CN104243818B

CN104243818B - Image processing method, device and equipment

Info

Publication number: CN104243818B
Application number: CN201410437384.3A
Authority: CN
Inventors: 唐明勇; 刘华君; 刘华一君; 肖彦林
Original assignee: Xiaomi Inc
Current assignee: Xiaomi Inc
Priority date: 2014-08-29
Filing date: 2014-08-29
Publication date: 2018-02-23
Anticipated expiration: 2034-08-29
Also published as: CN104243818A

Abstract

The disclosure is directed to a kind of image processing method, device and equipment, belongs to image technique field.Methods described includes：It is determined that it is currently at big group photo screening-mode；Obtain multiframe shooting image of the target to be captured in multiple specified shooting angle；Eye states recognition processing is carried out to the multiframe shooting image, is identified result；According to the recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, the specified image that eyes are in the target to be captured minimum number of closure state is chosen；Image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in opening the composograph of state.Due under group photo screening-mode greatly, automatically the target to be captured that eyes in shooting image can be in closure state is handled, so as to obtain the composograph that each target to be captured is in eyes-open state, therefore image processing operations more intelligence and simplicity, saves manpower and image processing time.

Description

Image processing method, device and equipment

Technical field

This disclosure relates to image technique field, more particularly to a kind of image processing method, device and equipment.

Background technology

The stimulation to be emitted beam when taking pictures due to flash lamp and the natural reaction of human body, the moment people that shutter is pressed Often the situation of blink occurs.For the numerous big group photo of number, this phenomenon is especially prominent.It not only have impact on image It is attractive in appearance, also reduce satisfaction of the user to image.Therefore, a kind of image processing method is needed badly to solve this problem.

Correlation technique can be continuously shot multiple image in the big group photo of shooting.Afterwards, one is chosen manually in multiple image Two field picture is as synthesis primary image.If user A has blinked eyes in synthesis primary image, manually in other remaining frame figures The image that user A opens eyes is chosen as in, and chooses the face area that user A eyes are in state of opening；Afterwards, manually will User A eyes are in the face area for state of opening and synthesis primary image is synthesized.Above-mentioned steps are performed repeatedly, until It is in opening the big group photo of state to proprietary eyes.

During the disclosure is realized, inventor has found that correlation technique at least has problems with：

In image processing process is carried out, due to needing to perform the operation for repairing blink situation repeatedly manually, so operation It is relatively complicated and complicated, it is not intelligent enough.

The content of the invention

To overcome problem present in correlation technique, the disclosure provides a kind of image processing method, device and equipment.

According to the first aspect of the embodiment of the present disclosure, there is provided a kind of image processing method, methods described include：

It is determined that it is currently at big group photo screening-mode；

Obtain multiframe shooting image of the target to be captured in multiple specified shooting angle；

Eye states recognition processing is carried out to the multiframe shooting image, is identified result；

According to the recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, eye is chosen Eyeball is in the specified image of the target to be captured minimum number of closure state；

Image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in opening the conjunction of state Into image.

Alternatively, the determination is currently at big group photo screening-mode, including：

Judge whether the target to be captured quantity in shooting picture is more than first threshold；If treated in the shooting picture Photographic subjects quantity is more than the first threshold, it is determined that is currently at big group photo screening-mode；Or,

In the case where distant view scape is other, judge that the edge of the shooting picture whether there is incomplete target to be captured；If There is incomplete target to be captured in the edge of the shooting picture, it is determined that be currently at big group photo screening-mode.

Judge whether the target to be captured quantity in shooting picture is more than first threshold；

If the target to be captured quantity in the shooting picture is more than the first threshold, the shooting picture is judged It whether there is target to be captured outside the viewfinder range covered；

If target to be captured be present outside the viewfinder range that the shooting picture is covered, it is determined that be currently at big conjunction Shadow screening-mode.

Alternatively, it is described before the multiframe shooting image for obtaining target to be captured in multiple specified shooting angle Method also includes：

Control capture apparatus is rotated, until finding a view the left hand edge line at interface and Far Left in the first shooting picture is waited to clap The distance for taking the photograph target is the first numerical value, records the first position information of the capture apparatus；

The capture apparatus is controlled to be rotated, until in the right hand edge line at the interface of finding a view and the second shooting picture most The distance of the right target to be captured is first numerical value, records the second place information of the capture apparatus；

According to the first position information and the second place information, calculate the capture apparatus horizontally rotates angle Degree；

According to the numerical values recited for horizontally rotating angle, at least one specified level shooting angle is determined.

Alternatively, the multiframe shooting image for obtaining target to be captured in multiple specified shooting angle, including：

After preset number two field picture is continuously shot in present level shooting angle, according at least one specified level Shooting angle, the capture apparatus is controlled to turn to next shooting angle；

The target to be captured edge that should be shot is identified in next shooting angle；

When it is determined that should shoot target to be captured edge after, be continuously shot preset number in next shooting angle Two field picture；

Above-mentioned steps are repeated, until being finished in each specified level shooting angle photographs.

Control capture apparatus is rotated, until finding a view the top edge line at interface and third shot is taken the photograph in picture and topmost waits to clap The distance for taking the photograph target is the first numerical value, records the 3rd positional information of the capture apparatus；

The capture apparatus is controlled to be rotated, until in the lower edge line at the interface of finding a view and the 4th shooting picture most The distance of following target to be captured is first numerical value, records the 4th positional information of the capture apparatus；

According to the 3rd positional information and the 4th positional information, the vertical angle of rotation of the capture apparatus is calculated Degree；

According to the numerical values recited of the vertical rotational angle, at least one specified vertical shooting angle is determined.

After preset number two field picture is continuously shot in current vertical shooting angle, according to described at least one specified vertical Shooting angle, the capture apparatus is controlled to turn to next shooting angle；

Above-mentioned steps are repeated, until specifying vertical shooting angle photographs to finish at each.

Alternatively, described to specify image to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in The composograph of state is opened, including：

In the multiframe shooting image, determine each to specify in shooting angle and whether include each target to be captured Eyes are in opening the image of state；

If each eye for specifying shooting angle to include each target to be captured of a frame is in opening the figure of state Picture, then specify described image corresponding to shooting angle to carry out synthesis processing each, obtain the composograph.

Alternatively, it is described to determine that each specifies in shooting angle whether the eyes comprising each target to be captured are in After the image for opening state, methods described also includes：

If each eye for specifying shooting angle to include each target to be captured of multiframe is in opening the finger of state Determine image, then the most image of the target to be captured number in smile state is chosen in the multiframe specifies image, to every Described image corresponding to one shooting angle carries out synthesis processing, obtains the composograph.

The image for the target to be captured minimum number that selection eyes are in closure state is made in the multiframe specifies image To synthesize primary image；

In the synthesis primary image, Eye states recognition processing is carried out to the synthesis primary image, obtains eyes Specified photographic subjects in closure state；

In the multiframe shooting image in addition to primary image is synthesized, the eyes of the selection specified photographic subjects, which are in, opens The facial zone of open state；

The synthesis primary image and the facial zone are synthesized, obtain the composograph.

Alternatively, it is described in each specifies an at least frame shooting image corresponding to shooting angle, choose eyes and be in After the specified image of the target to be captured minimum number of closure state, methods described also includes：

Specify shooting angle for each, judge be in an at least frame shooting image corresponding to the specified shooting angle The no eyes comprising each target to be captured are in opening the specified image of state；

If the eye of each target to be captured is not included in an at least frame shooting image corresponding to the specified shooting angle Eyeball is in opening the specified image of state, then controls the capture apparatus to re-start shooting, until the specified shooting angle The eyes comprising each target to be captured are in opening the specified image of state in an at least frame shooting image corresponding to degree.

According to the second aspect of the embodiment of the present disclosure, there is provided a kind of image processing apparatus, described device include：

Screening-mode determining module, for determining to be currently at big group photo screening-mode；

Shooting image acquisition module, for obtaining multiframe shooting figure of the target to be captured in multiple specified shooting angle Picture；

Shooting image identification module, for carrying out Eye states recognition processing to the multiframe shooting image, it is identified As a result；

Image is specified to choose module, for according to the recognition result, being specified at each corresponding to shooting angle at least In one frame shooting image, the specified image that eyes are in the target to be captured minimum number of closure state is chosen；

Image synthesizes processing module, for specifying image to carry out synthesis processing multiframe, obtains each target to be captured Eyes are in opening the composograph of state.

Alternatively, the screening-mode determining module, for judging whether the target to be captured quantity in shooting picture is big In first threshold；When the target to be captured quantity in the shooting picture is more than the first threshold, it is determined that being currently at big Group photo screening-mode；Or, in the case where distant view scape is other, judge that the edge of the shooting picture whether there is incomplete mesh to be captured Mark；When the edge of the shooting picture has incomplete target to be captured, it is determined that being currently at big group photo screening-mode.

Alternatively, the screening-mode determining module, for judging whether the target to be captured quantity in shooting picture is big In first threshold；When the target to be captured quantity in the shooting picture is more than the first threshold, the shooting picture is judged It whether there is target to be captured outside the viewfinder range that face is covered；When the external memory for the viewfinder range that the shooting picture is covered In target to be captured, it is determined that being currently at big group photo screening-mode.

Alternatively, described device also includes：

First control module, for controlling capture apparatus to be rotated, until the left hand edge line and first count at interface of finding a view The distance for taking the photograph Far Left target to be captured in picture is the first numerical value, records the first position information of the capture apparatus；

First control module, for controlling the capture apparatus to be rotated, until the right at the interface of finding a view The distance of rightmost target to be captured is first numerical value in edge line and the second shooting picture, records the of the capture apparatus Two positional informations；

First rotational angle computing module, for according to the first position information and the second place information, calculating The capture apparatus horizontally rotates angle；

First shooting angle-determining module, for horizontally rotating the numerical values recited of angle according to, is determined at least one Specified level shooting angle.

Alternatively, the shooting image acquisition module, for being continuously shot preset number in present level shooting angle After two field picture, according at least one specified level shooting angle, the capture apparatus is controlled to turn to next shooting angle Degree；The target to be captured edge that should be shot is identified in next shooting angle；When it is determined that the target to be captured edge that should be shot Afterwards, it is continuously shot preset number two field picture in next shooting angle；Above-mentioned steps are repeated, until at each Specified level shooting angle photographs finish.

Alternatively, described device also includes：

Second control module, for controlling capture apparatus to be rotated, until the top edge line and third shot at interface of finding a view The distance for taking the photograph the top target to be captured in picture is the first numerical value, records the 3rd positional information of the capture apparatus；

Second control module, for controlling the capture apparatus to be rotated, until the following of interface of finding a view The distance of target to be captured is first numerical value bottom in edge line and the 4th shooting picture, records the of the capture apparatus Four positional informations；

Second rotational angle computing module, for according to the 3rd positional information and the 4th positional information, calculating The vertical rotational angle of the capture apparatus；

Second shooting angle-determining module, for the numerical values recited according to the vertical rotational angle, determine at least one Specify vertical shooting angle.

Alternatively, the shooting image acquisition module, for being continuously shot preset number in current vertical shooting angle After two field picture, according at least one specified vertical shooting angle, the capture apparatus is controlled to turn to next shooting angle Degree；The target to be captured edge that should be shot is identified in next shooting angle；When it is determined that the target to be captured edge that should be shot Afterwards, it is continuously shot preset number two field picture in next shooting angle；Above-mentioned steps are repeated, until at each Vertical shooting angle photographs are specified to finish.

Alternatively, described image synthesis processing module, clapped in the multiframe shooting image, determining that each is specified Take the photograph in angle whether the image that the eyes comprising each target to be captured are in opening state；When each to be captured comprising a frame When the eyes of target are in opening the image of state, synthesis processing is carried out to described image corresponding to each shooting angle, Obtain the composograph.

Alternatively, described image synthesis processing module, it is additionally operable to when the eyes comprising each target to be captured of multiframe are located When the specified image for state of opening, the target to be captured number in smile state is chosen most in the multiframe specifies image More images, synthesis processing is carried out to described image corresponding to each shooting angle, obtains the composograph.

Alternatively, described image synthesis processing module, for selecting eyes to be in closure in specifying image in the multiframe The image of the target to be captured minimum number of state is as synthesis primary image；In the synthesis primary image, to the conjunction Eye states recognition processing is carried out into primary image, obtains the specified photographic subjects that eyes are in closure state；Except synthesis base In multiframe shooting image outside this image, the eyes for choosing the specified photographic subjects are in the facial zone for state of opening； The synthesis primary image and the facial zone are synthesized, obtain the composograph.

Alternatively, described device also includes：

Image judge module is specified, for specifying shooting angle for each, judges that the specified shooting angle is corresponding An at least frame shooting image in whether the eyes comprising each target to be captured are in opening the specified image of state；

3rd control module, for each when not included in an at least frame shooting image corresponding to the specified shooting angle When the eyes of target to be captured are in opening the specified image of state, the capture apparatus is controlled to re-start shooting, until The eyes comprising each target to be captured are in opening shape in an at least frame shooting image corresponding to the specified shooting angle The specified image of state.

According to the third aspect of the embodiment of the present disclosure, there is provided a kind of image processing equipment, the equipment include：

Processor；

For storing the memory of processor-executable instruction；

Wherein, the processor is configured as：It is determined that it is currently at big group photo screening-mode；Target to be captured is obtained more Multiframe shooting image in individual specified shooting angle；Eye states recognition processing is carried out to the multiframe shooting image, known Other result；According to the recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, eyes are chosen The specified image of target to be captured minimum number in closure state；Specify image to carry out synthesis processing to multiframe, obtain every The eyes of individual target to be captured are in opening the composograph of state.

The technical scheme provided by this disclosed embodiment can include the following benefits：

After it is determined that being currently at big group photo screening-mode, it is more in multiple specified shooting angle to obtain target to be captured Frame shooting image, and Eye states recognition processing is carried out to the multiframe shooting image, according to obtained recognition result, each In an at least frame shooting image corresponding to individual specified shooting angle, choose eyes and be in the target to be captured quantity of closure state most Few specified image；Afterwards, image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in opening The composograph of open state, due under group photo screening-mode greatly, closure state can be in eyes in shooting image automatically Target to be captured is handled, so as to obtain the composograph that each target to be captured is in eyes-open state, therefore image Processing operation more intelligence and simplicity, save manpower and image processing time.

It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not The disclosure can be limited.

Brief description of the drawings

Accompanying drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the present invention Example, and for explaining principle of the invention together with specification.

Fig. 1 is a kind of flow chart of image processing method according to an exemplary embodiment.

Fig. 2 is a kind of flow chart of image processing method according to an exemplary embodiment.

Fig. 3 is a kind of schematic diagram of shooting image according to an exemplary embodiment.

Fig. 4 is a kind of schematic diagram of shooting image according to an exemplary embodiment.

Fig. 5 a are a kind of schematic diagrames of shooting image according to an exemplary embodiment.

Fig. 5 b are a kind of schematic diagrames of shooting image according to an exemplary embodiment.

Fig. 6 a are a kind of schematic diagrames of shooting image according to an exemplary embodiment.

Fig. 6 b are a kind of schematic diagrames of shooting image according to an exemplary embodiment.

Fig. 6 c are a kind of schematic diagrames of shooting image according to an exemplary embodiment.

Fig. 7 is a kind of schematic diagram of shooting image according to an exemplary embodiment.

Fig. 8 is a kind of schematic diagram of shooting image according to an exemplary embodiment.

Fig. 9 is a kind of schematic diagram of shooting image according to an exemplary embodiment.

Figure 10 is a kind of block diagram of image processing apparatus according to an exemplary embodiment.

Figure 11 is a kind of block diagram of image processing equipment according to an exemplary embodiment.

Embodiment

Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment Described in embodiment do not represent and the consistent all embodiments of the present invention.On the contrary, they be only with it is such as appended The example of the consistent apparatus and method of some aspects being described in detail in claims, of the invention.

Fig. 1 is a kind of flow chart of image processing method according to an exemplary embodiment, as shown in figure 1, the figure As processing method is in image processing equipment, comprising the following steps.

In a step 101, it is determined that being currently at big group photo screening-mode.

In a step 102, multiframe shooting image of the target to be captured in multiple specified shooting angle is obtained.

In step 103, Eye states recognition processing is carried out to multiframe shooting image, is identified result.

At step 104, according to recognition result, an at least frame shooting image corresponding to shooting angle is specified at each In, choose the specified image that eyes are in the target to be captured minimum number of closure state.

In step 105, image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in Open the composograph of state.

The method that the embodiment of the present disclosure provides, after it is determined that being currently at big group photo screening-mode, obtain target to be captured Multiframe shooting image in multiple specified shooting angle, and Eye states recognition processing is carried out to the multiframe shooting image, According to obtained recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choose eyes and be in The specified image of the target to be captured minimum number of closure state；Afterwards, specify image to carry out synthesis processing to multiframe, obtain every The eyes of individual target to be captured are in opening the composograph of state, can be automatically to clapping due to taking a group photo under screening-mode greatly Take the photograph eyes in image and be in the target to be captured of closure state and handled, be in opening so as to obtain each target to be captured The composograph of eye state, therefore image processing operations more intelligence and simplicity, save manpower and image processing time.

Optionally it is determined that big group photo screening-mode is currently at, including：

Judge whether the target to be captured quantity in shooting picture is more than first threshold；It is if to be captured in shooting picture Destination number is more than first threshold, it is determined that is currently at big group photo screening-mode；Or,

In the case where distant view scape is other, judge that the edge of shooting picture whether there is incomplete target to be captured；If shooting There is incomplete target to be captured in the edge of picture, it is determined that be currently at big group photo screening-mode.

If the target to be captured quantity in shooting picture is more than first threshold, judge that what shooting picture covered finds a view It whether there is target to be captured outside scope；

If target to be captured be present outside the viewfinder range that shooting picture is covered, it is determined that be currently at big group photo and clap Take the photograph pattern.

Alternatively, before obtaining multiframe shooting image of the target to be captured in multiple specified shooting angle, this method is also Including：

Control capture apparatus is rotated, until finding a view the left hand edge line at interface and Far Left in the first shooting picture is waited to clap The distance for taking the photograph target is the first numerical value, the first position information of records photographing equipment；

Control capture apparatus is rotated, until finding a view the right hand edge line at interface and rightmost in the second shooting picture is waited to clap The distance for taking the photograph target is the first numerical value, the second place information of records photographing equipment；

According to first position information and second place information, calculate capture apparatus horizontally rotates angle；

Alternatively, multiframe shooting image of the target to be captured in multiple specified shooting angle is obtained, including：

After preset number two field picture is continuously shot in present level shooting angle, shot according at least one specified level Angle, control capture apparatus turn to next shooting angle；

When it is determined that should shoot target to be captured edge after, preset number frame figure is continuously shot in next shooting angle Picture；

Control capture apparatus is rotated, until finding a view the top edge line at interface and third shot is taken the photograph in picture and topmost waits to clap The distance for taking the photograph target is the first numerical value, the 3rd positional information of records photographing equipment；

Control capture apparatus is rotated, until the lower edge line at interface of finding a view in the 4th shooting picture with waiting to clap bottom The distance for taking the photograph target is the first numerical value, the 4th positional information of records photographing equipment；

According to the 3rd positional information and the 4th positional information, the vertical rotational angle of capture apparatus is calculated；

According to the numerical values recited of vertical rotational angle, at least one specified vertical shooting angle is determined.

After preset number two field picture is continuously shot in current vertical shooting angle, vertical shooting is specified according at least one Angle, control capture apparatus turn to next shooting angle；

Alternatively, image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in opening The composograph of state, including：

In multiframe shooting image, determine that each specifies the eyes that each target to be captured whether is included in shooting angle It is in opening the image of state；

Optionally it is determined that each is specified in shooting angle, whether the eyes comprising each target to be captured are in opening After the image of state, this method also includes：

If each eye for specifying shooting angle to include each target to be captured of multiframe is in opening the finger of state Determine image, then the most image of the target to be captured number in smile state is chosen in multiframe specifies image, to each Described image corresponding to shooting angle carries out synthesis processing, obtains the composograph.

Eyes are selected to be in the image of the target to be captured minimum number of closure state as conjunction in multiframe specifies image Into primary image；

In primary image is synthesized, Eye states recognition processing is carried out to synthesis primary image, eyes is obtained and is in closure The specified photographic subjects of state；

In the multiframe shooting image in addition to primary image is synthesized, selection specifies the eyes of photographic subjects to be in and opens shape The facial zone of state；

Synthesis primary image and facial zone are synthesized, obtain composograph.

Alternatively, in each specifies an at least frame shooting image corresponding to shooting angle, eyes is chosen and are in closure After the specified image of the target to be captured minimum number of state, this method also includes：

Shooting angle is specified for each, judges to specify and whether is wrapped in an at least frame shooting image corresponding to shooting angle Eyes containing each target to be captured are in opening the specified image of state；

If specify the eyes for not including each target to be captured in an at least frame shooting image corresponding to shooting angle equal Specified image in state of opening, then capture apparatus is controlled to re-start shooting, until specifying corresponding to shooting angle at least The eyes comprising each target to be captured are in opening the specified image of state in one frame shooting image.

Above-mentioned all optional technical schemes, any combination can be used to form the alternative embodiment of the present invention, herein no longer Repeat one by one.

Fig. 2 is a kind of flow chart of image processing method according to an exemplary embodiment, as shown in Fig. 2 the figure As processing method is in image processing equipment, comprising the following steps.

In step 201, it is determined that being currently at big group photo screening-mode.

Wherein, group photo screening-mode refers to and currently participates in the numerous screening-mode of number of taking pictures greatly.For example student's graduation is closed Shadow is regarded as memory, or the personnel participating in the meeting of convention takes a group photo.

In the disclosed embodiments, when it is determined that being currently at big group photo screening-mode, following three kinds of mode realities can be taken It is existing：

First way, judge whether the target to be captured quantity in shooting picture is more than first threshold；If shoot picture Target to be captured quantity in face is more than first threshold, it is determined that is currently at big group photo screening-mode.

Wherein, the big I of first threshold is 50 people or 100 people etc., and the embodiment of the present disclosure is not especially limited to this, Optionally the size of first threshold can be set.Target to be captured generally all refers to people.

For first way, determine that (view finder can currently photograph shooting picture using face recognition technology Picture) in number.Such as the facial image in collection shooting picture, and counted.When collection facial image finishes Afterwards, count value now is just the number in shooting picture.Referring to Fig. 3, so that first threshold is 50 people as an example, due to shooting picture In number be significantly greater than 50 people, it is thus determined that being currently at big group photo screening-mode.

The second way, in the case where distant view scape is other, judge that the edge of shooting picture whether there is incomplete mesh to be captured Mark；If there is incomplete target to be captured in the edge of shooting picture, it is determined that be currently at big group photo screening-mode.

Wherein, scape does not refer to because capture apparatus is different from the distance of target to be captured, and causes target to be captured clapping Take the photograph the difference of the range size showed in picture.The other division of scape generally can be divided into five kinds, by closely to remote respectively feature (more than shoulders of human body), close shot (more than human chest), middle scape (more than human knee), panorama (whole and the surrounding back of the body of human body Scape), distant view (target to be captured local environment).Why it is determined herein in the case where distant view scape is other, is because only that distant view scape Special talent can photograph more target to be captured and its local environment, convenient to carry out follow-up judgement.

In the disclosed embodiments, the edge of shooting picture, namely refer to the picture that view finder can photograph Edge.Referring to Fig. 4, incomplete target to be captured, refer to and half of face or half of body in shooting picture only be present and wait to clap Take the photograph target.When the edge that shooting picture is determined by face recognition technology has half of face or half of body, it is determined that current In big group photo screening-mode.

The third mode, judge whether the target to be captured quantity in shooting picture is more than first threshold；If shoot picture Target to be captured quantity in face is more than first threshold, then judges to whether there is outside the viewfinder range that shooting picture is covered and treat Photographic subjects；If target to be captured be present outside the viewfinder range that shooting picture is covered, it is determined that be currently at big group photo Screening-mode.

For the third mode, in order to accurately determine whether, in big group photo screening-mode, to take the judgement of two steps Mode.The first step, first judges whether the number in shooting picture is more than first threshold；Number in picture to be captured is more than the In the case of one threshold value, then judge whether the people not photographed also be present outside the viewfinder range that shooting picture is covered.Referring to Fig. 5 a, the people not photographed is also included outside the viewfinder range that shooting picture is covered.But due to shooting picture edge this When do not include half of face or half of body, therefore, also need the shooting angle of auto-changing capture apparatus.As shown in Figure 5 b, The people not photographed before just being contained after capture apparatus is rotated, in shooting picture now.Face is changed by shooting to be covered Viewfinder range outside target to be captured also be present, it is thus determined that being currently at big group photo screening-mode.

It should be noted that in addition to taking above-mentioned three kinds of modes and determining whether in big group photo screening-mode, also Other determination modes can be taken, the embodiment of the present disclosure is not especially limited to this.

In step 202, multiframe shooting image of the target to be captured in multiple specified shooting angle is obtained.

In the disclosed embodiments, obtain multiframe shooting image of the target to be captured in multiple specified shooting angle it Before, further comprising the steps of 202a to step 202d.

Step 202a, control capture apparatus is rotated, until in the left hand edge line and the first shooting picture at interface of finding a view The distance of Far Left target to be captured is the first numerical value, the first position information of records photographing equipment.

Wherein, the big I of the first numerical value is 1mm or 2mm etc., and the embodiment of the present disclosure is not made to the size of the first numerical value It is specific to limit.Can be the D coordinates value of capture apparatus, or the angle of rotation of the front position relative to rotation in the information of first position Degree etc., the embodiment of the present disclosure is not especially limited to the form of first position information.

In the disclosed embodiments, the purpose for performing step 202a is to determine under group photo screening-mode greatly, will locate When the leftmost people of horizontal direction is included within the viewfinder range that is covered of shooting picture, capture apparatus to rotate how much Degree.When controlling capture apparatus to be rotated, the interface of finding a view in view finder can constantly convert with the rotation of capture apparatus, Obtained shooting picture is different also with the rotation of capture apparatus.When occurring leftmost people in interface of finding a view, and its face Region is not complete incomplete, then the right hand edge line of leftmost people is in the shooting picture of left hand edge linear distance first at interface of finding a view During the first numerical value, control capture apparatus stops operating, and records the first position information of now capture apparatus.Now, first count Take the photograph in picture and the full facial region of Far Left target to be captured at least occur.

Step 202b, control capture apparatus is rotated, until in the right hand edge line and the second shooting picture at interface of finding a view The distance of rightmost target to be captured is the first numerical value, the second place information of records photographing equipment.

In the disclosed embodiments, the purpose for performing step 202a is to determine under group photo screening-mode greatly, will locate When the people of horizontal direction rightmost is included within the viewfinder range that is covered of shooting picture, capture apparatus to rotate how much Degree.When controlling capture apparatus to be rotated, the interface of finding a view in view finder can constantly convert with the rotation of capture apparatus, Obtained shooting picture is different also with the rotation of capture apparatus.When occurring the people of rightmost in interface of finding a view, and its face Region is not complete incomplete, then the right hand edge line of the people of rightmost is in the shooting picture of right hand edge linear distance first at interface of finding a view During the first numerical value, control capture apparatus stops operating, and records the first position information of now capture apparatus.Now, first count Take the photograph in picture and the full facial region of rightmost target to be captured at least occur.

Step 202c, according to first position information and second place information, calculate capture apparatus horizontally rotates angle.

In the disclosed embodiments, after first position information and second place information is obtained, according to the numerical value of the two, It can calculate to the whole target to be captured for currently participating in taking pictures are all contained in last composograph, then capture apparatus How many degree at least horizontal are rotated from left to right or from right to left.(do not rotated using first position information as relative to initial position Position before) rotate 30 degree, second place information is the then level of capture apparatus relative to exemplified by 30 degree of initial position rotation Rotational angle will reach 60 degree.

Step 202d, according to the numerical values recited for horizontally rotating angle, at least one specified level shooting angle is determined.

In the disclosed embodiments, may be excessive due to the number for currently participating in taking pictures after obtaining horizontally rotating angle, Angle is excessive so as to causing to horizontally rotate, therefore also needs, according to the size for horizontally rotating angle, to horizontally rotate angle and divided Cut, obtain at least one specified level shooting angle.When splitting to horizontally rotating angle, when horizontally rotating angular values When excessive, it can will horizontally rotate angle and carry out compared with repeated segmentation, for example be divided into 5 times or more, and obtain at least five specified level Shooting angle；When horizontally rotate angular values it is smaller when, can will horizontally rotate angle and carry out less time segmentation, for example be divided into 3 It is secondary or less, obtain at most 3 specified level shooting angle.

Wherein, after at least one specified level shooting angle is determined, target to be captured is being obtained in multiple specified bats When taking the photograph the multiframe shooting image in angle, following manner can be taken to realize：

The first step, after being continuously shot preset number two field picture in present level shooting angle, specified according at least one Horizontal shooting angle, control capture apparatus turn to next shooting angle.

Wherein, preset number can be 3 or 4 etc., and the embodiment of the present disclosure is not especially limited to the size of preset number. When being shot at least one specified level shooting angle, can be shot according to order from left to right, can also according to from The order of right-to-left is shot, and the embodiment of the present disclosure is not especially limited to this.In the shooting angle a specified photographs After preset number two field picture, control capture apparatus turns to next shooting angle, carries out preset number two field picture again Shooting.

Referring to Fig. 6 a, so that order from left to right is shot as an example, then when present level shooting angle is shot, Dotted line can only be shot with the part target to be captured in left region, dotted line can not be by present level shooting angle with right region Photograph.Therefore, capture apparatus need to be controlled turn to next shooting angle shown in Fig. 6 b, with dotted line in shooting figure 6a With the target to be captured in right region.

Second step, the target to be captured edge that should be shot is identified in next shooting angle.

In the disclosed embodiments, before being shot in a shooting angle specified, also need first to identify and currently should The target to be captured edge of shooting.Why this is done because need to ensure participate in take pictures everyone be both present in shooting picture In, and the shooting picture of different shooting angles does not overlap on a large scale.Referring to Fig. 6 b, when capture apparatus turns to next bat After taking the photograph angle, the target to be captured edge that be able to should currently be shot according to the image automatic identification obtained in a upper shooting angle, Also dotted line is defined as target to be captured edge.So in next shooting angle, just as shown in Figure 6 b from dotted line with the right side Region starts to shoot.

3rd step, when it is determined that should shoot target to be captured edge after, be continuously shot in next shooting angle default Number two field picture.

In the disclosed embodiments, can be since edge it is determined that behind the target to be captured edge that should currently shoot It is continuously shot, obtains preset number two field picture again.

Referring to Fig. 6 c, the image of top is the panoramic picture for the target to be captured that participation is taken pictures.Lower left image is in Fig. 6 a The shooting image obtained in shown specified shooting angle, lower right image are what is obtained in the specified shooting angle shown in Fig. 6 b Shooting image.From Fig. 6 c, the image border of the two overlaps well, after the two is carried out into synthesis processing, obtained conjunction It is almost consistent into image and the image of top.Any one target to be captured is not missed, does not occur overlapping to be captured yet Target.

4th step, above-mentioned steps are repeated, until being finished in each specified level shooting angle photographs.

After the above-mentioned first step to the 3rd step is repeated, it can obtain default in the shooting angle specified at each Number two field picture.That is, each shooting angle specified corresponds to preset number two field picture.

It should be noted that in addition to being divided into multiple shooting angle in the horizontal direction and carrying out repeatedly shooting, referring to Fig. 7, It there is likely to be because the number for currently participating in taking pictures is numerous, it is multiple rows of so as to divide into erect-position.And capture apparatus is being carried out During shooting, the shooting ability of capture apparatus is limited to, it is impossible to which the people of each row is covered into the situation in interface of finding a view.Cause This, the embodiment of the present disclosure is additionally included in the step of vertical direction is repeatedly shot.Step 202e as described below to step 202h.

Step 202e, control capture apparatus is rotated, until finding a view the top edge line at interface and third shot is taken the photograph in picture The distance of the top target to be captured is the first numerical value, the 3rd positional information of records photographing equipment.

With step 202a similarly, here is omitted for the step.

Step 202f, control capture apparatus is rotated, until in the lower edge line and the 4th shooting picture at interface of finding a view The distance of target to be captured is the first numerical value bottom, the 4th positional information of records photographing equipment.

With step 202b similarly, here is omitted for the step.

Step 202g, according to the 3rd positional information and the 4th positional information, the vertical rotational angle of capture apparatus is calculated.

With step 202c similarly, here is omitted for the step.

Step 202h, according to the numerical values recited of vertical rotational angle, at least one specified vertical shooting angle is determined.

With step 202d similarly, here is omitted for the step.

Wherein, after at least one specified vertical shooting angle is determined, target to be captured is being obtained in multiple specified bats When taking the photograph the multiframe shooting image in angle, following manner can be taken to realize：

The first step, after being continuously shot preset number two field picture in current vertical shooting angle, specified according at least one Vertical shooting angle, control capture apparatus turn to next shooting angle.

The process is identical with the above-mentioned principle shot in specified level shooting angle, and here is omitted.

4th step, above-mentioned steps are repeated, until specifying vertical shooting angle photographs to finish at each.

It should be noted that specifying shooting angle to may refer to specified level shooting angle, can also refer to specify vertical clap Angle is taken the photograph, may also refer to horizontal shooting angle and vertical shooting angle, the embodiment of the present disclosure is not especially limited to this, the disclosure Embodiment is only illustrated so that specified shooting angle is specified level shooting angle as an example.

In addition, when carrying out image taking, can also be judged in real time according to image recognition technology each in current taken image Whether the eyes of target to be captured are in opening state；If it is, continue subsequent treatment；If it is not, then continue into Row shooting, until shooting successfully, detailed process is as follows：

Shooting angle is specified for each, judges to specify and whether is wrapped in an at least frame shooting image corresponding to shooting angle Eyes containing each target to be captured are in opening the specified image of state；If specify an at least frame corresponding to shooting angle The eyes for not including each target to be captured in shooting image are in opening the specified image of state, then control capture apparatus weight Newly shot, until specifying the eyes comprising each target to be captured in an at least frame shooting image corresponding to shooting angle equal Specified image in state of opening.

In step 203, Eye states recognition processing is carried out to multiframe shooting image, is identified result.

Wherein, multiframe shooting image is included in the preset number two field picture obtained in each specified shooting angle.Eyes State includes opening state and closure state.

In the disclosed embodiments, can be offline in advance before Eye states recognition processing is carried out to multiframe shooting image Establish training pattern.That is, collecting substantial amounts of face sample data in advance, and substantial amounts of face sample data is carried out at analysis Reason, obtains training pattern.After multiframe shooting image is obtained, each in each two field picture can be determined according to the training pattern The eye state of target to be captured, is identified result.

In step 204, according to recognition result, an at least frame shooting image corresponding to shooting angle is specified at each In, choose the specified image that eyes are in the target to be captured minimum number of closure state.

In the disclosed embodiments, preset number frame shooting figure is have taken in shooting angle due to being specified at each Picture, and specify each two field picture in shooting angle to carry out Eye states recognition processing each, so can basis Recognition result, specified at each and an eyeball of opening one's eyes is chosen in shooting angle be in the target to be captured minimum number of closure state Specify image.That is, the minimum image of a frame eye closing number is chosen in each shooting angle.How many specified shooting angle Degree, it can obtain that how many frame specify image.

In step 205, eyes are selected to be in the target to be captured minimum number of closure state in multiframe specifies image Image as synthesis primary image.

In the disclosed embodiments, obtain multiframe specify image after, due to each frame specify image in eyes be in close The number of conjunction state there may be difference, is when subsequently carrying out image synthesis processing, can reduce work as much as possible Measure, synthesis primary image need to be also chosen in multiframe specifies image.When choosing synthesis primary image, if each frame is specified Whole target to be captured is contained in image, then eyes are chosen directly in multiple image is in the number of closure state most Few image, as synthesis primary image.If including part target to be captured in each two field picture, multiframe is referred to Determine image and carry out splicing, obtain synthesizing primary image.Wherein, when target to be captured eyes are in closure state, shooting The image arrived is as shown in Figure 8.

In step 206, in primary image is synthesized, Eye states recognition processing is carried out to synthesis primary image, obtained Eyes are in the specified photographic subjects of closure state.

In the disclosed embodiments, after obtaining synthesizing primary image, need first according to the identification shown in above-mentioned steps 203 Method carries out Eye states recognition processing to synthesis primary image, it is determined that eyes are in the finger of closure state in synthesis primary image Determine photographic subjects.So as to which in subsequent process, eyes in synthesis primary image are in the face of the specified photographic subjects of closure state Portion region is replaced.

In step 207, in the multiframe shooting image in addition to primary image is synthesized, the eye for specifying photographic subjects is chosen Eyeball is in the facial zone for state of opening.

In the disclosed embodiments, when choosing facial zone of the eyes for specifying photographic subjects in state of opening, both It can choose in multiframe specifies image, can also be chosen in multiframe shooting image.Being specified when each frame in image is included all During target to be captured, it can be specified from multiframe and the facial zone that the eyes for specifying photographic subjects are in state of opening is chosen in image. When each frame, which is specified, includes part target to be captured in image, it can be chosen from multiframe shooting image and specify photographic subjects Eyes are in the facial zone for state of opening.The embodiment of the present disclosure is not especially limited to this.

In a step 208, synthesis primary image and the facial zone are synthesized, obtains composograph.

In the disclosed embodiments, the eyes for synthesizing primary image and specified photographic subjects are in the face for state of opening When region is synthesized, the facial zone that the eyes for synthesizing specified photographic subjects in primary image can be in closure state is gone Remove, and facial zone of the eyes of the specified photographic subjects of selection in state of opening is filled into pair in synthesis primary image Region is answered, and then obtains composograph.

It should be noted that when performing the method that the embodiment of the present disclosure provides, above-mentioned steps 203 to step 208 may be used also Replaced by following step 210 and step 211.Step 210 and step 211 are as follows.

In step 210, in multiframe shooting image, determine that each specifies whether to include in shooting angle and each wait to clap The eyes for taking the photograph target are in opening the image of state.

It is determined that whether the eyes comprising each target to be captured are in opening state in each specified shooting angle Image when, the identification method in above-mentioned steps 203 can be taken to be handled, here is omitted.

In step 211, if each eye for specifying shooting angle to include each target to be captured of a frame is in The image of state is opened, then specifies image corresponding to shooting angle to carry out synthesis processing each, obtains composograph.

In the disclosed embodiments, if each frame specify image in include whole target to be captured, it is determined that , can will be any after each eye for specifying shooting angle to include each target to be captured of a frame is in opening the image of state Image corresponding to shooting angle is specified as composograph.Whole wait to clap in addition, if each frame specifies to include in image Take the photograph target, then can be it is determined that any one specifies shooting angle to include the image that each target to be captured of a frame is in opening state When, the image is directly defined as composograph.If each frame specifies the target to be captured for including part in image, often Image corresponding to one specified shooting angle carries out splicing, obtains composograph.

It should be noted that when performing the method that the embodiment of the present disclosure provides, after above-mentioned steps 210, can also wrap Include following steps 212.

In the step 212, if each eye for specifying shooting angle to include each target to be captured of multiframe is in The specified image of state is opened, then the most figure of the target to be captured number in smile state is chosen in multiframe specifies image Picture, synthesis processing is carried out to image corresponding to each shooting angle, obtains composograph.

In the disclosed embodiments, if each frame specify image in include whole target to be captured, it is determined that , can be more at this after each eye for specifying shooting angle to include each target to be captured of multiframe is in opening the image of state The most image of the target to be captured data in smile state is chosen in two field picture, and as composograph.If in addition, Each frame, which is specified in image, includes whole target to be captured, then can be it is determined that any one specifies shooting angle to include multiframe When each target to be captured is in opening the image of state, directly chooses and treated in the specified shooting angle in smile state The most image of photographic subjects, and it is defined as composograph.Image after synthesis can be as shown in Figure 9.If each frame is specified Include the target to be captured of part in image, then it is determined that each specifies shooting angle to include multiframe each mesh to be captured Target eyes are in opening the specified image of state, then are selected in each specifies multiframe corresponding to shooting angle to specify image The most image of the target to be captured number in smile state is taken, and the image to being chosen in each shooting angle closes Into processing, composograph as shown in Figure 9 is obtained.

Figure 10 is a kind of block diagram of image processing apparatus according to an exemplary embodiment.Reference picture 10, the device Including screening-mode determining module 1001, shooting image acquisition module 1002, shooting image identification module 1003, specified image choosing Modulus block 1004, image synthesis processing module 1005.

Wherein, screening-mode determining module 1001, for determining to be currently at big group photo screening-mode；Shooting image obtains Module 1002 is connected with screening-mode determining module 1001, more in multiple specified shooting angle for obtaining target to be captured Frame shooting image；Shooting image identification module 1003 is connected with shooting image acquisition module 1002, for multiframe shooting image Eye states recognition processing is carried out, is identified result；Image is specified to choose module 1004 and shooting image identification module 1003 Connection, for according to recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choosing at eyes In the specified image of the target to be captured minimum number of closure state；Image synthesizes processing module 1005 and chooses mould with specified image Block 1004 connects, and for specifying image to carry out synthesis processing multiframe, the eyes for obtaining each target to be captured are in opening The composograph of state.

Alternatively, screening-mode determining module, for judging whether the target to be captured quantity in shooting picture is more than the One threshold value；When the target to be captured quantity in shooting picture is more than first threshold, it is determined that being currently at big group photo screening-mode； Or, in the case where distant view scape is other, judge that the edge of shooting picture whether there is incomplete target to be captured；When the side of shooting picture When incomplete target to be captured at edge be present, it is determined that being currently at big group photo screening-mode.

Alternatively, screening-mode determining module, for judging whether the target to be captured quantity in shooting picture is more than the One threshold value；When the target to be captured quantity in shooting picture is more than first threshold, the model of finding a view that shooting picture is covered is judged It whether there is target to be captured outside enclosing；When target to be captured be present outside the viewfinder range that shooting picture is covered, it is determined that It is currently at big group photo screening-mode.

Alternatively, the device also includes：

First control module, for controlling capture apparatus to be rotated, until the left hand edge line and first count at interface of finding a view The distance for taking the photograph Far Left target to be captured in picture is the first numerical value, the first position information of records photographing equipment；

First control module, for controlling capture apparatus to be rotated, until the right hand edge line and second count at interface of finding a view The distance for taking the photograph rightmost target to be captured in picture is the first numerical value, the second place information of records photographing equipment；

First rotational angle computing module, for according to first position information and second place information, calculating capture apparatus Horizontally rotate angle；

First shooting angle-determining module, for according to the numerical values recited for horizontally rotating angle, determining at least one specify Horizontal shooting angle.

Alternatively, shooting image acquisition module, for being continuously shot preset number frame figure in present level shooting angle As after, according at least one specified level shooting angle, control capture apparatus turns to next shooting angle；In next bat Take the photograph the target to be captured edge that identification should be shot in angle；When it is determined that should shoot target to be captured edge after, in next bat Take the photograph in angle and be continuously shot preset number two field picture；Above-mentioned steps are repeated, until in each specified level shooting angle Photographs finish.

Alternatively, the device also includes：

Second control module, for controlling capture apparatus to be rotated, until the top edge line and third shot at interface of finding a view The distance for taking the photograph the top target to be captured in picture is the first numerical value, the 3rd positional information of records photographing equipment；

Second control module, for controlling capture apparatus to be rotated, until the lower edge line at interface of finding a view and the 4th is clapped It is the first numerical value to take the photograph in picture the distance of target to be captured bottom, the 4th positional information of records photographing equipment；

Second rotational angle computing module, for according to the 3rd positional information and the 4th positional information, calculating capture apparatus Vertical rotational angle；

Second shooting angle-determining module, for the numerical values recited according to vertical rotational angle, determine at least one specify Vertical shooting angle.

Alternatively, shooting image acquisition module, for being continuously shot preset number frame figure in current vertical shooting angle As after, vertical shooting angle is specified according at least one, control capture apparatus turns to next shooting angle；In next bat Take the photograph the target to be captured edge that identification should be shot in angle；When it is determined that should shoot target to be captured edge after, in next bat Take the photograph in angle and be continuously shot preset number two field picture；Above-mentioned steps are repeated, until specifying vertical shooting angle at each Photographs finish.

Alternatively, image synthesis processing module, in multiframe shooting image, determining that each is specified in shooting angle Whether the eyes comprising each target to be captured are in opening the image of state；When the eye for including each target to be captured of a frame When eyeball is in opening the image of state, synthesis processing is carried out to described image corresponding to each shooting angle, obtained described Composograph.

Alternatively, image synthesis processing module, it is additionally operable to when the eyes comprising each target to be captured of multiframe are in opening During the specified image of open state, the most figure of the target to be captured number in smile state is chosen in multiframe specifies image Picture, synthesis processing is carried out to described image corresponding to each shooting angle, obtains the composograph.

Alternatively, image synthesis processing module, for selecting eyes to be in treating for closure state in specifying image in multiframe The image of photographic subjects minimum number is as synthesis primary image；In primary image is synthesized, eye is carried out to synthesis primary image Eyeball state recognition is handled, and obtains the specified photographic subjects that eyes are in closure state；In the multiframe in addition to primary image is synthesized In shooting image, the facial zone for specifying the eyes of photographic subjects to be in state of opening is chosen；Will synthesis primary image and face Region is synthesized, and obtains composograph.

Alternatively, the device also includes：

Image judge module is specified, for specifying shooting angle for each, judges to specify corresponding to shooting angle extremely Whether the eyes comprising each target to be captured are in opening the specified image of state in a few frame shooting image；

3rd control module, each wait to clap for working as to specify not include in an at least frame shooting image corresponding to shooting angle When taking the photograph the eyes of target and being in opening the specified image of state, control capture apparatus re-starts shooting, is shot until specifying The eyes comprising each target to be captured are in opening the specified image of state in an at least frame shooting image corresponding to angle.

The device that the embodiment of the present disclosure provides, after it is determined that being currently at big group photo screening-mode, obtain target to be captured Multiframe shooting image in multiple specified shooting angle, and Eye states recognition processing is carried out to the multiframe shooting image, According to obtained recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choose eyes and be in The specified image of the target to be captured minimum number of closure state；Afterwards, specify image to carry out synthesis processing to multiframe, obtain every The eyes of individual target to be captured are in opening the composograph of state, can be automatically to clapping due to taking a group photo under screening-mode greatly Take the photograph eyes in image and be in the target to be captured of closure state and handled, be in opening so as to obtain each target to be captured The composograph of eye state, therefore image processing operations more intelligence and simplicity, save manpower and image processing time.

On the device in above-described embodiment, wherein modules perform the concrete mode of operation in relevant this method Embodiment in be described in detail, explanation will be not set forth in detail herein.

Figure 11 is a kind of block diagram of equipment 1100 for image procossing according to an exemplary embodiment.For example, Equipment 1100 can be mobile phone, digital broadcast terminal, tablet device, personal digital assistant etc..

Reference picture 11, equipment 1100 can include following one or more assemblies：Processing component 1102, memory 1104, Power supply module 1106, multimedia groupware 1108, audio-frequency assembly 1110, I/O (Input/Output, input/output) interface 1112, sensor cluster 1114, and communication component 1116.

The integrated operation of the usual control device 1100 of processing component 1102, such as communicated with display, call, data, The operation that camera operation and record operation are associated.Processing component 1102 can include one or more processors 1120 to perform Instruction, to complete all or part of step of above-mentioned method.In addition, processing component 1102 can include one or more moulds Block, the interaction being easy between processing component 1102 and other assemblies.For example, processing component 1102 can include multi-media module, To facilitate the interaction between multimedia groupware 1108 and processing component 1102.

Memory 1104 is configured as storing various types of data to support the operation in equipment 1100.These data Example includes being used for the instruction of any application program or method operated in equipment 1100, contact data, telephone book data, Message, picture, video etc..Memory 1104 can by any kind of volatibility or non-volatile memory device or they Combination is realized, such as SRAM (Static Random Access Memory, static RAM), EEPROM (Electrically-Erasable Programmable Read-Only Memory, the read-only storage of electrically erasable Device), EPROM (Erasable Programmable Read Only Memory, Erasable Programmable Read Only Memory EPROM), PROM (Programmable Read-Only Memory, programmable read only memory), and ROM (Read-Only Memory, it is read-only to deposit Reservoir), magnetic memory, flash memory, disk or CD.

Power supply module 1106 provides electric power for the various assemblies of equipment 1100.Power supply module 1106 can include power management System, one or more power supplys, and other components associated with generating, managing and distributing electric power for equipment 1100.

Multimedia groupware 1108 is included in the screen of one output interface of offer between the equipment 1100 and user. In some embodiments, screen can include LCD (Liquid Crystal Display, liquid crystal display) and TP (Touch Panel, touch panel).If screen includes touch panel, screen may be implemented as touch-screen, to receive from user's Input signal.Touch panel includes one or more touch sensors with the gesture on sensing touch, slip and touch panel.Institute Stating touch sensor can the not only border of sensing touch or sliding action, but also detect and the touch or slide phase The duration and pressure of pass.In certain embodiments, multimedia groupware 1108 includes a front camera and/or rearmounted taken the photograph As head.When equipment 1100 is in operator scheme, during such as screening-mode or video mode, front camera and/or rear camera The multi-medium data of outside can be received.Each front camera and rear camera can be a fixed optical lens systems System has focusing and optical zoom capabilities.

Audio-frequency assembly 1110 is configured as output and/or input audio signal.For example, audio-frequency assembly 1110 includes one MIC (Microphone, microphone), when equipment 1100 is in operator scheme, such as call model, logging mode and speech recognition mould During formula, microphone is configured as receiving external audio signal.The audio signal received can be further stored in memory 1104 or sent via communication component 1116.In certain embodiments, audio-frequency assembly 1110 also includes a loudspeaker, for defeated Go out audio signal.

I/O interfaces 1112 provide interface, above-mentioned peripheral interface module between processing component 1102 and peripheral interface module Can be keyboard, click wheel, button etc..These buttons may include but be not limited to：Home button, volume button, start button and Locking press button.

Sensor cluster 1114 includes one or more sensors, and the state for providing various aspects for equipment 1100 is commented Estimate.For example, sensor cluster 1114 can detect opening/closed mode of equipment 1100, the relative positioning of component, such as group Part is the display and keypad of equipment 1100, and sensor cluster 1114 can be with 1,100 1 groups of detection device 1100 or equipment The position of part changes, the existence or non-existence that user contacts with equipment 1100, the orientation of equipment 1100 or acceleration/deceleration and equipment 1100 temperature change.Sensor cluster 1114 can include proximity transducer, be configured to connect in no any physics The presence of object nearby is detected when touching.Sensor cluster 1114 can also include optical sensor, such as CMOS (Complementary Metal Oxide Semiconductor, CMOS) or CCD (Charge-coupled Device, Charged Couple Element) imaging sensor, for being used in imaging applications.In certain embodiments, the sensor cluster 1114 can also wrap Include acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.

Communication component 1116 is configured to facilitate the communication of wired or wireless way between equipment 1100 and other equipment.If Standby 1100 can access the wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof.It is exemplary at one In embodiment, communication component 1116 receives broadcast singal or broadcast correlation from external broadcasting management system via broadcast channel Information.In one exemplary embodiment, the communication component 1116 also include NFC (Near Field Communication, Near-field communication) module, to promote junction service.For example, RFID (Radio Frequency can be based in NFC module Identification, radio frequency identification) technology, IrDA (Infra-red Data Association, Infrared Data Association) skill Art, UWB (Ultra Wideband, ultra wide band) technology, BT (Bluetooth, bluetooth) technologies and other technologies are realized.

In the exemplary embodiment, equipment 1100 can be by one or more ASIC (Application Specific Integrated Circuit, application specific integrated circuit), DSP (Digital signal Processor, at data signal Manage device), DSPD (Digital signal Processor Device, digital signal processing appts), PLD (Programmable Logic Device, PLD), FPGA) (Field Programmable Gate Array, field programmable gate Array), controller, microcontroller, microprocessor or other electronic components realize, for performing the above method.

In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided Such as include the memory 1104 of instruction, above-mentioned instruction can be performed to complete the above method by the processor 1120 of equipment 1100.Example Such as, the non-transitorycomputer readable storage medium can be ROM, RAM (Random Access Memory, arbitrary access Memory), CD-ROM (Compact Disc Read-Only Memory, compact disc read-only memory), tape, floppy disk and light number According to storage device etc..

A kind of non-transitorycomputer readable storage medium, when the instruction in storage medium is held by the processor of mobile terminal During row so that mobile terminal is able to carry out a kind of image processing method, and this method includes：

It is determined that it is currently at big group photo screening-mode；

Eye states recognition processing is carried out to multiframe shooting image, is identified result；

According to recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choose at eyes In the specified image of the target to be captured minimum number of closure state；

If each eye for specifying shooting angle to include each target to be captured of a frame is in opening the figure of state Picture, then specify image corresponding to shooting angle to carry out synthesis processing each, obtain composograph.

If each eye for specifying shooting angle to include each target to be captured of multiframe is in opening the finger of state Determine image, then the most image of the target to be captured number in smile state is chosen in multiframe specifies image, to each Image corresponding to shooting angle carries out synthesis processing, obtains composograph.

Synthesis primary image and facial zone are synthesized, obtain composograph.

The non-transitorycomputer readable storage medium that the embodiment of the present disclosure provides, it is determined that being currently at big group photo shooting After pattern, multiframe shooting image of the target to be captured in multiple specified shooting angle is obtained, and to the multiframe shooting image Eye states recognition processing is carried out, according to obtained recognition result, specifies an at least frame corresponding to shooting angle to clap at each Take the photograph in image, choose the specified image that eyes are in the target to be captured minimum number of closure state；Afterwards, figure is specified to multiframe As carrying out synthesis processing, the eyes for obtaining each target to be captured are in opening the composograph of state, due to taking a group photo greatly Under screening-mode, the target to be captured that automatically eyes in shooting image can be in closure state is handled, every so as to obtain One target to be captured is in the composograph of eyes-open state, therefore image processing operations more intelligence and simplicity, saves Manpower and image processing time.

Those skilled in the art will readily occur to the present invention its after considering specification and putting into practice invention disclosed herein Its embodiment.The application be intended to the present invention any modification, purposes or adaptations, these modifications, purposes or Person's adaptations follow the general principle of the present invention and including the undocumented common knowledges in the art of the disclosure Or conventional techniques.Description and embodiments are considered only as exemplary, and true scope and spirit of the invention are by following Claim is pointed out.

It should be appreciated that the invention is not limited in the precision architecture for being described above and being shown in the drawings, and And various modifications and changes can be being carried out without departing from the scope.The scope of the present invention is only limited by appended claim.

Claims

1. a kind of image processing method, it is characterised in that methods described includes：

It is determined that it is currently at big group photo screening-mode；

According to the recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choose at eyes In the specified image of the target to be captured minimum number of closure state；

Image is specified to carry out synthesis processing to multiframe, the eyes for obtaining each target to be captured are in opening the composite diagram of state Picture；

Wherein, before the multiframe shooting image for obtaining target to be captured in multiple specified shooting angle, methods described is also Including：Control capture apparatus is rotated, until the left hand edge line and Far Left in the first shooting picture at interface of finding a view are to be captured The distance of target is the first numerical value, records the first position information of the capture apparatus；The capture apparatus is controlled to be rotated, Until the distance of rightmost target to be captured is the described first number in the right hand edge line at the interface of finding a view and the second shooting picture Value, record the second place information of the capture apparatus；According to the first position information and the second place information, calculate The capture apparatus horizontally rotates angle；According to the numerical values recited for horizontally rotating angle, at least one specified water is determined Flat shooting angle；

And/or control capture apparatus is rotated, until the top edge line at interface of finding a view is taken the photograph in picture with third shot and topmost treated The distance of photographic subjects is the first numerical value, records the 3rd positional information of the capture apparatus；The capture apparatus is controlled to carry out Rotate, until the lower edge line at the interface of finding a view with the distance of target to be captured is described the bottom in the 4th shooting picture One numerical value, record the 4th positional information of the capture apparatus；According to the 3rd positional information and the 4th positional information, Calculate the vertical rotational angle of the capture apparatus；According to the numerical values recited of the vertical rotational angle, at least one finger is determined Fixed vertical shooting angle.

2. according to the method for claim 1, it is characterised in that the determination is currently at big group photo screening-mode, including：

Judge whether the target to be captured quantity in shooting picture is more than first threshold；It is if to be captured in the shooting picture Destination number is more than the first threshold, it is determined that is currently at big group photo screening-mode；Or,

In the case where distant view scape is other, judge that the edge of the shooting picture whether there is incomplete target to be captured；It is if described There is incomplete target to be captured in the edge of shooting picture, it is determined that be currently at big group photo screening-mode.

3. according to the method for claim 1, it is characterised in that the determination is currently at big group photo screening-mode, including：

If the target to be captured quantity in the shooting picture is more than the first threshold, judge that the shooting picture is covered It whether there is target to be captured outside the viewfinder range of lid；

If target to be captured be present outside the viewfinder range that the shooting picture is covered, it is determined that be currently at big group photo and clap Take the photograph pattern.

4. according to the method for claim 1, it is characterised in that the acquisition target to be captured is in multiple specified shooting angle On multiframe shooting image, including：

After preset number two field picture is continuously shot in present level shooting angle, shot according at least one specified level Angle, the capture apparatus is controlled to turn to next shooting angle；

5. according to the method for claim 1, it is characterised in that the acquisition target to be captured is in multiple specified shooting angle On multiframe shooting image, including：

After preset number two field picture is continuously shot in current vertical shooting angle, vertically shot according at least one specify Angle, the capture apparatus is controlled to turn to next shooting angle；

6. the method according to any claim in claim 1 to 5, it is characterised in that described that image is specified to multiframe Synthesis processing is carried out, the eyes for obtaining each target to be captured are in opening the composograph of state, including：

In the multiframe shooting image, determine that each specifies the eyes that each target to be captured whether is included in shooting angle It is in opening the image of state；

If each eye for specifying shooting angle to include each target to be captured of a frame is in opening the image of state, Specify described image corresponding to shooting angle to carry out synthesis processing each, obtain the composograph.

7. according to the method for claim 6, it is characterised in that described to determine whether included in each specified shooting angle After the eyes of each target to be captured are in opening the image of state, methods described also includes：

If each eye for specifying shooting angle to include each target to be captured of multiframe is in opening the specified figure of state Picture, then the most image of the target to be captured number in smile state is chosen in the multiframe specifies image, to each Described image corresponding to shooting angle carries out synthesis processing, obtains the composograph.

8. the method according to any claim in claim 1 to 5, it is characterised in that described that image is specified to multiframe Synthesis processing is carried out, the eyes for obtaining each target to be captured are in opening the composograph of state, including：

Selection eyes are in the image of the target to be captured minimum number of closure state as conjunction in the multiframe specifies image Into primary image；

In the synthesis primary image, Eye states recognition processing is carried out to the synthesis primary image, eyes is obtained and is in The specified photographic subjects of closure state；

In the multiframe shooting image in addition to primary image is synthesized, the eyes of the selection specified photographic subjects, which are in, opens shape The facial zone of state；

9. according to the method for claim 1, it is characterised in that described to be specified at each at least one corresponding to shooting angle In frame shooting image, after the specified image for choosing the target to be captured minimum number that eyes are in closure state, methods described Also include：

Shooting angle is specified for each, judges whether wrapped in an at least frame shooting image corresponding to the specified shooting angle Eyes containing each target to be captured are in opening the specified image of state；

If the eyes for not including each target to be captured in an at least frame shooting image corresponding to the specified shooting angle are equal Specified image in state of opening, then control the capture apparatus to re-start shooting, until the specified shooting angle pair The eyes comprising each target to be captured are in opening the specified image of state at least frame shooting image answered.

10. a kind of image processing apparatus, it is characterised in that described device includes：

Shooting image acquisition module, for obtaining multiframe shooting image of the target to be captured in multiple specified shooting angle；

Shooting image identification module, for carrying out Eye states recognition processing to the multiframe shooting image, it is identified result；

Image is specified to choose module, for according to the recognition result, an at least frame corresponding to shooting angle to be specified at each In shooting image, the specified image that eyes are in the target to be captured minimum number of closure state is chosen；

Image synthesizes processing module, for specifying image to carry out synthesis processing multiframe, obtains the eyes of each target to be captured It is in opening the composograph of state；

Wherein, described device also includes：

First control module, for controlling capture apparatus to be rotated, until the left hand edge line at interface of finding a view and the first shooting picture The distance of Far Left target to be captured is the first numerical value in face, records the first position information of the capture apparatus；Described first Control module, for controlling the capture apparatus to be rotated, until the right hand edge line at the interface of finding a view and the second shooting picture The distance of rightmost target to be captured is first numerical value in face, records the second place information of the capture apparatus；First Rotational angle computing module, for according to the first position information and the second place information, calculating the capture apparatus Horizontally rotate angle；First shooting angle-determining module, for horizontally rotating the numerical values recited of angle according to, it is determined that extremely A few specified level shooting angle；

And/or second control module, for controlling capture apparatus to be rotated, until the top edge line and the 3rd at interface of finding a view The distance of the top target to be captured is the first numerical value in shooting picture, records the 3rd positional information of the capture apparatus；Institute The second control module is stated, for controlling the capture apparatus to be rotated, until the lower edge line and the 4th at the interface of finding a view The distance of target to be captured is first numerical value bottom in shooting picture, records the 4th position letter of the capture apparatus Breath；Second rotational angle computing module, for according to the 3rd positional information and the 4th positional information, calculating the bat Take the photograph the vertical rotational angle of equipment；Second shooting angle-determining module, for the numerical values recited according to the vertical rotational angle, Determine at least one specified vertical shooting angle.

11. device according to claim 10, it is characterised in that the screening-mode determining module, for judging to shoot Whether the target to be captured quantity in picture is more than first threshold；When the target to be captured quantity in the shooting picture is more than institute When stating first threshold, it is determined that being currently at big group photo screening-mode；Or, in the case where distant view scape is other, judge the side of the shooting picture It whether there is incomplete target to be captured at edge；When the edge of the shooting picture has incomplete target to be captured When, it is determined that being currently at big group photo screening-mode.

12. device according to claim 10, it is characterised in that the screening-mode determining module, for judging to shoot Whether the target to be captured quantity in picture is more than first threshold；When the target to be captured quantity in the shooting picture is more than institute When stating first threshold, judge to whether there is target to be captured outside the viewfinder range that the shooting picture is covered；When the bat Take the photograph when target to be captured be present outside the viewfinder range that picture is covered, it is determined that being currently at big group photo screening-mode.

13. device according to claim 10, it is characterised in that the shooting image acquisition module, in current water After preset number two field picture is continuously shot in flat shooting angle, according at least one specified level shooting angle, institute is controlled State capture apparatus and turn to next shooting angle；The target to be captured edge that should be shot is identified in next shooting angle； When it is determined that should shoot target to be captured edge after, be continuously shot preset number two field picture in next shooting angle； Above-mentioned steps are repeated, until being finished in each specified level shooting angle photographs.

14. device according to claim 10, it is characterised in that the shooting image acquisition module, for being hung down currently After being continuously shot preset number two field picture in straight shooting angle, according at least one specified vertical shooting angle, institute is controlled State capture apparatus and turn to next shooting angle；The target to be captured edge that should be shot is identified in next shooting angle； When it is determined that should shoot target to be captured edge after, be continuously shot preset number two field picture in next shooting angle； Above-mentioned steps are repeated, until specifying vertical shooting angle photographs to finish at each.

15. the device according to any claim in claim 10 to 14, it is characterised in that described image synthesis is handled Module, whether each target to be captured is included in the multiframe shooting image, determining each to specify in shooting angle Eyes be in opening the image of state；When the eyes comprising each target to be captured of a frame are in opening the image of state When, synthesis processing is carried out to described image corresponding to each shooting angle, obtains the composograph.

16. device according to claim 15, it is characterised in that described image synthesize processing module, be additionally operable to when comprising When the eyes of each target to be captured of multiframe are in opening the specified image of state, in the multiframe specifies image at selection In the most image of the target to be captured number of smile state, described image corresponding to each shooting angle is carried out at synthesis Reason, obtains the composograph.

17. the device according to any claim in claim 10 to 14, it is characterised in that described image synthesis is handled Module, the image for the target to be captured minimum number for being in closure state for selection eyes in specifying image in the multiframe are made To synthesize primary image；In the synthesis primary image, Eye states recognition processing is carried out to the synthesis primary image, obtained The specified photographic subjects of closure state are in eyes；In the multiframe shooting image in addition to primary image is synthesized, institute is chosen The eyes for stating specified photographic subjects are in the facial zone for state of opening；The synthesis primary image and the facial zone are entered Row synthesis, obtains the composograph.

18. device according to claim 10, it is characterised in that described device also includes：

Image judge module is specified, for specifying shooting angle for each, is judged corresponding to the specified shooting angle extremely Whether the eyes comprising each target to be captured are in opening the specified image of state in a few frame shooting image；

3rd control module, for when in an at least frame shooting image corresponding to the specified shooting angle not comprising each waiting to clap When taking the photograph the eyes of target and being in opening the specified image of state, the capture apparatus is controlled to re-start shooting, until described The eyes comprising each target to be captured in an at least frame shooting image corresponding to shooting angle are specified to be in opening state Specify image.

19. a kind of image processing equipment, it is characterised in that the equipment includes：

Processor；

For storing the memory of processor-executable instruction；

Wherein, the processor is configured as：It is determined that it is currently at big group photo screening-mode；Target to be captured is obtained in multiple fingers Determine the multiframe shooting image in shooting angle；Eye states recognition processing is carried out to the multiframe shooting image, is identified tying Fruit；According to the recognition result, in each specifies an at least frame shooting image corresponding to shooting angle, choose eyes and be in The specified image of the target to be captured minimum number of closure state；Specify image to carry out synthesis processing to multiframe, obtain each treat The eyes of photographic subjects are in opening the composograph of state；

Wherein, before the multiframe shooting image for obtaining target to be captured in multiple specified shooting angle, the processor It is additionally configured to：Control capture apparatus is rotated, until Far Left in the left hand edge line at interface of finding a view and the first shooting picture The distance of target to be captured is the first numerical value, records the first position information of the capture apparatus；The capture apparatus is controlled to enter Row rotates, until the distance of rightmost target to be captured is described in the right hand edge line at the interface of finding a view and the second shooting picture First numerical value, record the second place information of the capture apparatus；According to the first position information and the second confidence Breath, calculate the capture apparatus horizontally rotates angle；According to the numerical values recited for horizontally rotating angle, determine at least one Specified level shooting angle；