, the facial image extracted can be identified, according to the identification each facial image of structure determination
Corresponding piece identity.And then corresponding with piece identity sample facial image is obtained from presetting database, using as mesh
This facial image of standard specimen.
In practical application, since face is there are the variation of espressiove, and the size of eyes is to be not quite similar under different expressions
's.It therefore, can be to store multiple and different expressions of same personage in presetting database in order to promote the accuracy of comparison result
Sample facial image, therefrom to match most suitable target sample facial image.
That is, in some embodiments, it can include in presetting database:Multiple sample face image sets;Sample people
It can include in face image set:The sample facial image of multiple and different expressions of same face.So, step is " according to face
Recognition result obtains and the matched target sample facial image of facial image from presetting database ", it can include flowing down
Journey:
According to face recognition result, determined from presetting database and the matched target sample face figure of the facial image
Image set closes;
Identify the expression of the facial image;
Target sample facial image is chosen from target sample face image set according to the expression.
Specifically, the facial image under each personage's difference expression can be acquired, when building presetting database to obtain
Multiple sample facial images of same personage, and multiple sample facial images are stored in the form of gathering to database.
In addition, when building presetting database, the facial image of same personage's different angle can also be acquired, such as positive visual angle
The facial image of degree, the facial image of left strabismus angle, right facial image for squinting angle etc., compare knot with further promotion
The accuracy of fruit.
When it is implemented, by facial image compared with target sample facial image when, due to the size of image, angle may
It has differences, leads to not directly relatively.Therefore, affine transform algorithm can be utilized, facial image is adjusted to and target sample
The same size of this facial image, in order to which subsequent image compares operation.That is, in some embodiments, step is " by the people
Face image is compared with target sample facial image, to obtain comparison result ", below scheme can be included:
The facial image is aligned with target sample facial image;
Calculate in the facial image after alignment eyes in the first opening degree of eye areas and target sample facial image
Second opening degree in region;
Compare the first opening degree and the second opening degree, to determine that the first opening degree is less than the second opening degree, obtain comparing knot
Fruit.
Specifically, using affine transform algorithm, facial image is aligned with target sample facial image, by facial image
Identical size and angle are adjusted to target sample facial image, so as to the direct comparison of the two.
In the first opening degree of eye areas in calculating the facial image after being aligned, can first obtain in eye areas
Fissura palpebrae value between eyelid and palpebra inferior is specifically as follows upper eyelid palpebra inferior in the maximum distance in horizontal direction.
Then, the fissura palpebrae value based on acquisition calculates the first opening degree.It in some embodiments, can be directly using fissura palpebrae value as folding
Degree.
Likewise, the second opening degree can refer to the computational methods of above-mentioned first opening degree, this is repeated no more.Finally, than
Compared with the size of the first opening degree and the second opening degree.
Then step " according to comparison result, judges whether the eye areas of all persons in current image frame meets default item
Part " can include below scheme:
If comparison result includes the first opening degree and is less than the second opening degree, the eye of all persons in current image frame is judged
Eyeball region is unsatisfactory for preset condition;
If comparison result does not include the first opening degree and is less than the second opening degree, all persons in current image frame are judged
Eye areas meets preset condition.
Specifically, comparison result includes the first opening degree less than there are someone in the second opening degree namely current image frame
Eyes size, do not reach corresponding eyes size in presetting database, therefore, it is determined that be unsatisfactory for condition.Comparison result is not
The eyes size for being less than all faces in the second opening degree namely picture frame including the first opening degree has all reached presetting database
In corresponding eyes size, therefore, it is determined that meet condition.
104th, judge in acquired picture frame, if each personage is corresponding with described at least frame eye areas satisfaction
The picture frame of preset condition;If so, step 105 is performed, if it is not, performing step 102.
Specifically, there are the eyes sizes of someone in current image frame, corresponding eye in presetting database is not reached
During eyeball size, detect in accessed all picture frames, if owner is corresponding with eyes size and has reached preset data
The picture frame of eyes size in library.
105th, stop continuing to obtain picture frame.
It, can be with specifically, when the eye areas of all persons in acquired current image frame all meets preset condition
Think that the eyes of all persons in picture frame are all bigger.At this point it is possible to stop continuing obtaining picture frame from caching sequence, with
This grabs frame time to shorten, so as to promote image taking speed.
In addition, when in acquired picture frame, each personage is corresponding with an at least frame eye areas and meets described preset
During the picture frame of condition, it is believed that in the picture frame grabbed, each personage is corresponding with the larger image of eyes.This
When, it can stop continuing obtaining picture frame from caching sequence, frame time be grabbed to shorten with this, so as to promote image taking speed.
From the foregoing, it will be observed that the image processing method provided in the embodiment of the present application, is instructed by receiving image acquisition;Response
It is instructed in image acquisition, cached picture frame is obtained from caching sequence according to caching sequencing, wherein, in picture frame extremely
Include an identifiable face less;Whether the eye areas of all persons meets default in current image frame acquired in judging
Condition;If so, stop obtaining picture frame;If it is not, then continue to obtain picture frame, until in acquired picture frame, Mei Yiren
Object is all corresponding with the picture frame that an at least frame eye areas meets preset condition.This programme passes through the determining picture frame obtained in real time
Whether middle eye areas meets condition, carrys out the quantity that dynamic adjusts the picture frame that need to be obtained, and improves the flexible of picture frame acquisition
Property;Meanwhile can reduce to a certain extent and grab frame time, improve image taking speed.
Referring to Fig. 2, Fig. 2 is another flow diagram of image processing method provided by the embodiments of the present application, flow can
To include:
201st, electronic equipment receives image acquisition instruction.
In some embodiments, image acquisition instruction can be after camera of electronic equipment is opened, and user passes through
What the physical shutter key on pressing electronic equipment was triggered.
In some embodiments, which instructs and can also be after camera of electronic equipment is opened, Yong Hutong
It crosses and touches what the virtual shutter control on electronic equipment display interface was triggered.
202nd, electronic equipment is instructed in response to the image acquisition, is obtained and is delayed from caching sequence according to caching sequencing
The picture frame deposited, wherein, an identifiable face is included at least in picture frame.
Specifically, after image acquisition instruction is received, electronic equipment can respond the instruction and be captured from caching sequence
Corresponding picture frame.
In specific implementation process, it can successively capture and delay from the caching sequence according to the caching sequence after arriving first
Deposit picture frame, with ensure crawl image continuity.Wherein, grasp speed can be according to the shutter parameter of electronic equipment camera
And it determines.It can include one or more personages in acquired picture frame, and including at least a recognizable face, with after an action of the bowels
Continuous image processing operations.
203rd, electronic equipment extracts facial image from acquired current image frame.
Specifically, since the original image that directly acquires is due to the limitation by various conditions and random disturbances, often not
It can directly use, which can be pre-processed, such as gray correction, noise filtering pretreatment operation.Then,
Image recognition algorithm can be based on, the extraction of characteristics of image is carried out to pretreated current image frame, therefrom to extract color spy
Sign, textural characteristics, shape feature and spatial relation feature etc..So as to which current image frame is dropped to low-dimensional from high latitude,
To obtain most reflecting the low-dimensional sample characteristics of image essence.Based on this, it detected from current image frame, recognize face spy
Sign, such as eyes, nose, face face feature, so that it is determined that go out including facial image, and therefrom extraction is recognized
One or more facial images.
204th, facial image is identified in electronic equipment, obtains face recognition result.
Specifically, the facial image extracted can be identified, according to the identification each facial image of structure determination
Corresponding piece identity.And then corresponding with piece identity sample facial image is obtained from presetting database, using as mesh
This facial image of standard specimen.
205th, electronic equipment obtains and the matched target sample of facial image according to face recognition result from presetting database
This facial image.
In the embodiment of the present application, need first to build the database for including all persons' face in the picture frame.That is, it needs
The human face image information of all persons in current image frame is acquired in advance, to obtain the sample facial image of each personage, and will
Obtained sample facial image is added in database, to build presetting database.It in this way, can be from the preset data
Choose the matched sample facial image of facial image with being extracted.By by facial image, with the sample face that matches
Image is compared, and judges whether the eye areas of all persons in current image frame meets preset condition.
In practical application, since face is there are the variation of espressiove, and the size of eyes is to be not quite similar under different expressions
's.It therefore, can be to store multiple and different expressions of same personage in presetting database in order to promote the accuracy of comparison result
Sample facial image, therefrom to match most suitable target sample facial image.It specifically, can be in structure preset data
During library, the facial image under each personage's difference expression is acquired, to obtain multiple sample facial images of same personage, and should
Multiple sample facial images are stored in the form of gathering to database.
That is, in some embodiments, it can include in presetting database:Multiple sample face image sets;Sample people
It can include in face image set:The sample facial image of multiple and different expressions of same face.It is possible to known according to face
Not as a result, determining to be somebody's turn to do with the matched target sample face image set of the facial image, then identification from presetting database
The expression of facial image chooses target sample facial image further according to the expression from target sample face image set.
For example, if the expression for recognizing the facial image is amimia face, the personage is corresponding from presetting database
In target sample face image set, amimia sample facial image is extracted, using as target sample facial image;For another example,
If the expression of the facial image is recognized to laugh, the corresponding target sample face image set of the personage from presetting database
In conjunction, the sample facial image of laugh expression is extracted, using as target sample facial image.
206th, electronic equipment is compared by the facial image, with target sample facial image, to obtain comparison result.
When it is implemented, by facial image compared with target sample facial image when, due to the size of image, angle may
It has differences, leads to not directly relatively.Therefore, affine transform algorithm can be utilized, facial image is adjusted to and target sample
This facial image is aligned, and facial image and target sample facial image is adjusted to identical size and angle, so as to the two
Direct comparison.
207th, electronic equipment is according to comparison result, judge all persons in current image frame eye areas whether meet it is pre-
If condition;If so, step 211 is performed, if it is not, performing step 208.
In some embodiments, can calculate alignment after facial image in eye areas the first opening degree and
The second opening degree of eye areas, then compares the first opening degree and the second opening degree in target sample facial image, to determine
First opening degree is less than the second opening degree, obtains comparison result.
Specifically, in the first opening degree of eye areas in calculating the facial image after being aligned, eyes can be first obtained
Fissura palpebrae value in region between upper eyelid and palpebra inferior, be specifically as follows upper eyelid palpebra inferior in horizontal direction most
Big distance.Then, the fissura palpebrae value based on acquisition calculates the first opening degree.It in some embodiments, can be directly by fissura palpebrae value
As opening degree.
Likewise, the second opening degree can refer to the computational methods of above-mentioned first opening degree, this is repeated no more.Finally, than
Compared with the size of the first opening degree and the second opening degree.
In addition, in one embodiment, electronic equipment can carry out the eyes size in detection image in the following way.
For example, electronic equipment can first pass through face and Eye Recognition, the ocular in image is identified, then obtain the eye
Region area ratio shared in whole image.The area ratio is big, it may be considered that the eyes of user are opened larger.The face
Product ratio is small, it may be considered that the eyes of user are opened smaller.For another example, electronic equipment can calculate human eye in image vertical
The number of shared pixel, the size of the number can be used to indicate that the size of human eye on direction.
208th, electronic equipment is judged in acquired picture frame, if each personage is corresponding with an at least frame eye areas
Meet the picture frame of the preset condition;If so, step 211 is performed, if it is not, performing step 209.
Specifically, there are the eyes sizes of someone in current image frame, corresponding eye in presetting database is not reached
During eyeball size, detect in accessed all picture frames, if owner is corresponding with eyes size and has reached preset data
The picture frame of eyes size in library.
209th, the frame number of picture frame accessed by electronic equipment statistics.
Specifically, an accumulator can be set, after image acquisition instruction is received, a frame is obtained from caching sequence
Picture frame just accumulates once, with the frame number of picture frame accessed by statistics.It, will when receiving next image acquisition instruction
Recorded data understands, and starts counting up again.
210th, electronic equipment judges whether the frame number reaches predetermined threshold value;If so, step 211 is performed, if it is not, performing step
202。
Specifically, the predetermined threshold value can be that image is captured as corresponding to a shutter set by production manufacturer
Frame number, for example, the frame number can be 4 frames, 6 frames, 8 frames etc..
It is understood that the frame number of picture frame may not exceed the predetermined threshold value accessed by above-mentioned statistics.
211st, electronic equipment stops obtaining picture frame.
It, can be with specifically, when the eye areas of all persons in acquired current image frame all meets preset condition
Think that the eyes of all persons in picture frame are all bigger.At this point it is possible to stop continuing obtaining picture frame from caching sequence, with
This grabs frame time to shorten, so as to promote image taking speed.
In addition, when in acquired picture frame, each personage is corresponding with an at least frame eye areas and meets described preset
During the picture frame of condition, it is believed that in the picture frame grabbed, each personage is corresponding with the larger image of eyes.This
When, it can stop continuing obtaining picture frame from caching sequence, frame time be grabbed to shorten with this, so as to promote image taking speed.
In addition, when the frame number of picture frame accessed by statistics reaches set upper limit value, force to stop continuing to postpone
It deposits and picture frame is obtained in sequence.
For example, by taking smart mobile phone as an example, after the preview interface of camera is entered, a frame is acquired every 30 milliseconds to 60 milliseconds
Image, and the image collected is saved in buffer queue.The buffer queue can be fixed length queue, such as the buffer queue can
To preserve the newest collected 15 frame image of mobile phone.
With reference to figure 3, user A opens that mobile phone camera is prepared as first, second, the third three people shoot group photo, and mobile phone can be examined at this time
The photographing instruction that user A is triggered by button of taking pictures is measured, and can be according to the photographing instruction at regular intervals from caching sequence
One frame image of middle crawl.If mobile phone is detected first, second in the first frame image that is captured and third eyes size, and respectively
It is compared with first, second pre-stored in mobile phone photo album, the third respective sample facial image, to determine in first frame image
Whether first, second and third eyes size degree reach the size degree of the eyes in respectively corresponding sample facial image.
Assuming that human eye magnitude numerical value is respectively in first, second sample facial image corresponding with the third three people:75、80、82.If the
In one frame image, the eyes magnitude numerical value of first is 80, the eyes magnitude numerical value that the eyes magnitude numerical value of second is 80, third is 84, then
The eyes size of all persons is all larger in apparent first frame image, can stop capturing image from caching sequence, and will at this time
First frame image is directly output to be used as photo in photograph album.
If if in first frame image, the eyes that the eyes magnitude numerical value of first is 70, the eyes magnitude numerical value of second is 80, third are big
Fractional value is 84, then the eyes size degree that can obtain first does not reach eyes size degree in sample facial image, and
Second and third eyes size degree have all reached eyes size degree in sample facial image.Therefore, need to continue from caching sequence
Middle acquisition image, until the eyes size degree of first in the image grabbed reaches eyes size degree in sample facial image
When, stop capturing image from caching sequence.
In practical application, after grabbing frame and finishing, need to handle the picture frame captured, to obtain all persons
Eyes are all bigger images.In some embodiments, by acquired picture frame for more people's images, then to stop obtaining
After taking picture frame, below scheme can also be included:
If acquired number of image frames is multiframe, base image is determined from acquired multiple image frame, it is described
A facial image for meeting above-mentioned preset condition is included at least in base image;
Determine not meet the facial image to be replaced of preset condition from base image;
In other pending images outside base image, the target facial image for meeting preset condition, target are determined
Facial image and the facial image that facial image to be replaced is identical personage;
In base image, facial image to be replaced is replaced with into target facial image, obtains handling by image replacement
Base image;
Image noise reduction processing is carried out to the base image that processing is replaced by image and is exported.
Specifically, a facial image for meeting above-mentioned preset condition namely institute are included at least in the base image really
The eyes of at least one personage are larger in the base image made.After base image is determined, from base image really
The facial image to be replaced (i.e. the smaller facial image to be replaced of eyes) for not meeting preset condition is made, and surplus from what is captured
The target facial image (i.e. the larger facial image to be replaced of eyes) for meeting preset condition is extracted in remaining picture frame.Then,
Facial image to be replaced is replaced with into target facial image, the larger facial image of eyes in residual image frames is also replaced into base
The smaller facial image of eyes in plinth image, to obtain all larger image of the eyes of all persons.Finally, then to the image
Noise reduction process is carried out, and is output in the photograph album of electronic equipment as photo.
From the foregoing, it will be observed that whether condition is met by eye areas in the determining picture frame obtained in real time in application scheme,
Carry out the quantity that dynamic adjusts the picture frame that need to be obtained, improve the flexibility of picture frame acquisition;Meanwhile it can subtract to a certain extent
Frame time is grabbed less, improves image taking speed.
Referring to Fig. 4, Fig. 4 is the structure diagram of image processing apparatus provided by the embodiments of the present application.Image procossing fills
Putting 300 can include:Receiving module 31, respond module 32, judgment module 33, control module 304.Wherein:
Receiving module 31, for receiving image acquisition instruction;
Respond module 32, in response to described image acquisition instruction, being obtained from caching sequence according to caching sequencing
Cached picture frame is taken, wherein, an identifiable face is included at least in picture frame;
Judgment module 33, it is default whether the eye areas for judging all persons in acquired current image frame meets
Condition;
Control module 34, for the respond module 32 when the judgment module 33 is judged to being, to be controlled to stop obtaining
Picture frame;
Respond module 32 is additionally operable to when the judgment module 33 is determined as no, continues to obtain picture frame, until acquired
Picture frame in, each personage is corresponding with the picture frame that an at least frame eye areas meets preset condition.
In one embodiment, judgment module 33 can be further used for:
Facial image is extracted from acquired current image frame;
Target sample facial image is matched from presetting database according to the facial image;
It is compared by the facial image, with the target sample facial image, obtains comparison result;
According to the comparison result, judge whether the eye areas of all persons in the current image frame meets preset condition.
In one embodiment, judgment module 33 can be further used for:
The facial image is identified, obtains face recognition result;
According to the face recognition result, obtained and the matched target sample face figure of the facial image from presetting database
Picture.
In one embodiment, which includes:Multiple sample face image sets;The sample face figure
Image set conjunction includes:The sample facial image of multiple and different expressions of same face.Judgment module 33 can be further used for:
According to face recognition result, determined from presetting database and the matched target sample face figure of the facial image
Image set closes;
Identify the expression of the facial image;
Target sample facial image is chosen from the target sample face image set according to the expression.
In one embodiment, judgment module 33 can be further used for:
The facial image is aligned with the target sample facial image;
Calculate in the facial image after alignment eyes in the first opening degree of eye areas and target sample facial image
Second opening degree in region;
Compare the first opening degree and the second opening degree, to determine that the first opening degree is less than the second opening degree, obtain comparing knot
Fruit.
In one embodiment, judgment module 33 can be further used for:
If comparison result includes the first opening degree and is less than the second opening degree, the eye of all persons in current image frame is judged
Eyeball region is unsatisfactory for preset condition;
If comparison result does not include the first opening degree and is less than the second opening degree, all persons in current image frame are judged
Eye areas meets preset condition.
In one embodiment, with reference to figure 5, image processing apparatus 300 can also include:
Statistical module 35, for counting the frame number of accessed picture frame;
Determining module 36, for determining whether the frame number reaches predetermined threshold value;
Control module 34 is further used for when determining module is determined as, and the stopping of control response module 32 continues to obtain
Picture frame.
In one embodiment, acquired picture frame is more people's images;With reference to figure 6, image processing apparatus 300 may be used also
To include:Processing module 37.Wherein, processing module 37 can be used for:
After stopping obtaining picture frame, if acquired number of image frames is multiframe, from acquired multiple image frame
In determine base image, in the base image include at least a facial image for meeting the preset condition;
Determine not meet the facial image to be replaced of the preset condition from the base image;
In other pending images outside the base image, the target facial image for meeting the preset condition is determined,
The target facial image and the facial image that the facial image to be replaced is identical personage;
In the base image, which is replaced with into the target image, is obtained by image replacement
The base image of reason;
The base image progress image noise reduction processing of processing is replaced by image to this and is exported.
Image processing apparatus provided in the embodiment of the present application is instructed by receiving image acquisition;It is obtained in response to image
Instruction fetch obtains cached picture frame according to caching sequencing from caching sequence, wherein, one is included at least in picture frame
A identifiable face;Judge whether the eye areas of all persons in acquired current image frame meets preset condition;If
It is then to stop obtaining picture frame;If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding
There is the picture frame that an at least frame eye areas meets preset condition.This programme passes through eyes area in the determining picture frame obtained in real time
Whether domain meets condition, carrys out the quantity that dynamic adjusts the picture frame that need to be obtained, improves the flexibility of picture frame acquisition;Meanwhile
It can reduce to a certain extent and grab frame time, improve image taking speed.
The embodiment of the present application provides a kind of computer-readable storage medium, computer program is stored thereon with, when the meter
When calculation machine program performs on computers so that the computer is performed such as the step in image processing method provided in this embodiment
Suddenly.
The embodiment of the present application also provides a kind of electronic equipment, and including memory, processor, the processor is by calling this to deposit
The computer program stored in reservoir, for performing the step in image processing method provided in this embodiment.
For example, above-mentioned electronic equipment can be the electronic equipments such as tablet computer or smart mobile phone.Referring to Fig. 7,
Fig. 7 is the structure diagram of electronic equipment provided by the embodiments of the present application.
The electronic equipment 400 can include the components such as sensor 401, memory 402, processor 403.People in the art
Member is appreciated that the electronic devices structure shown in Fig. 7 does not form the restriction to electronic equipment, can include more than illustrating
Or less component either combines certain components or different components arrangement.
Sensor 401 can include the biographies such as gyro sensor (such as three-axis gyroscope sensor), acceleration transducer
Sensor.
Memory 402 can be used for storage application program and data.Include and can hold in the application program that memory 402 stores
Line code.Application program can form various functions module.Processor 403 is stored in the application journey of memory 402 by operation
Sequence, so as to perform various functions application and data processing.
Processor 403 is the control centre of electronic equipment, utilizes each of various interfaces and the entire electronic equipment of connection
A part is stored in by running or performing the application program being stored in memory 402 and call in memory 402
Data perform the various functions of electronic equipment and processing data, so as to carry out integral monitoring to electronic equipment.
In the present embodiment, the processor 403 in electronic equipment can be according to following instruction, will be one or more
The corresponding executable code of process of application program is loaded into memory 402, and is stored in storage by processor 403 to run
Application program in device 402, so as to fulfill step:
Receive image acquisition instruction;
It is instructed in response to the image acquisition, cached picture frame is obtained from caching sequence according to caching sequencing,
Wherein, an identifiable face is included at least in picture frame;
Judge whether the eye areas of all persons in acquired current image frame meets preset condition;
If so, stop obtaining picture frame;
If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding with an at least frame eye
Eyeball region meets the picture frame of the preset condition.
As shown in figure 8, image processing circuit includes image-signal processor 540 and control logic device 550.Imaging device
510 image datas captured are handled first by image-signal processor 540, and image-signal processor 540 carries out image data
Analyze the image statistics to capture the one or more control parameters that can be used for determining and/or imaging device 510.Imaging is set
Standby 510 may include the camera with one or more lens 511 and imaging sensor 512.Imaging sensor 512 may include color
Color filter array (such as Bayer filters), imaging sensor 512 can be obtained to be captured with each imaging pixel of imaging sensor 512
Luminous intensity and wavelength information, and provide one group of raw image data being handled by image-signal processor 540.Sensor
520 can be supplied to image-signal processor 540 based on 520 interface type of sensor raw image data.520 interface of sensor
SMIA (Standard Mobile Imaging Architecture, Standard Mobile Imager framework) interface, other can be utilized
The combination of serial or parallel camera interface or above-mentioned interface.
Image-signal processor 540 handles raw image data pixel by pixel in various formats.For example, each image slices
Element can have the bit depth of 8,10,12 or 14 bits, and image-signal processor 540 can carry out one or more to raw image data
The statistical information of a image processing operations, collection about image data.Wherein, image processing operations can be by identical or different position
Depth accuracy carries out.
Image-signal processor 540 can also receive pixel data from video memory 530.For example, from 520 interface of sensor
Raw pixel data is sent to video memory 530, the raw pixel data in video memory 530 is available to image letter
Number processor 540 is for processing.Video memory 530 can be in a part, storage device or electronic equipment for memory device
Independent private memory, and may include DMA (Direct Memory Access, direct direct memory access (DMA)) feature.
When receiving the raw image data from 520 interface of sensor or from video memory 530, picture signal
Processor 540 can carry out one or more image processing operations, such as time-domain filtering.Treated, and image data can be transmitted to image
Memory 530, to carry out other processing before shown.Image-signal processor 540 is received from video memory 530
Data are handled, and the image real time transfer in original domain and in RGB and YCbCr color spaces is carried out to the processing data.Place
Image data after reason may be output to display 570, so that user watches and/or by graphics engine or GPU (Graphics
Processing Unit, graphics processor) it is further processed.In addition, the output of image-signal processor 540 also can be transmitted to
Video memory 530, and display 570 can read image data from video memory 530.In one embodiment, image
Memory 530 can be configured as realizing one or more frame buffers.In addition, the output of image-signal processor 540 can be transmitted
To encoder/decoder 560, so as to encoding/decoding image data.The image data of coding can be saved, and aobvious being shown in
It is decompressed before showing in 570 equipment of device.Encoder/decoder 560 can be realized by CPU or GPU or coprocessor.
The determining statistical data of image-signal processor 540 can be transmitted to control logic device 550.For example, statistical data can
It is passed including the images such as automatic exposure, automatic white balance, automatic focusing, flicker detection, black level compensation, 511 shadow correction of lens
512 statistical information of sensor.Control logic device 550 may include performing the processor of one or more routines (such as firmware) and/or micro-
Controller, one or more routines according to the statistical data of reception, can determine imaging device 510 control parameter and control
Parameter.For example, control parameter may include 520 control parameter of sensor (such as gain, time of integration of spectrum assignment), camera
The combination for the control parameter, 511 control parameter of lens (such as focusing or zoom focal length) or these parameters of glistening.ISP control ginsengs
Number may include the gain level and color correction matrix for automatic white balance and color adjustment (for example, during RGB processing),
And 511 shadow correction parameter of lens.
It is the step of realizing the processing method of image provided in this embodiment with image processing techniques in Fig. 8 below:
Receive image acquisition instruction;
It is instructed in response to the image acquisition, cached picture frame is obtained from caching sequence according to caching sequencing,
Wherein, an identifiable face is included at least in picture frame;
Judge whether the eye areas of all persons in acquired current image frame meets preset condition;
If so, stop obtaining picture frame;
If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding with an at least frame eye
Eyeball region meets the picture frame of the preset condition.
In one embodiment, electronic equipment is in the eyes for performing all persons in the current image frame acquired in judging
When whether region meets the step of preset condition, can specifically it include:
Facial image is extracted from acquired current image frame;
Target sample facial image is matched from presetting database according to the facial image;
It is compared by the facial image, with the target sample facial image, obtains comparison result;
According to the comparison result, judge whether the eye areas of all persons in the current image frame meets preset condition.
In one embodiment, electronic equipment perform matched from presetting database according to the facial image it is corresponding
During the step of sample facial image, can specifically it include:
The facial image is identified, obtains face recognition result;
According to the face recognition result, obtained and the matched target sample face figure of the facial image from presetting database
Picture.
In one embodiment, presetting database includes:Multiple sample face image sets;Sample face image set
Conjunction includes:The sample facial image of multiple and different expressions of same face.Then electronic equipment is being performed according to the recognition of face
As a result, when obtaining the step with the matched target sample facial image of the facial image from presetting database, can specifically wrap
It includes:
According to face recognition result, determined from presetting database and the matched target sample face figure of the facial image
Image set closes;
Identify the expression of the facial image;
Target sample facial image is chosen from the target sample face image set according to the expression.
In one embodiment, electronic equipment is being performed the facial image and target sample facial image progress
Compare, during obtaining the step of comparison result, can specifically include:
The facial image is aligned with the target sample facial image;
Calculate in the facial image after alignment eyes in the first opening degree of eye areas and target sample facial image
Second opening degree in region;
Compare the first opening degree and the second opening degree, to determine that the first opening degree is less than the second opening degree, obtain comparing knot
Fruit.
In one embodiment, electronic equipment is being performed according to the comparison result, judges own in the current image frame
It, specifically can be with when whether the eye areas of personage meets the step of preset condition:
If comparison result includes the first opening degree and is less than the second opening degree, the eye of all persons in current image frame is judged
Eyeball region is unsatisfactory for preset condition;
If comparison result does not include the first opening degree and is less than the second opening degree, all persons in current image frame are judged
Eye areas meets preset condition.
In one embodiment, in the acquired current image frame of judgement the eye areas of all persons be unsatisfactory for it is pre-
If after condition, following steps can also be performed in electronic equipment:
The frame number of picture frame accessed by statistics;
Judge whether the frame number reaches predetermined threshold value;
If so, stop continuing to obtain picture frame.
In one embodiment, acquired picture frame is more people's images;After stopping obtaining picture frame, electronics is set
It is standby that following steps can also be performed:
If acquired number of image frames is multiframe, base image is determined from acquired multiple image frame, the base
A facial image for meeting the preset condition is included at least in plinth image;
Determine not meet the facial image to be replaced of the preset condition from the base image;
In other pending images outside the base image, the target facial image for meeting the preset condition is determined,
The target facial image and the facial image that the facial image to be replaced is identical personage;
In the base image, which is replaced with into the target image, is obtained by image replacement
The base image of reason;
The base image progress image noise reduction processing of processing is replaced by image to this and is exported.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, the detailed description above with respect to image processing method is may refer to, details are not described herein again.
The image processing apparatus provided by the embodiments of the present application belongs to same with the image processing method in foregoing embodiments
Design, can run the either method provided in the image processing method embodiment on the image processing apparatus, specific real
Existing process refers to the image processing method embodiment, and details are not described herein again.
It should be noted that for the embodiment of the present application image processing method, those of ordinary skill in the art can be with
Understand all or part of flow for realizing the embodiment of the present application image processing method, be that can be controlled by computer program
Relevant hardware is completed, which can be stored in a computer read/write memory medium, be such as stored in memory
In, and performed by least one processor, it may include the flow of the embodiment such as the image processing method in the process of implementation.Its
In, the storage medium being somebody's turn to do can be magnetic disc, CD, read-only memory (ROM, Read Only Memory), random access memory
(RAM, Random Access Memory) etc..
For the image processing apparatus of the embodiment of the present application, each function module can be integrated in a processing chip
In or modules be individually physically present, can also two or more modules be integrated in a module.It is above-mentioned
The form that hardware had both may be used in integrated module is realized, can also be realized in the form of software function module.It is described integrated
If module realized in the form of software function module and be independent product sale or in use, one can also be stored in
In a computer read/write memory medium, which is for example read-only memory, disk or CD etc..
A kind of image processing method, device, storage medium and the electronic equipment provided above the embodiment of the present application
Be described in detail, specific case used herein is expounded the principle of the present invention and embodiment, more than it is real
The explanation for applying example is merely used to help understand the method and its core concept of the present invention;Meanwhile for those skilled in the art,
Thought according to the present invention, there will be changes in specific embodiments and applications, in conclusion in this specification
Appearance should not be construed as limiting the invention.
Claims (11)
1. a kind of image processing method, applied to electronic equipment, which is characterized in that including:
Receive image acquisition instruction;
In response to described image acquisition instruction, cached picture frame is obtained from caching sequence according to caching sequencing,
In, an identifiable face is included at least in picture frame;
Judge whether the eye areas of all persons in acquired current image frame meets preset condition;
If so, stop obtaining picture frame;
If it is not, then continue to obtain picture frame, until in acquired picture frame, each personage is corresponding with an at least frame eyes area
Domain meets the picture frame of the preset condition.
2. image processing method according to claim 1, which is characterized in that in the current image frame acquired in the judgement
Whether the eye areas of all persons meets preset condition, including:
Facial image is extracted from acquired current image frame;
Target sample facial image is matched from presetting database according to the facial image;
It is compared by the facial image, with the target sample facial image, obtains comparison result;
According to the comparison result, judge whether the eye areas of all persons in the current image frame meets preset condition.
3. image processing method according to claim 2, which is characterized in that it is described according to the facial image from present count
According to matching corresponding sample facial image in library, including:
The facial image is identified, obtains face recognition result;
According to the face recognition result, obtained and the matched target sample face figure of the facial image from presetting database
Picture.
4. image processing method according to claim 3, which is characterized in that the presetting database includes:Multiple samples
This face image set;The sample face image set includes:The sample face figure of multiple and different expressions of same face
Picture;
It is described according to the face recognition result, obtained and the matched target sample people of the facial image from presetting database
Face image, including:
According to face recognition result, determined from presetting database and the matched target sample facial image of the facial image
Set;
Identify the expression of the facial image;
Target sample facial image is chosen from the target sample face image set according to the expression.
5. image processing method according to claim 2, which is characterized in that described by the facial image and the mesh
This facial image of standard specimen is compared, to obtain comparison result, including:
The facial image is aligned with the target sample facial image;
Calculate in the facial image after alignment eye areas in the first opening degree of eye areas and target sample facial image
The second opening degree;
Compare the first opening degree and the second opening degree, to determine that the first opening degree is less than the second opening degree, obtain comparison result.
6. image processing method according to claim 5, which is characterized in that it is described according to the comparison result, judge institute
Whether the eye areas for stating all persons in current image frame meets preset condition, including:
If comparison result includes the first opening degree and is less than the second opening degree, the eyes area of all persons in current image frame is judged
Domain is unsatisfactory for preset condition;
If comparison result does not include the first opening degree and is less than the second opening degree, the eyes of all persons in current image frame are judged
Region meets preset condition.
7. image processing method according to claim 1, which is characterized in that the institute in the acquired current image frame of judgement
The eye areas for having personage is unsatisfactory for after preset condition, is further included:
The frame number of picture frame accessed by statistics;
Judge whether the frame number reaches predetermined threshold value;
If so, stop continuing to obtain picture frame.
8. according to claim 1-7 any one of them image processing methods, which is characterized in that acquired picture frame is more people
Image;After stopping obtaining picture frame, further include:
If acquired number of image frames is multiframe, base image, the basis are determined from acquired multiple image frame
A facial image for meeting the preset condition is included at least in image;
Determine not meet the facial image to be replaced of the preset condition from the base image;
In other pending images outside the base image, the target facial image for meeting the preset condition is determined,
The target facial image and the facial image that the facial image to be replaced is identical personage;
In the base image, the facial image to be replaced is replaced with into the target facial image, is obtained by image
Replace the base image of processing;
Image noise reduction processing is carried out to the base image by image replacement processing and is exported.
9. a kind of image processing apparatus, applied to electronic equipment, which is characterized in that including:
Receiving module, for receiving image acquisition instruction;
Respond module, in response to described image acquisition instruction, obtaining and delaying from caching sequence according to caching sequencing
The picture frame deposited, wherein, an identifiable face is included at least in picture frame;
Whether judgment module, the eye areas for judging all persons in acquired current image frame meet preset condition;
Control module, for the respond module when the judgment module is judged to being, to be controlled to stop obtaining picture frame;
The respond module, for when the judgment module is determined as no, continuing to obtain picture frame, until acquired image
In frame, each personage is corresponding with the picture frame that an at least frame eye areas meets preset condition.
10. a kind of storage medium, is stored thereon with computer program, which is characterized in that when the computer program is in computer
During upper execution so that the computer performs the method as described in any one of claim 1-8.
11. a kind of electronic equipment, including memory, processor, which is characterized in that the processor is by calling the memory
The computer program of middle storage, for performing the method as described in any one of claim 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810277051.7A CN108259769B (en) | 2018-03-30 | 2018-03-30 | Image processing method, image processing device, storage medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810277051.7A CN108259769B (en) | 2018-03-30 | 2018-03-30 | Image processing method, image processing device, storage medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108259769A true CN108259769A (en) | 2018-07-06 |
CN108259769B CN108259769B (en) | 2020-08-14 |
Family
ID=62747688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810277051.7A Active CN108259769B (en) | 2018-03-30 | 2018-03-30 | Image processing method, image processing device, storage medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108259769B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109543581A (en) * | 2018-11-15 | 2019-03-29 | 北京旷视科技有限公司 | Image processing method, image processing apparatus and non-volatile memory medium |
CN109949213A (en) * | 2019-03-15 | 2019-06-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating image |
CN112419447A (en) * | 2020-11-17 | 2021-02-26 | 北京达佳互联信息技术有限公司 | Method and device for generating dynamic graph, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130010084A1 (en) * | 2010-04-19 | 2013-01-10 | Panasonic Corporation | Three-dimensional imaging device and three-dmensional imaging method |
CN103049085A (en) * | 2012-12-19 | 2013-04-17 | 苏州贝腾特电子科技有限公司 | Method for double clicking virtual mouse |
CN105072327A (en) * | 2015-07-15 | 2015-11-18 | 广东欧珀移动通信有限公司 | Eye-closing-preventing person photographing method and device thereof |
CN106204435A (en) * | 2016-06-27 | 2016-12-07 | 北京小米移动软件有限公司 | Image processing method and device |
-
2018
- 2018-03-30 CN CN201810277051.7A patent/CN108259769B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130010084A1 (en) * | 2010-04-19 | 2013-01-10 | Panasonic Corporation | Three-dimensional imaging device and three-dmensional imaging method |
CN103049085A (en) * | 2012-12-19 | 2013-04-17 | 苏州贝腾特电子科技有限公司 | Method for double clicking virtual mouse |
CN105072327A (en) * | 2015-07-15 | 2015-11-18 | 广东欧珀移动通信有限公司 | Eye-closing-preventing person photographing method and device thereof |
CN106204435A (en) * | 2016-06-27 | 2016-12-07 | 北京小米移动软件有限公司 | Image processing method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109543581A (en) * | 2018-11-15 | 2019-03-29 | 北京旷视科技有限公司 | Image processing method, image processing apparatus and non-volatile memory medium |
CN109949213A (en) * | 2019-03-15 | 2019-06-28 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating image |
CN109949213B (en) * | 2019-03-15 | 2023-06-16 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating image |
CN112419447A (en) * | 2020-11-17 | 2021-02-26 | 北京达佳互联信息技术有限公司 | Method and device for generating dynamic graph, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN108259769B (en) | 2020-08-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103353933B (en) | Image recognition apparatus and control method thereof | |
US8861806B2 (en) | Real-time face tracking with reference images | |
CN107833197A (en) | Method, apparatus, computer-readable recording medium and the electronic equipment of image procossing | |
CN109005366A (en) | Camera module night scene image pickup processing method, device, electronic equipment and storage medium | |
CN108419012A (en) | Photographic method, device, storage medium and electronic equipment | |
CN106161980A (en) | Photographic method and system based on dual camera | |
CN108229369A (en) | Image capturing method, device, storage medium and electronic equipment | |
KR101185243B1 (en) | Apparatus and method for registering a plurlity of face image for face recognition | |
CN103685940A (en) | Method for recognizing shot photos by facial expressions | |
CN107743200A (en) | Method, apparatus, computer-readable recording medium and the electronic equipment taken pictures | |
CN109565551A (en) | It is aligned in reference frame composograph | |
CN112771612B (en) | Method and device for shooting image | |
CN108717530A (en) | Image processing method, device, computer readable storage medium and electronic equipment | |
CN108259769A (en) | Image processing method, device, storage medium and electronic equipment | |
WO2014084249A1 (en) | Facial recognition device, recognition method and program therefor, and information device | |
CN108520493A (en) | Processing method, device, storage medium and the electronic equipment that image is replaced | |
CN108737728A (en) | A kind of image capturing method, terminal and computer storage media | |
CN107172354A (en) | Method for processing video frequency, device, electronic equipment and storage medium | |
CN108401110A (en) | Acquisition methods, device, storage medium and the electronic equipment of image | |
CN109151325A (en) | A kind of processing method and processing unit synthesizing smiling face | |
CN108574803A (en) | Choosing method, device, storage medium and the electronic equipment of image | |
JP2010511340A (en) | Artifact removal for images taken with flash | |
CN108282616B (en) | Processing method, device, storage medium and the electronic equipment of image | |
CN108462831B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product |
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 | ||
CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |