CN105405094A - Method for processing face in instant video and electronic device - Google Patents
Method for processing face in instant video and electronic device Download PDFInfo
- Publication number
- CN105405094A CN105405094A CN201510837468.0A CN201510837468A CN105405094A CN 105405094 A CN105405094 A CN 105405094A CN 201510837468 A CN201510837468 A CN 201510837468A CN 105405094 A CN105405094 A CN 105405094A
- Authority
- CN
- China
- Prior art keywords
- face
- ratio
- instant video
- user
- video frame
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000012545 processing Methods 0.000 title abstract description 7
- 238000003672 processing method Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 abstract description 48
- 230000000694 effects Effects 0.000 abstract description 18
- 210000000887 face Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 5
- 210000003128 head Anatomy 0.000 description 5
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002087 whitening effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G06T3/04—
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/14—Systems for two-way working
Abstract
The present invention discloses a method for processing a face in an instant video and an electronic device, and belongs to the field of image processing. The method comprises: acquiring a scale of a reference face; and adjusting the face in a current instant video frame according to the scale of the reference face. According to the method for processing the face in the instant video and the electronic device, which are provided by the present invention, by adjusting the face in the current instant video according to the scale of the reference face, the scale of the face in the current instant video is changed, so that the requirement that a user can adjust the scale of the face in the process of instant video is satisfied, the instant video effect of the user is improved, and the user experience is improved; meanwhile, by adjusting the face scale of the user according to the scale of the reference face, satisfaction of the user to face adjustment can be improved, and the instant video can be performed in the face scale, so that the user is more willing to perform a video call, and thus, the conventional problem that the user is unwilling to perform instant video due to the face scale is avoided, and the user experience is improved.
Description
Technical field
The present invention relates to image processing field, the face processing method particularly in a kind of instant video and electronic equipment.
Background technology
Along with instant video application on mobile terminals universal, make increasing user should be used for realizing and mutual between other people by instant video, but, due to limitation and the reason such as user self face is too fat or ratio is inharmonious of mobile terminal device, user is caused to be unwilling to carry out instant video call, so need to provide the face processing method in a kind of instant video, to the requirement of face's aesthetic property, the wish degree that user carries out instant video call is improved to improve user in instant video.
Prior art is by carrying out whitening process or improving the brightness of face, to improve the aesthetic property of the people face in instant video to the people face in instant video.
But when the method using prior art to provide, can only whitening process be carried out to face or improve face's brightness, and the fat or thin ratio of face in instant video is still constant, user can not adjust face's ratio, thus make in instant video process, still can not meet the requirement of user to the face's aesthetic property in instant video, make user still be unwilling to carry out video calling, Consumer's Experience is poor.
Summary of the invention
Can to the demand that face's ratio adjusts in instant video process in order to meet user, improve the effect that user carries out instant video, improve Consumer's Experience, user is made more to be ready to carry out video calling, embodiments provide the face processing method in a kind of instant video and electronic equipment, described technical scheme is as follows:
First aspect, provides the face processing method in a kind of instant video, and described method comprises:
Obtain the ratio with reference to face;
According to the described ratio with reference to face, adjust the face in current instant video frame.
In conjunction with first aspect, in the implementation that the first is possible, the described ratio obtained with reference to face comprises:
Obtain with reference to face; And
According to described with reference to face, obtain the described ratio with reference to face.
In conjunction with the first possible implementation of first aspect or first aspect, in the implementation that the second is possible, the described ratio with reference to face comprises at least one in the ratio between Aspect Ratio, face ratio and face.
In conjunction with the first possible implementation of first aspect, in the implementation that the third is possible, described acquisition comprises with reference to face:
Obtain multiple unique points of the described face in described current instant video frame;
According to described multiple unique point, the face in the face picture that acquisition is maximum with described human face similarity degree is as described reference face; Or
Face in the face picture that acquisition user selects is as described reference face.
In conjunction with the implementation that the second of first aspect is possible, in the 4th kind of possible implementation, described according to the described ratio with reference to face, the face adjusted in current instant video frame comprises:
According to the described described Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in described current instant video frame; And/or
According to the described described face ratio with reference to face, adjust the face ratio of the face in described current instant video frame; And/or
According to the ratio between the described described face with reference to face, the ratio between the face adjusting the face in described current instant video frame.
In conjunction with first aspect to the 4th kind of implementation that any one is possible of first aspect, in the 5th kind of possible implementation, described method also comprises:
After face in the current instant video frame of described adjustment, follow the tracks of described face.
In conjunction with the 5th kind of possible implementation of first aspect, in the 6th kind of possible implementation, the described face of described tracking comprises:
The point of the Partial Feature in described multiple unique point of described face is used to follow the tracks of described face.
In conjunction with the 5th kind or the 6th kind of possible implementation of first aspect, in the 7th kind of possible implementation, described method also comprises:
If described face tracking is lost, then again obtain the face in instant video.
In conjunction with the 7th kind of possible implementation of first aspect, in the 8th kind of possible implementation, after the described face again obtained in instant video, method also comprises:
Whether the face again obtained described in judgement is identical with the face in instant video before described loss, if identical, then according to the described face that the resize ratio adjustment of the described face before described loss obtains again;
If not identical, then re-execute first aspect to first aspect the 8th kind of possible implementation described in step.
Second aspect, provides a kind of electronic equipment, and described electronic equipment comprises:
Acquisition module, for obtaining the ratio with reference to face;
Adjusting module, for according to the described ratio with reference to face, adjusts the face in current instant video frame.
In conjunction with second aspect, in the implementation that the first is possible, described acquisition module specifically for:
Obtain with reference to face; And
According to described with reference to face, obtain the described ratio with reference to face.
In conjunction with the first possible implementation of second aspect or second aspect, in the implementation that the second is possible, the described ratio with reference to face comprises at least one in the ratio between Aspect Ratio, face ratio and face.
In conjunction with the first possible implementation of second aspect, in the implementation that the third is possible, described acquisition module also specifically for:
Obtain multiple unique points of the described face in described current instant video frame;
According to described multiple unique point, the face in the face picture that acquisition is maximum with described human face similarity degree is as described reference face; Or
Face in the face picture that acquisition user selects is as described reference face.
In conjunction with the implementation that the second of second aspect is possible, in the 4th kind of possible implementation, described adjusting module specifically for:
According to the described described Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in described current instant video frame; And/or
According to the described described face ratio with reference to face, adjust the face ratio of the face in described current instant video frame; And/or
According to the ratio between the described described face with reference to face, the ratio between the face adjusting the face in described current instant video frame.
In conjunction with second aspect to the 4th kind of implementation that any one is possible of second aspect, in the 5th kind of possible implementation,
Described electronic equipment also comprises tracking module, after the face in the current instant video frame of described adjustment, follows the tracks of described face.
In conjunction with the 5th kind of possible implementation of second aspect, in the 6th kind of possible implementation,
The point of the Partial Feature in described multiple unique point of described face is used to follow the tracks of described face.
In conjunction with the 5th kind or the 6th kind of possible implementation of second aspect, in the 7th kind of possible implementation, described acquisition module also specifically for:
If described face tracking is lost, then again obtain the face in instant video.
In conjunction with the 7th kind of possible implementation of second aspect, in the 8th kind of possible implementation,
Described electronic equipment also comprises judge module;
Whether described judge module is identical with the face in instant video before described loss for the face again obtained described in judging, if identical, then triggers the described face that adjusting module obtains again according to the adjustment of the resize ratio of the described face before described loss;
If not identical, then trigger corresponding module perform second aspect to second aspect the 8th kind of possible implementation described in operation.
The third aspect, provide a kind of electronic equipment, the processor that described electronic equipment comprises display screen, camera, transmission/reception module, storer and is connected with described display screen, described camera, described transmission/reception module, described storer, wherein, described storer is for storing batch processing code, and described processor calls program code that described storer stores for performing following operation:
Obtain the ratio with reference to face;
According to the described ratio with reference to face, adjust the face in current instant video frame.
In conjunction with the third aspect, in the implementation that the first is possible, described processor calls program code that described storer stores for performing following operation:
Obtain with reference to face; And
According to described with reference to face, obtain the described ratio with reference to face.
In conjunction with the first possible implementation of the third aspect or the third aspect, in the implementation that the second is possible, the described ratio with reference to face comprises at least one in the ratio between Aspect Ratio, face ratio and face.
In conjunction with the first possible implementation of the third aspect, in the implementation that the third is possible, described processor calls program code that described storer stores for performing following operation:
Obtain multiple unique points of the described face in described current instant video frame;
According to described multiple unique point, the face in the face picture that acquisition is maximum with described human face similarity degree is as described reference face; Or
Face in the face picture that acquisition user selects is as described reference face.
In conjunction with the implementation that the second of the third aspect is possible, described in the 4th kind of possible implementation, processor calls program code that described storer stores for performing following operation:
According to the described described Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in described current instant video frame; And/or
According to the described described face ratio with reference to face, adjust the face ratio of the face in described current instant video frame; And/or
According to the ratio between the described described face with reference to face, the ratio between the face adjusting the face in described current instant video frame.
In conjunction with the third aspect to the 4th kind of implementation that any one is possible of the third aspect, in the 5th kind of possible implementation, described processor calls program code that described storer stores for performing following operation:
After face in the current instant video frame of described adjustment, follow the tracks of described face.
In conjunction with the 5th kind of possible implementation of the third aspect, in the 6th kind of possible implementation, described processor calls program code that described storer stores for performing following operation:
The point of the Partial Feature in described multiple unique point of described face is used to follow the tracks of described face.
In conjunction with the 5th kind or the 6th kind of possible implementation of the third aspect, in the 7th kind of possible implementation, described processor calls program code that described storer stores for performing following operation:
If described face tracking is lost, then again obtain the face in instant video.
In conjunction with the 7th kind of possible implementation of the third aspect, in the 8th kind of possible implementation, described processor calls program code that described storer stores for performing following operation:
Whether the face again obtained described in judgement is identical with the face in instant video before described loss, if identical, then according to the described face that the resize ratio adjustment of the described face before described loss obtains again;
If not identical, then re-execute the third aspect to the third aspect the 8th kind of possible implementation described in operation.
The embodiment of the invention discloses the face processing method in a kind of instant video and electronic equipment.Described method comprises: obtain the ratio with reference to face; According to the ratio with reference to face, adjust the face in current instant video frame.The present invention is by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the face processing method's process flow diagram in a kind of instant video of providing of the embodiment of the present invention;
Fig. 2 is the face processing method's process flow diagram in a kind of instant video of providing of the embodiment of the present invention;
Fig. 3 is the face processing method's process flow diagram in a kind of instant video of providing of the embodiment of the present invention;
Fig. 4 is the face processing method's process flow diagram in a kind of instant video of providing of the embodiment of the present invention;
Fig. 5 is the face processing method's process flow diagram in a kind of instant video of providing of the embodiment of the present invention;
Fig. 6 is the electronic devices structure schematic diagram that the embodiment of the present invention provides;
Fig. 7 is the electronic devices structure schematic diagram that the embodiment of the present invention provides.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Embodiments provide the face processing method in a kind of instant video, the method is applied to the instant video call under instant video interaction scenarios, wherein, this electronic equipment at least comprises video input module and video display module, video input module can comprise camera, video display module can comprise display screen, and at least can run instant video application program in electronic equipment, the video input module of this instant video application program controlling electronic equipment and video display module, user is by this application program adjustment face ratio, and it is mutual to carry out instant video by this face's ratio.
This electronic equipment can be any one in smart mobile phone, panel computer and wearable device, and the embodiment of the present invention is not limited concrete electronic equipment; In addition, in instant video interactive process, the data transmission comprising instant video can be realized by point-to-point mode, and also can be realized by the mode of transit server, the embodiment of the present invention be limited concrete data transfer mode.
Embodiment one
Embodiments provide the face processing method in a kind of instant video, with reference to shown in Fig. 1, the method comprises:
101, the ratio with reference to face is obtained.
Concrete, this process comprises:
Obtain with reference to face; And
According to reference to face, obtain the ratio with reference to face.
Wherein, at least one in comprising between Aspect Ratio, face ratio and face ratio with reference to the ratio of face.
In addition, this process can also comprise:
Obtain the ratio of the reference face stored.
Wherein, obtain reference face can comprise:
Obtain multiple unique points of the face in current instant video frame;
According to multiple unique point, the face in the face picture that acquisition is maximum with human face similarity degree is as reference face; Or
Face in the face picture that acquisition user selects is as reference face.
102, according to the ratio with reference to face, the face in current instant video frame is adjusted.
Concrete, this process comprises:
According to the Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in current instant video frame; And/or
According to the face ratio with reference to face, adjust the face ratio of the face in current instant video frame; And/or
According to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame.
Optionally, the method also comprises:
After face in the current instant video frame of adjustment, track human faces.
Concrete, use the Partial Feature point in multiple unique points of face to follow the tracks of face.
Optionally, the method also comprises:
If face tracking is lost, then again obtain the face in instant video.
Optionally, after again obtaining the face in instant video, the method also comprises:
Judge that whether the face again obtained is identical with the face lost in front instant video, if identical, then according to the face that the resize ratio adjustment of the face before loss obtains again;
If not identical, then re-execute above-mentioned in steps.
Embodiments provide the face processing method in a kind of instant video, by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment two
Embodiments provide the face processing method in a kind of instant video, in embodiments of the present invention, adjust according to the Aspect Ratio of Aspect Ratio to the face in instant video with reference to face, with reference to shown in Fig. 2, the method comprises:
201, obtain with reference to face.
Concrete, this process can comprise:
A, obtain multiple unique points of the face in current instant video frame;
Detect the face in current instant video frame, the multiple unique points that can be used in describing face are obtained according to testing result, these multiple unique points being used for describing face can comprise multiple unique point parameter of face circumference and multiple unique points of human face five-sense-organ, human face five-sense-organ can comprise eyebrow, eyes, nose, face, ear, in addition, these multiple unique points being used for describing face can also comprise other, and the embodiment of the present invention is not limited for the multiple unique points describing face concrete.
Wherein, unique point can be described by the parameter of unique point, and the parameter of unique point can comprise the coordinate of unique point.
Wherein, can pass through SDM (SupervisedDescentMethod, supervised gradient decent method) algorithm and obtain unique point, also can obtain unique point by other means, the embodiment of the present invention is not limited the concrete mode obtaining unique point.
Exemplary, multiple unique points of the face in this current instant video can be 66 unique points for describing this face circumference and/or human face five-sense-organ, wherein each unique point is located by the coordinate of correspondence, multiple unique points of the face in the current instant video of this acquisition can complete when instant video carries out detection face at the beginning, also can be to carry out when user triggers the instruction of adjustment human face ratio completing when detecting face.
B, according to multiple unique point, to obtain with the face in the maximum face picture of human face similarity degree as with reference to face;
Obtain the face picture maximum with this human face similarity degree in the following manner:
Obtain the multiple unique points of often opening the face in face picture in multiple face picture, multiple unique point can be used in describing face circumference and this human face five-sense-organ in this face picture;
Wherein, the quantity of often opening multiple unique points of the face in face picture in the quantity of multiple unique points of the face in the current instant video frame of acquisition and multiple face picture of acquisition is identical;
Multiple unique point of face in the current instant video frame that calculating obtains and the similarity between the multiple unique points of often opening the face in face picture in multiple face picture above-mentioned of acquisition;
Concrete, this similarity can be the cosine similarity between the unique point of each relevant position, in addition, also can calculate similarity by other means, and the embodiment of the present invention is not limited the concrete mode calculating similarity.
According to the similarity result calculated, obtain the face picture that similarity is maximum; And
Using the face in face picture maximum for this similarity as reference face.
Wherein, multiple face picture above-mentioned can be the pictures in multiple beautiful face picture storehouses of collecting in advance, also can be multiple face picture that user is stored in electronic equipment this locality, can also be multiple face picture of other websites of link, can also be multiple face picture obtained by other means, the concrete obtain manner of the embodiment of the present invention to multiple face picture above-mentioned be limited.
Because according to unique point, obtain the face picture maximum with human face similarity degree, make to obtain result more accurate, simultaneously using the face in the maximum face picture of similarity that obtains as with reference to face, more close to the face in instant video, therefore by the human face ratio in this reference face adjustment instant video, reduce the generation of the situation that real face difference is too large in the face after adjustment and instant video, make the face of user in instant video undistorted, and face's ratio can be adjusted to customer satisfaction system ratio, thus further increase the effect of instant video, improve the satisfaction of user, improve Consumer's Experience.
Optionally, when multiple face picture above-mentioned are the pictures in multiple beautiful face picture storehouses of collecting in advance, method also comprises:
Set up with reference to face picture library;
Concrete, set up with reference to face picture library by collecting beautiful face picture.
Optionally, method also comprises:
Obtain and store the characteristic point information often opening face in this reference face picture library; And
Calculate the Aspect Ratio often opening face; And/or
Calculate the face ratio of often opening face; And/or
Calculate the ratio between the face often opening face; And
Store the ratio between Aspect Ratio and/or face ratio and/or face of often opening face.
From this reference face picture library, the process obtained with reference to face can comprise:
A, the unique point of often opening face equal number obtaining in current instant video frame and store in reference face picture library;
B, according to human face characteristic point in this current instant video frame, calculate the similarity with the unique point with reference to multiple faces in face picture library respectively;
Face in the reference face picture that c, acquisition similarity are maximum is as reference face.
By setting up with reference to face picture library, because this picture library can store the face picture of number of different types, therefore facilitating user's face picture that quick obtaining is the most similar in instant video, improve the efficiency of the most similar face picture of acquisition, simultaneously, because the characteristic point information often opening face can be stored in this picture library and/or often open the ratio between the Aspect Ratio of face and/or the face ratio of often opening face and/or the face often opening face, because prestored the related data with reference to face, thus can these data of quick obtaining in instant video, and without the need to calculating again after the most similar face of acquisition, thus reduce the calculated amount of electronics processors in instant video process, improve the work efficiency of processor, decrease and take processor resource and the instant video card that causes pauses the phenomenon such as not smooth because calculate, thus further increase Consumer's Experience, improve the effect of instant video.
Except aforesaid way, obtaining reference face can also be:
Face in the face picture that acquisition user selects is as reference face.
Concrete, face in the face picture that user selects electronic equipment this locality to store is as reference face, also face in the face picture in the website linked can be selected as with reference to face, can also select to carry out face in the face picture revised as with reference to face by repairing figure instrument, this face picture carrying out revising can be user oneself, also can be other, in addition, user can also select face in other face picture as with reference to face, and the embodiment of the present invention is not limited the face picture that user selects.
By obtaining face in face picture that user selects as with reference to face, make user can self-defined reference picture, thus further increase Consumer's Experience, improve user satisfaction.
In addition, can also obtain by other means with reference to face, the embodiment of the present invention is not limited this.
202, according to reference to face, the ratio with reference to face is obtained.
Wherein, the ratio with reference to face comprises Aspect Ratio.
Obtain the Aspect Ratio according to the reference face calculated with reference to face, or obtain the Aspect Ratio of the reference face prestored.
From this reference face picture library, the process obtained with reference to the ratio of face can comprise:
According to the reference face picture that the similarity in the reference face picture library obtained is maximum, the Aspect Ratio of the face in the reference face picture that this similarity that acquisition stores is maximum.
By obtaining the reference face Aspect Ratio prestored, compared to carrying out calculating in instant video process, reduce the calculated amount of electronics processors, improve the work efficiency of processor, decrease and take processor resource and the instant video card that causes pauses the phenomenon such as not smooth because calculate, thus further increase Consumer's Experience, improve the effect of instant video.
203, according to the Aspect Ratio with reference to face, the Aspect Ratio of the face in current instant video frame is adjusted.
Concrete, according to the Aspect Ratio with reference to face, zoom in or out the Aspect Ratio of the face in current instant video frame, this process comprises:
Immediately zoomed in or out depending on the ratio of the face in frame of video current by bilinear interpolation, also can zoom in or out the ratio of face by other means.
Wherein, zooming in or out the Aspect Ratio of the face in current instant video frame can be zoom in or out this instant video frame, also can be according to the human face characteristic point detected, the face area in instant video frame is zoomed in or out, and corresponding zooming in or out is carried out to the head zone beyond face area, can also be that the head zone that this comprises face is zoomed in or out.
By the Aspect Ratio according to reference face, adjust the Aspect Ratio of the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, thus further increase the effect that user carries out instant video, improve Consumer's Experience.
It should be noted that, this step realizes the ratio according to reference to face, and adjust the process of the face in current instant video frame, except aforesaid way, can also realize this process by other means, the embodiment of the present invention is not limited concrete mode.
By the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user because the problem of face's ratio problems and instant video of being unwilling, improve Consumer's Experience.
Embodiments provide the face processing method in a kind of instant video, by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment three
Embodiments provide the face processing method in a kind of instant video, in embodiments of the present invention, according to reference to the ratio between the Aspect Ratio of face and/or face ratio and/or face, ratio between the Aspect Ratio of the face in instant video and/or face ratio and/or face is adjusted, with reference to shown in Fig. 3, the method comprises:
301, obtain with reference to face.
Concrete, this step is identical with the step 201 in embodiment two, is no longer repeated herein.
302, according to reference to face, the ratio with reference to face is obtained.
Wherein, at least one in comprising between Aspect Ratio, face ratio and face ratio with reference to the ratio of face.
Obtain at least one in the ratio between the Aspect Ratio according to reference the face calculated with reference to face, face ratio and face, or at least one in ratio between the Aspect Ratio of the reference face that prestores of acquisition, face ratio and face.
At least one in the ratio between reference face Aspect Ratio, face ratio and face prestored by acquisition, compared to carrying out calculating in instant video process, reduce the calculated amount of electronics processors, improve the work efficiency of processor, decrease and take processor resource and the instant video card that causes pauses the phenomenon such as not smooth because calculate, thus further increase Consumer's Experience, improve the effect of instant video.
303, according to the Aspect Ratio with reference to face, the Aspect Ratio of the face in current instant video frame is adjusted.
Concrete, this step is identical with the step 203 in embodiment two, is no longer repeated herein.
304, according to the face ratio with reference to face, the face ratio of the face in current instant video frame is adjusted.
According to the face ratio with reference to face, the face ratio of the face in current instant video frame is zoomed in or out.
305, according to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame.
According to the ratio between the face with reference to face, the distance between the face of the face in current instant video frame is zoomed in or out;
By according to the face ratio with reference to face and/or adjust the ratio between the face ratio of the face in current instant video frame and/or face with reference to the ratio between human face five-sense-organ, make the adjustment of human face ratio in instant video more accurate, improve the effect of human face ratio adjustment in instant video, thus further increase Consumer's Experience, make user more be ready to carry out instant video call.
It should be noted that, this step 303 to step 305 realizes the ratio according to reference to face, adjusts the process of the face in current instant video frame, except aforesaid way, can also realize this process by other means, the embodiment of the present invention is not limited concrete mode; Wherein, step 303 can perform according to said sequence to step 305, also can perform simultaneously, and the embodiment of the present invention is not limited the order of concrete execution step 303 to step 305.
By the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user because the problem of face's ratio problems and instant video of being unwilling, improve Consumer's Experience.
It should be noted that, also only step 303 and step 304 can be performed in actual applications, also can be only perform step 303 and step 305, also can be can also be only perform step 304 and step 305, can also be only perform step 304 or step 305, the embodiment of the present invention be limited this.
Embodiments provide the face processing method in a kind of instant video, by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment four
Embodiments provide the face processing method in a kind of instant video, in embodiments of the present invention, after adjusting according to the Aspect Ratio of Aspect Ratio to the face in instant video with reference to face, this face is followed the tracks of, with reference to shown in Fig. 4, the method comprises:
401, obtain with reference to face.
Concrete, this step is identical with the step 201 in embodiment two, is no longer repeated herein.
402, according to reference to face, the ratio with reference to face is obtained.
Wherein, the ratio with reference to face comprises Aspect Ratio.
Concrete, this step is identical with the step 202 in embodiment two, is no longer repeated herein.
403, according to the Aspect Ratio with reference to face, the Aspect Ratio of the face in current instant video frame is adjusted.
Concrete, this step is identical with the step 203 in embodiment two, is no longer repeated herein.
It should be noted that, this step realizes the ratio according to reference to face, and adjust the process of the face in current instant video frame, except aforesaid way, can also realize this process by other means, the embodiment of the present invention is not limited concrete mode.
404, track human faces.
Concrete, according to multiple feature point tracking faces of face.
Wherein, unique point comprises unique point coordinate, according to the unique point coordinate for describing face circumference of initial detecting, follows the tracks of this face in instant video.
Preferably, the Partial Feature point in multiple unique points of face is used to follow the tracks of face.
Concrete, when detecting the face in instant video, need to obtain the unique point with reference man's face equal number, after this face being detected, when following the tracks of this face, use than unique point less when detecting, such as use 66 unique points according to when carrying out Face datection with reference to face, during tracking, only use 15 unique points.
Partial Feature point in this step can be the Partial Feature point for describing in multiple unique points of face circumference.
By using the Partial Feature point in multiple unique points of face, face is followed the tracks of, make the algorithm that can adopt lightweight in tracing process, thus reduce the calculated amount of tracking, greatly reduce the calculating of processor, decrease taking processor resource, improve the treatment effeciency of processor, thus further increase Consumer's Experience, improve the efficiency of carrying out instant video.
If 405 face trackings are lost, then again obtain the face in instant video.
In tracing process, if the face tracking in instant video is lost, then again detect the face in instant video, obtain the unique point with equal number during execution step 401.
Wherein, tracking loss comprises user in instant video process and pulls up stakes, there is comparatively big-movement in the head of user, such as head rotates away from camera, close camera or head suddenly, or being moved or rotation etc. of the electronic equipment of user, and detect in instant video and occur other faces, in addition, can also comprise the tracking loss because other situations cause, the embodiment of the present invention is not limited the concrete situation of following the tracks of loss that causes.
406, judge that whether the face again obtained is identical with the face lost in front instant video, if identical, then perform 407; If not identical, then re-execute step 401 to step 406.
Again the multiple unique points of the human face characteristic point obtained with the face lost in front instant video are contrasted, if comparing result is identical, then determines that the face again obtained is identical with the face lost in front instant video, then perform step 407; If comparing result is not identical, then re-execute unique point and the step afterwards of the face obtained in current instant video frame.
Wherein, the identical error comprising the parameter of Feature point correspondence is no more than preset range, otherwise is then not identical, and preset range can be arranged according to practical application.
It should be noted that, performs the step of 401 to 406 when the face before judging the face that again obtains and losing in instant video is not identical, the process of the step performed by after this judgement and judgement is cyclic process.
407, according to the face that the resize ratio adjustment of the face before loss obtains again.
According to the Aspect Ratio of the face that the Aspect Ratio adjustment of the reference face of the face before loss obtains again, concrete adjustment mode is identical with step 403, is no longer repeated herein.
By again obtaining the face in instant video when face tracking is lost, and judge that whether the face again obtained is identical with the face lost in front instant video, according to the face that the resize ratio adjustment of the face before loss obtains again when judging identical, thus without the need to obtaining with reference to face according to the face in the instant video again obtained again, but directly according to the face that the resize ratio adjustment of the face before loss obtains again, thus enter the calculated amount that does not decrease processor, decrease owing to calculating taking processor resource, improve the treatment effeciency of processor, thus further increase Consumer's Experience, improve the efficiency of carrying out instant video.
Embodiments provide the face processing method in a kind of instant video, by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment five
Embodiments provide the face processing method in a kind of instant video, in embodiments of the present invention, according to reference to the ratio between the Aspect Ratio of face and/or face ratio and/or face, after ratio between the Aspect Ratio of the face in instant video and/or face ratio and/or face is adjusted, this face is followed the tracks of, with reference to shown in Fig. 5, the method comprises:
501, obtain with reference to face.
Concrete, this step is identical with the step 201 in embodiment two, is no longer repeated herein.
502, according to reference to face, the ratio with reference to face is obtained.
Wherein, at least one in comprising between Aspect Ratio, face ratio and face ratio with reference to the ratio of face.
Concrete, this step is identical with the step 302 in embodiment three, is no longer repeated herein.
503, according to the Aspect Ratio with reference to face, the Aspect Ratio of the face in current instant video frame is adjusted.
Concrete, this step is identical with the step 203 in embodiment two, is no longer repeated herein.
504, according to the face ratio with reference to face, the face ratio of the face in current instant video frame is adjusted.
Concrete, this step is identical with the step 304 in embodiment three, is no longer repeated herein.
505, according to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame.
Concrete, this step is identical with the step 305 in embodiment three, is no longer repeated herein.
It should be noted that, this step 503 to step 505 realizes the ratio according to reference to face, adjusts the process of the face in current instant video frame, except aforesaid way, can also realize this process by other means, the embodiment of the present invention is not limited concrete mode; Wherein, step 503 can perform according to said sequence to step 505, also can perform simultaneously, and the embodiment of the present invention is not limited the order of concrete execution step 503 to step 505.
It should be noted that, also only step 503 and step 504 can be performed in actual applications, also can be only perform step 503 and step 505, also can be can also be only perform step 504 and step 505, can also be only perform step 504 or step 505, the embodiment of the present invention be limited this.
506, track human faces.
Concrete, according to Facial features tracking face.
Wherein, unique point comprises unique point coordinate, according to the unique point coordinate for describing face circumference and human face five-sense-organ profile of initial detecting, follows the tracks of this face in instant video.
Preferably, the Partial Feature point in multiple unique points of face is used to follow the tracks of face.
Concrete, this step is identical with the step that the Partial Feature point in multiple unique points of the use face in embodiment four step 404 is followed the tracks of face, is no longer repeated herein
In this step, Partial Feature point can be the Partial Feature point in unique point for describing face circumference, also can be the Partial Feature point in the unique point for describing face circumference and human face five-sense-organ profile, can also be the unique point for describing human face five-sense-organ profile; As long as this Partial Feature point can determine the face in this instant video.
If 507 face trackings are lost, then again obtain the face in instant video.
Concrete, this step is identical with the step 405 in embodiment four, is no longer repeated herein.
508, judge that whether the face again obtained is identical with the face lost in front instant video, if identical, then perform 509; If not identical, then re-execute step 501 to step 508.
This concrete step is identical with step 406 in embodiment four, is no longer repeated herein.
It should be noted that, performs the step of 501 to 508 when the face before judging the face that again obtains and losing in instant video is not identical, the process of the step performed by after this judgement and judgement is cyclic process.
509, according to the face that the resize ratio adjustment of the face before loss obtains again.
According to the Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in current instant video frame;
Concrete, this step is identical with the step 203 in embodiment two, is no longer repeated herein; And/or
According to the face ratio with reference to face, adjust the face ratio of the face in current instant video frame;
Concrete, this step is identical with the step 304 in embodiment three, is no longer repeated herein; And/or
According to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame;
Concrete, this step is identical with the step 305 in embodiment three, is no longer repeated herein.
By again obtaining the face in instant video when face tracking is lost, and judge that whether the face again obtained is identical with the face lost in front instant video, according to the face that the resize ratio adjustment of the face before loss obtains again when judging identical, thus without the need to obtaining with reference to face according to the face in the instant video again obtained again, but directly according to the face that the resize ratio adjustment of the face before loss obtains again, thus enter the calculated amount that does not decrease processor, decrease owing to calculating taking processor resource, improve the treatment effeciency of processor, thus further increase Consumer's Experience, improve the efficiency of carrying out instant video.
Embodiments provide the face processing method in a kind of instant video, by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment six
This bright embodiment provides a kind of electronic equipment 6, and with reference to shown in Fig. 6, this electronic equipment 6 comprises:
Acquisition module 61, for obtaining the ratio with reference to face;
Adjusting module 62, for according to the ratio with reference to face, adjusts the face in current instant video frame.
Optionally, acquisition module 61 specifically for:
Obtain with reference to face; And
According to reference to face, obtain the ratio with reference to face.
Optionally, at least one in comprising between Aspect Ratio, face ratio and face ratio with reference to the ratio of face.
Optionally, acquisition module 61 also specifically for:
Obtain multiple unique points of the face in current instant video frame;
According to multiple unique point, the face in the face picture that acquisition is maximum with human face similarity degree is as reference face; Or
Face in the face picture that acquisition user selects is as reference face.
Optionally, adjusting module 62 specifically for:
According to the Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in current instant video frame; And/or
According to the face ratio with reference to face, adjust the face ratio of the face in current instant video frame; And/or
According to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame.
Optionally, electronic equipment also comprises tracking module 63, after the face in the current instant video frame of adjustment, and track human faces.
Optionally, the Partial Feature point in multiple unique points of face is used to follow the tracks of face.
Optionally, acquisition module 61 also specifically for:
If face tracking is lost, then again obtain the face in instant video.
Optionally, electronic equipment also comprises judge module 64;
Whether judge module 64 is identical with the face lost in front instant video for judging the face again obtained, if identical, then triggers the face that adjusting module obtains again according to the resize ratio adjustment of the face before loss;
If not identical, then trigger corresponding module and perform above-mentioned all operations.
Embodiments provide a kind of electronic equipment, this electronic equipment is by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Embodiment seven
Embodiments provide a kind of electronic equipment 7, with reference to shown in Fig. 7, this electronic equipment 7 comprises display screen 71, camera 72, transmission/reception module 73, storer 74 and with display screen 71, camera 72, transmission/reception module 73, the processor 75 that storer 74 connects, wherein, storer 74 is for storing batch processing code, and processor 75 calls program code that storage 74 device stores for performing following operation:
Obtain the ratio with reference to face;
According to the ratio with reference to face, adjust the face in current instant video frame.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
Obtain with reference to face; And
According to reference to face, obtain the ratio with reference to face.
Optionally, at least one in comprising between Aspect Ratio, face ratio and face ratio with reference to the ratio of face.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
Obtain multiple unique points of the face in current instant video frame;
According to multiple unique point, the face in the face picture that acquisition is maximum with human face similarity degree is as reference face; Or
Face in the face picture that acquisition user selects is as reference face.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
According to the Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in current instant video frame; And/or
According to the face ratio with reference to face, adjust the face ratio of the face in current instant video frame; And/or
According to the ratio between the face with reference to face, the ratio between the face adjusting the face in current instant video frame.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
After face in the current instant video frame of adjustment, track human faces.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
The Partial Feature point in multiple unique points of face is used to follow the tracks of face.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
If face tracking is lost, then again obtain the face in instant video.
Optionally, processor 75 calls program code that storage 74 device stores for performing following operation:
Judge that whether the face again obtained is identical with the face lost in front instant video, if identical, then according to the face that the resize ratio adjustment of the face before loss obtains again;
If not identical, then re-execute above-mentioned all operations.
Embodiments provide a kind of electronic equipment, this electronic equipment is by the ratio according to reference face, adjust the face in current instant video, thus the human face ratio changed in current instant video, meeting user can to the demand that face's ratio adjusts in instant video process, improve the effect that user carries out instant video, improve Consumer's Experience, simultaneously, according to face's ratio of the ratio adjustment user oneself with reference to face, the satisfaction that user adjusts face can be improved, and carry out instant video with this face's ratio, user is made more to be ready to carry out video calling, avoid traditional user is unwilling to carry out instant video problem because of face's ratio problems, improve Consumer's Experience.
Above-mentioned all alternatives, can adopt and combine arbitrarily formation optional embodiment of the present invention, this is no longer going to repeat them.
It should be noted that: the electronic equipment that above-described embodiment provides is when performing the face processing method in instant video, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by equipment is divided into different functional modules, to complete all or part of function described above.In addition, the face processing method's embodiment in the electronic equipment that above-described embodiment provides and instant video belongs to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the face processing method in instant video, is characterized in that, described method comprises:
Obtain the ratio with reference to face;
According to the described ratio with reference to face, adjust the face in current instant video frame.
2. method according to claim 1, is characterized in that, the described ratio obtained with reference to face comprises:
Obtain with reference to face; And
According to described with reference to face, obtain the described ratio with reference to face.
3. method according to claim 1 and 2, is characterized in that, the described ratio with reference to face comprises at least one in the ratio between Aspect Ratio, face ratio and face.
4. method according to claim 2, is characterized in that, described acquisition comprises with reference to face:
Obtain multiple unique points of the described face in described current instant video frame;
According to described multiple unique point, the face in the face picture that acquisition is maximum with described human face similarity degree is as described reference face; Or
Face in the face picture that acquisition user selects is as described reference face.
5. method according to claim 3, is characterized in that, described according to the described ratio with reference to face, the face adjusted in current instant video frame comprises:
According to the described described Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in described current instant video frame; And/or
According to the described described face ratio with reference to face, adjust the face ratio of the face in described current instant video frame; And/or
According to the ratio between the described described face with reference to face, the ratio between the face adjusting the face in described current instant video frame.
6. an electronic equipment, is characterized in that, described electronic equipment comprises:
Acquisition module, for obtaining the ratio with reference to face;
Adjusting module, for according to the described ratio with reference to face, adjusts the face in current instant video frame.
7. equipment according to claim 6, is characterized in that, described acquisition module specifically for:
Obtain with reference to face; And
According to described with reference to face, obtain the described ratio with reference to face.
8. the equipment according to claim 6 or 7, is characterized in that, the described ratio with reference to face comprises at least one in the ratio between Aspect Ratio, face ratio and face.
9. equipment according to claim 7, is characterized in that, described acquisition module also specifically for:
Obtain multiple unique points of the described face in described current instant video frame;
According to described multiple unique point, the face in the face picture that acquisition is maximum with described human face similarity degree is as described reference face; Or
Face in the face picture that acquisition user selects is as described reference face.
10. equipment according to claim 8, is characterized in that, described adjusting module specifically for:
According to the described described Aspect Ratio with reference to face, adjust the Aspect Ratio of the face in described current instant video frame; And/or
According to the described described face ratio with reference to face, adjust the face ratio of the face in described current instant video frame; And/or
According to the ratio between the described described face with reference to face, the ratio between the face adjusting the face in described current instant video frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510837468.0A CN105405094A (en) | 2015-11-26 | 2015-11-26 | Method for processing face in instant video and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510837468.0A CN105405094A (en) | 2015-11-26 | 2015-11-26 | Method for processing face in instant video and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105405094A true CN105405094A (en) | 2016-03-16 |
Family
ID=55470562
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510837468.0A Pending CN105405094A (en) | 2015-11-26 | 2015-11-26 | Method for processing face in instant video and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105405094A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924894A (en) * | 2006-09-27 | 2007-03-07 | 北京中星微电子有限公司 | Multiple attitude human face detection and track system and method |
| CN101179665A (en) * | 2007-11-02 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Method and device for transmitting face synthesized video |
| CN101216882A (en) * | 2007-12-28 | 2008-07-09 | 北京中星微电子有限公司 | A method and device for positioning and tracking on corners of the eyes and mouths of human faces |
| CN101231703A (en) * | 2008-02-28 | 2008-07-30 | 上海交通大学 | Method for tracing a plurality of human faces base on correlate vector machine to improve learning |
| CN101964064A (en) * | 2010-07-27 | 2011-02-02 | 上海摩比源软件技术有限公司 | Human face comparison method |
| CN104574299A (en) * | 2014-12-25 | 2015-04-29 | 小米科技有限责任公司 | Face picture processing method and device |
| CN104715447A (en) * | 2015-03-02 | 2015-06-17 | 百度在线网络技术（北京）有限公司 | Image synthesis method and device |
| CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
| US9195881B2 (en) * | 2012-12-28 | 2015-11-24 | Samsung Electronics Co., Ltd. | Image transformation apparatus and method |
-
2015
- 2015-11-26 CN CN201510837468.0A patent/CN105405094A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924894A (en) * | 2006-09-27 | 2007-03-07 | 北京中星微电子有限公司 | Multiple attitude human face detection and track system and method |
| CN101179665A (en) * | 2007-11-02 | 2008-05-14 | 腾讯科技（深圳）有限公司 | Method and device for transmitting face synthesized video |
| CN101216882A (en) * | 2007-12-28 | 2008-07-09 | 北京中星微电子有限公司 | A method and device for positioning and tracking on corners of the eyes and mouths of human faces |
| CN101231703A (en) * | 2008-02-28 | 2008-07-30 | 上海交通大学 | Method for tracing a plurality of human faces base on correlate vector machine to improve learning |
| CN101964064A (en) * | 2010-07-27 | 2011-02-02 | 上海摩比源软件技术有限公司 | Human face comparison method |
| US9195881B2 (en) * | 2012-12-28 | 2015-11-24 | Samsung Electronics Co., Ltd. | Image transformation apparatus and method |
| CN104574299A (en) * | 2014-12-25 | 2015-04-29 | 小米科技有限责任公司 | Face picture processing method and device |
| CN104715447A (en) * | 2015-03-02 | 2015-06-17 | 百度在线网络技术（北京）有限公司 | Image synthesis method and device |
| CN104751408A (en) * | 2015-03-26 | 2015-07-01 | 广东欧珀移动通信有限公司 | Face image adjusting method and device |
Non-Patent Citations (1)
| Title |
|---|
| 时召会: "人脸表情识别综述", 《万方会议数据库》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110136229B (en) | Method and equipment for real-time virtual face changing | |
| WO2019134516A1 (en) | Method and device for generating panoramic image, storage medium, and electronic apparatus | |
| EP3917131A1 (en) | Image deformation control method and device and hardware device | |
| US20220103743A1 (en) | Picture focusing method, apparatus, terminal, and corresponding storage medium | |
| CN104616347A (en) | Expression migration method, electronic equipment and system | |
| CN107451952B (en) | Splicing and fusing method, equipment and system for panoramic video | |
| US11734804B2 (en) | Face image processing method and apparatus, electronic device, and storage medium | |
| CN104853134A (en) | Video communication method and video communication device | |
| CN109472738B (en) | Image illumination correction method and device, electronic equipment and storage medium | |
| CN112017222A (en) | Video panorama stitching and three-dimensional fusion method and device | |
| CN110941332A (en) | Expression driving method and device, electronic equipment and storage medium | |
| CN112527115B (en) | User image generation method, related device and computer program product | |
| CN111553362A (en) | Video processing method, electronic equipment and computer readable storage medium | |
| CN112416206A (en) | Display window adjusting method, device, electronic device and storage medium | |
| CN110149476A (en) | A kind of time-lapse photography method, apparatus, system and terminal device | |
| CN111726526B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN113205011A (en) | Image mask determining method and device, storage medium and electronic equipment | |
| CN107864333A (en) | Image processing method, device, terminal and storage medium | |
| CN112714337A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN110047126B (en) | Method, apparatus, electronic device, and computer-readable storage medium for rendering image | |
| US11810336B2 (en) | Object display method and apparatus, electronic device, and computer readable storage medium | |
| WO2022227996A1 (en) | Image processing method and apparatus, electronic device, and readable storage medium | |
| CN105405094A (en) | Method for processing face in instant video and electronic device | |
| CN114299271A (en) | Three-dimensional modeling method, three-dimensional modeling apparatus, electronic device, and readable storage medium | |
| CN113223128B (en) | Method and apparatus for generating image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160316 |
|
| RJ01 | Rejection of invention patent application after publication |