CN104243818A

CN104243818A - Image processing method and device and image processing equipment

Info

Publication number: CN104243818A
Application number: CN201410437384.3A
Authority: CN
Inventors: 唐明勇; 刘华一君; 肖彦林
Original assignee: Xiaomi Inc
Current assignee: Beijing Xiaomi Technology Co Ltd; Xiaomi Inc
Priority date: 2014-08-29
Filing date: 2014-08-29
Publication date: 2014-12-24
Anticipated expiration: 2034-08-29
Also published as: CN104243818B

Abstract

The invention discloses an image processing method and device and image processing equipment, and belongs to the technical field of images. The image processing method comprises the steps that it is determined that a current shooting mode is a group photo shooting mode; multiple frames of shot images of targets to be shot at multiple assigned shooting angles are obtained; eye state recognition processing is carried out on the multiple frames of shot images, and a recognition result is obtained; according to the recognition result, in at least one frame of shot image corresponding to each assigned shooting angle, assigned images with the smallest number of targets to be shot with the closed eyes is selected; composition processing is carried out on the multiple assigned images, and a composite image in which the eyes of each target to be shot are open is obtained. Due to the fact that in the group photo shooting mode, the targets to be short with the closed eyes in the shot images can be automatically processed, the composite image in which the eyes of each target to be shot are open is obtained, image processing is intelligent, easy and convenient, and labor and image processing time are saved.

Description

Image processing method, device and equipment

Technical field

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

Background technology

When taking pictures, the stimulation emitted beam due to photoflash lamp and the natural reaction of human body, the moment people that shutter is pressed there will be the situation of nictation often.For the large group photo of large contingent, this phenomenon is particularly outstanding.Not only have impact on the attractive in appearance of image, also reduce the satisfaction of user to image.Therefore, need a kind of image processing method badly and solve this problem.

Correlation technique, can continuous shoot multi-frame images when shooting is taken a group photo greatly.Afterwards, in multiple image, a two field picture is manually chosen as synthesis primary image.If in synthesis primary image, user A has blinked eyes, the then manual image chosen user A and open eyes in other two field pictures remaining, and chooses the face area that user A eyes are in the state of opening; Afterwards, the face area manually user A eyes being in the state of opening synthesizes with synthesis primary image.Repeatedly perform above-mentioned steps, until obtain the large group photo that proprietary eyes are all in the state of opening.

Realizing in process of the present disclosure, inventor finds that correlation technique at least exists following problem:

Carrying out in image processing process, owing to needing manually repeatedly to perform the operation of repairing situation nictation, so operation is comparatively loaded down with trivial details and complicated, intelligent not.

Summary of the invention

For overcoming Problems existing in correlation technique, the disclosure provides a kind of image processing method, device and equipment.

According to the first aspect of disclosure embodiment, provide a kind of image processing method, described method comprises:

Determine currently to be in screening-mode of taking a group photo greatly;

Obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle;

Eye states recognition process is carried out to described multiframe photographic images, obtains recognition result;

According to described recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state;

Specify image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening.

Alternatively, describedly determine currently to be in screening-mode of taking a group photo greatly, comprising:

Judge whether the destination number to be captured in shooting picture is greater than first threshold; If the destination number to be captured in described shooting picture is greater than described first threshold, then determine currently to be in screening-mode of taking a group photo greatly; Or,

Under distant view scape is other, judge whether the edge of described shooting picture exists incomplete target to be captured; If the edge of described shooting picture exists incomplete target to be captured, then determine currently to be in screening-mode of taking a group photo greatly.

Judge whether the destination number to be captured in shooting picture is greater than first threshold;

If the destination number to be captured in described shooting picture is greater than described first threshold, then judge whether there is target to be captured outside the viewfinder range that described shooting picture covers;

If there is target to be captured outside the viewfinder range that described shooting picture covers, then determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, before the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, described method also comprises:

Control capture apparatus to rotate, until the distance of Far Left target to be captured is the first numerical value in the left hand edge line at interface of finding a view and the first shooting picture, record the primary importance information of described capture apparatus;

Control described capture apparatus to rotate, until described in the distance of rightmost target to be captured in the right hand edge line at interface and the second shooting picture of finding a view be described first numerical value, record the second place information of described capture apparatus;

According to described primary importance information and described second place information, what calculate described capture apparatus horizontally rotates angle;

According to the described numerical values recited horizontally rotating angle, determine at least one specified level shooting angle.

Alternatively, the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, comprising:

After present level shooting angle takes preset number two field picture continuously, according at least one specified level shooting angle described, control described capture apparatus and turn to next shooting angle;

Next shooting angle identifies the object edge to be captured that should take;

When after the object edge to be captured determining to take, described next shooting angle takes preset number two field picture continuously;

Repeat above-mentioned steps, until complete in each specified level shooting angle photographs.

Control capture apparatus to rotate, until the distance that the top edge line at interface of finding a view and third shot take the photograph target to be captured topmost in picture is the first numerical value, record the 3rd positional information of described capture apparatus;

Control described capture apparatus to rotate, until described in the distance of target to be captured bottom of finding a view in the lower limb line at interface and the 4th shooting picture be described first numerical value, record the 4th positional information of described capture apparatus;

According to described 3rd positional information and described 4th positional information, calculate the vertical rotation angle of described capture apparatus;

According to the numerical values recited of described vertical rotation angle, determine that at least one specifies vertical shooting angle.

In current vertical shooting angle continuously after shooting preset number two field picture, according to described at least one specify vertical shooting angle, control described capture apparatus and turn to next shooting angle;

Next shooting angle identifies the object edge to be captured that should take;

Repeat above-mentioned steps, until specify vertical shooting angle photographs complete at each.

Alternatively, described to multiframe specify image carry out synthesis process, the eyes obtaining each target to be captured are all in the composograph of the state of opening, and comprising:

In described multiframe photographic images, determine that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening;

If each eye of specifying shooting angle to comprise each target to be captured of a frame is all in the image of the state of opening, then specifies described image corresponding to shooting angle to carry out synthesis process to each, obtain described composograph.

Alternatively, after the described eyes determining whether each appointment shooting angle comprises each target to be captured are all in the image of the state of opening, described method also comprises:

If each eye of specifying shooting angle to comprise each target to be captured of multiframe is all in the appointment image of the state of opening, then specify in image in described multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Specifying in image in described multiframe selects eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image;

In described synthesis primary image, Eye states recognition process is carried out to described synthesis primary image, obtain the appointment photographic subjects that eyes are in closure state;

In the multiframe photographic images except synthesis primary image, the eyes choosing described appointment photographic subjects are in the facial zone of the state of opening;

Described synthesis primary image and described facial zone are synthesized, obtains described composograph.

Alternatively, describedly to specify at least one frame photographic images corresponding to shooting angle at each, choose after eyes are in the minimum appointment image of the destination number to be captured of closure state, described method also comprises:

Specify shooting angle for each, the eyes judging whether to comprise at least one frame photographic images that described appointment shooting angle is corresponding each target to be captured are all in the appointment image of the state of opening;

If the eyes not comprising each target to be captured at least one frame photographic images that described appointment shooting angle is corresponding are all in the appointment image of the state of opening, then control described capture apparatus and re-start shooting, until the eyes comprising each target to be captured at least one frame photographic images corresponding to described appointment shooting angle are all in the appointment image of the state of opening.

According to the second aspect of disclosure embodiment, provide a kind of image processing apparatus, described device comprises:

Screening-mode determination module, is currently in screening-mode of taking a group photo greatly for determining;

Photographic images acquisition module, for obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle;

Photographic images identification module, for carrying out Eye states recognition process to described multiframe photographic images, obtains recognition result;

Specify image to choose module, for according to described recognition result, at least one frame photographic images that each specifies shooting angle corresponding, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state;

Images uniting processing module, for specifying image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening.

Alternatively, described screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in described shooting picture is greater than described first threshold, determine currently to be in screening-mode of taking a group photo greatly; Or, under distant view scape is other, judge whether the edge of described shooting picture exists incomplete target to be captured; When the edge of described shooting picture exists incomplete target to be captured, determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, described screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in described shooting picture is greater than described first threshold, judge whether there is target to be captured outside the viewfinder range that described shooting picture covers; When there is target to be captured outside the viewfinder range that described shooting picture covers, determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, described device also comprises:

First control module, rotates for controlling capture apparatus, until the distance of Far Left target to be captured is the first numerical value in the left hand edge line at interface of finding a view and the first shooting picture, records the primary importance information of described capture apparatus;

Described first control module, rotates for controlling described capture apparatus, until described in the distance of rightmost target to be captured in the right hand edge line at interface and the second shooting picture of finding a view be described first numerical value, record the second place information of described capture apparatus;

First rotational angle computing module, for according to described primary importance information and described second place information, what calculate described capture apparatus horizontally rotates angle;

First shooting angle determination module, for horizontally rotating the numerical values recited of angle described in basis, determines at least one specified level shooting angle.

Alternatively, described photographic images acquisition module, after take preset number two field picture continuously in present level shooting angle, according at least one specified level shooting angle described, controls described capture apparatus and turns to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, described next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until complete in each specified level shooting angle photographs.

Alternatively, described device also comprises:

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

Described second control module, rotates for controlling described capture apparatus, until described in the distance of target to be captured bottom of finding a view in the lower limb line at interface and the 4th shooting picture be described first numerical value, record the 4th positional information of described capture apparatus;

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

Second shooting angle determination module, for the numerical values recited according to described vertical rotation angle, determines that at least one specifies vertical shooting angle.

Alternatively, described photographic images acquisition module, in current vertical shooting angle continuously after shooting preset number two field picture, according to described at least one specify vertical shooting angle, control described capture apparatus and turn to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, described next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until specify vertical shooting angle photographs complete at each.

Alternatively, described Images uniting processing module, in described multiframe photographic images, determines that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening; When the eyes comprising each target to be captured of a frame are all in the image of the state of opening, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Alternatively, described Images uniting processing module, time also for being all in the appointment image of the state of opening when the eyes comprising each target to be captured of multiframe, specify in image in described multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Alternatively, described Images uniting processing module, selects eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image for specifying in image in described multiframe; In described synthesis primary image, Eye states recognition process is carried out to described synthesis primary image, obtain the appointment photographic subjects that eyes are in closure state; In the multiframe photographic images except synthesis primary image, the eyes choosing described appointment photographic subjects are in the facial zone of the state of opening; Described synthesis primary image and described facial zone are synthesized, obtains described composograph.

Alternatively, described device also comprises:

Specify image judge module, for specifying shooting angle for each, the eyes judging whether to comprise at least one frame photographic images that described appointment shooting angle is corresponding each target to be captured are all in the appointment image of the state of opening;

3rd control module, during for being all in the appointment image of the state of opening when the eyes not comprising each target to be captured at least one frame photographic images that described appointment shooting angle is corresponding, control described capture apparatus and re-start shooting, until the eyes comprising each target to be captured at least one frame photographic images corresponding to described appointment shooting angle are all in the appointment image of the state of opening.

According to the third aspect of disclosure embodiment, provide a kind of image processing equipment, described equipment comprises:

Processor;

For the memory of storage of processor executable instruction;

Wherein, described processor is configured to: determine currently to be in screening-mode of taking a group photo greatly; Obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle; Eye states recognition process is carried out to described multiframe photographic images, obtains recognition result; According to described recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Specify image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening.

The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:

Determine current be in large group photo screening-mode after, obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle, and Eye states recognition process is carried out to described multiframe photographic images, according to the recognition result obtained, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Afterwards, image is specified to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening, due under large group photo screening-mode, can automatically process the target to be captured that eyes in photographic images are in closure state, thus obtain the composograph that each target to be captured is all in eyes-open state, therefore image processing operations is comparatively intelligent and easy, saves manpower and image processing time.

Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.

Accompanying drawing explanation

Accompanying drawing to be herein merged in specification and to form the part of this specification, shows embodiment according to the invention, and is used from specification one and explains principle of the present invention.

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

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

Fig. 3 is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 4 is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 5 a is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 5 b is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 6 a is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 6 b is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 6 c is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 7 is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 8 is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

Fig. 9 is the schematic diagram of a kind of photographic images according to an exemplary embodiment.

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

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

Embodiment

Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Execution mode described in following exemplary embodiment does not represent all execution modes consistent with the present invention.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present invention are consistent.

Fig. 1 is the flow chart of a kind of image processing method according to an exemplary embodiment, and as shown in Figure 1, this image processing method is used for, in image processing equipment, comprising the following steps.

In a step 101, determine currently to be in screening-mode of taking a group photo greatly.

In a step 102, the multiframe photographic images of target to be captured in multiple appointment shooting angle is obtained.

In step 103, Eye states recognition process is carried out to multiframe photographic images, obtains recognition result.

At step 104, according to recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state.

In step 105, specify image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening.

The method that disclosure embodiment provides, determine current be in large group photo screening-mode after, obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle, and Eye states recognition process is carried out to described multiframe photographic images, according to the recognition result obtained, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Afterwards, image is specified to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening, due under large group photo screening-mode, can automatically process the target to be captured that eyes in photographic images are in closure state, thus obtain the composograph that each target to be captured is all in eyes-open state, therefore image processing operations is comparatively intelligent and easy, saves manpower and image processing time.

Alternatively, determine currently to be in screening-mode of taking a group photo greatly, comprising:

Judge whether the destination number to be captured in shooting picture is greater than first threshold; If the destination number to be captured in shooting picture is greater than first threshold, then determine currently to be in screening-mode of taking a group photo greatly; Or,

Under distant view scape is other, judge whether the edge of shooting picture exists incomplete target to be captured; If the edge of shooting picture exists incomplete target to be captured, then determine currently to be in screening-mode of taking a group photo greatly.

If the destination number to be captured in shooting picture is greater than first threshold, then judge whether there is target to be captured outside the viewfinder range that shooting picture covers;

If there is target to be captured outside the viewfinder range that shooting picture covers, then determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, before obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle, the method also comprises:

Control capture apparatus to rotate, until the distance of Far Left target to be captured is the first numerical value in the left hand edge line at interface of finding a view and the first shooting picture, the primary importance information of records photographing equipment;

Control capture apparatus to rotate, until the distance of rightmost target to be captured is the first numerical value in the right hand edge line at interface of finding a view and the second shooting picture, the second place information of records photographing equipment;

According to primary importance information and second place information, what calculate capture apparatus horizontally rotates angle;

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

Alternatively, obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle, comprising:

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

Next shooting angle identifies the object edge to be captured that should take;

When after the object edge to be captured determining to take, next shooting angle takes preset number two field picture continuously;

Control capture apparatus to rotate, until the distance that the top edge line at interface of finding a view and third shot take the photograph target to be captured topmost in picture is the first numerical value, the 3rd positional information of records photographing equipment;

Control capture apparatus to rotate, until in the lower limb line at interface of finding a view and the 4th shooting picture bottom the distance of target to be captured be the first numerical value, the 4th positional information of records photographing equipment;

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

According to the numerical values recited of vertical rotation angle, determine that at least one specifies vertical shooting angle.

After current vertical shooting angle takes preset number two field picture continuously, specify vertical shooting angle according at least one, control capture apparatus and turn to next shooting angle;

Next shooting angle identifies the object edge to be captured that should take;

Alternatively, specify image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening, and comprising:

In multiframe photographic images, determine that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening;

Alternatively, determine that each specifies after the eyes whether shooting angle comprising each target to be captured are all in the image of the state of opening, the method also comprises:

If each eye of specifying shooting angle to comprise each target to be captured of multiframe is all in the appointment image of the state of opening, then specify in image in multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Specifying in image in multiframe selects eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image;

In synthesis primary image, Eye states recognition process is carried out to synthesis primary image, obtains the appointment photographic subjects that eyes are in closure state;

In the multiframe photographic images except synthesis primary image, choose the facial zone of specifying the eyes of photographic subjects to be in the state of opening;

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

Alternatively, specify at least one frame photographic images corresponding to shooting angle at each, choose after eyes are in the minimum appointment image of the destination number to be captured of closure state, the method also comprises:

Shooting angle is specified for each, judges to specify the eyes whether comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening;

If specify the eyes not comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening, then control capture apparatus and re-start shooting, until specify the eyes comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening.

Above-mentioned all alternatives, can adopt and combine arbitrarily formation optional embodiment of the present invention, this is no longer going to repeat them.

Fig. 2 is the flow chart of a kind of image processing method according to an exemplary embodiment, and as shown in Figure 2, this image processing method is used for, in image processing equipment, comprising the following steps.

In step 201, determine currently to be in screening-mode of taking a group photo greatly.

Wherein, large group photo screening-mode refers to current participation and to take pictures the screening-mode of large contingent.Such as, student's graduation is taken a group photo, or the personnel participating in the meeting of convention takes a group photo.

In the disclosed embodiments, determine current be in large group photo screening-mode time, following three kinds of modes can be taked to realize:

Whether first kind of way, the destination number to be captured judged in shooting picture are greater than first threshold; If the destination number to be captured in shooting picture is greater than first threshold, then determine currently to be in screening-mode of taking a group photo greatly.

Wherein, the size of first threshold can be 50 people or 100 people etc., and disclosure embodiment does not do concrete restriction to this, optionally can arrange the size of first threshold.Target to be captured all refers to people usually.

For first kind of way, the number in face recognition technology determination shooting picture (the current picture that can photograph of view finder) can be utilized.Such as, gather the facial image in shooting picture, and count.After collection facial image, count value now is just the number in shooting picture.See Fig. 3, be 50 people for first threshold, because the number in shooting picture is obviously greater than 50 people, therefore determine currently to be in screening-mode of taking a group photo greatly.

The second way, under distant view scape is other, judge whether the edge of shooting picture exists incomplete target to be captured; If the edge of shooting picture exists incomplete target to be captured, then determine currently to be in screening-mode of taking a group photo greatly.

Wherein, scape does not refer to because capture apparatus is different from the distance of target to be captured, and the difference of the range size causing target to be captured to present in shooting picture.Other division of scape generally can be divided into five kinds, by near to being far respectively feature (more than shoulders of human body), close shot (more than human chest), middle scape (more than human knee), panorama (the whole and ambient background of human body), distant view (residing for target to be captured environment).Why determine under distant view scape is other herein, be because only have distant view scape special talent can photograph more target to be captured and environment residing for it, conveniently carry out follow-up judgement.

In the disclosed embodiments, namely the edge of shooting picture, also refer to the edge of the picture that view finder can photograph.See Fig. 4, incomplete target to be captured, refers to the target to be captured that only there is half of face or half of health in shooting picture.When the edge by face recognition technology determination shooting picture exists half of face or half of health, then determine currently to be in screening-mode of taking a group photo greatly.

Whether the third mode, the destination number to be captured judged in shooting picture are greater than first threshold; If the destination number to be captured in shooting picture is greater than first threshold, then judge whether there is target to be captured outside the viewfinder range that shooting picture covers; If there is target to be captured outside the viewfinder range that shooting picture covers, then determine currently to be in screening-mode of taking a group photo greatly.

For the third mode, in order to accurately determine currently whether be in screening-mode of taking a group photo greatly, take two step judgment modes.The first step, first judges whether the number in shooting picture is greater than first threshold; Number in picture to be captured is greater than first threshold, then judge whether also there is the people do not photographed outside the viewfinder range that shooting picture covers.See Fig. 5 a, outside the viewfinder range that shooting picture covers, also comprise the people do not photographed.But because the edge of shooting picture does not now comprise half of face or half of health, therefore, also need the shooting angle of auto-changing capture apparatus.As shown in Figure 5 b, after rotation capture apparatus, the people do not photographed before just containing in shooting picture now.Change outside viewfinder range that face covers due to shooting and also there is target to be captured, therefore determine currently to be in screening-mode of taking a group photo greatly.

It should be noted that, except taking above-mentioned three kinds of modes to determine current whether being in except large group photo screening-mode, other also can be taked to determine mode, and disclosure embodiment does not do concrete restriction to this.

In step 202., the multiframe photographic images of target to be captured in multiple appointment shooting angle is obtained.

In the disclosed embodiments, before obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle, further comprising the steps of 202a is to step 202d.

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

Wherein, the size of the first numerical value can be 1mm or 2mm etc., and disclosure embodiment does not do concrete restriction to the size of the first numerical value.Can be the D coordinates value of capture apparatus in primary importance information, or relative to the rotational angle etc. of the front position of rotation, disclosure embodiment does not do concrete restriction to the form of primary importance information.

In the disclosed embodiments, performing the object of step 202a is to determine under large group photo screening-mode, by be in the leftmost people of horizontal direction be included within the viewfinder range that shooting picture covers time, capture apparatus will rotate how many degree.When controlling capture apparatus and rotating, the interface of finding a view in view finder constantly can convert along with the rotation of capture apparatus, and the shooting picture obtained is also different along with the rotation of capture apparatus.When occurring leftmost people in interface of finding a view, and its facial zone is complete not incomplete, when then the right hand edge line of leftmost people is the first numerical value in left hand edge linear distance first shooting picture at interface of finding a view, controls capture apparatus and stop operating, and record the primary importance information of now capture apparatus.Now, at least there is the full facial region of Far Left target to be captured in the first shooting picture.

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

In the disclosed embodiments, performing the object of step 202a is to determine under large group photo screening-mode, by be in the rightmost people of horizontal direction be included within the viewfinder range that shooting picture covers time, capture apparatus will rotate how many degree.When controlling capture apparatus and rotating, the interface of finding a view in view finder constantly can convert along with the rotation of capture apparatus, and the shooting picture obtained is also different along with the rotation of capture apparatus.When occurring rightmost people in interface of finding a view, and its facial zone is complete not incomplete, when then the right hand edge line of rightmost people is the first numerical value in right hand edge linear distance first shooting picture at interface of finding a view, controls capture apparatus and stop operating, and record the primary importance information of now capture apparatus.Now, at least there is the full facial region of rightmost target to be captured in the first shooting picture.

Step 202c, according to primary importance information and second place information, calculate capture apparatus horizontally rotate angle.

In the disclosed embodiments, after obtaining primary importance information and second place information, according to the numerical value of the two, the target whole to be captured that just can calculate to current participation be taken pictures all is included in last composograph, then capture apparatus at least wants level to rotate how many degree from left to right or from right to left.Be rotate 30 degree relative to initial position (position before not rotating) with primary importance information, second place information is that to rotate 30 degree relative to initial position be example, then the horizontally rotating angle and will reach 60 degree of capture apparatus.

Step 202d, basis horizontally rotate the numerical values recited of angle, determine at least one specified level shooting angle.

In the disclosed embodiments, after obtaining horizontally rotating angle, the number may taken pictures due to current participation is too much, thus it is excessive to cause horizontally rotating angle, therefore also need, according to the size horizontally rotating angle, angle will be horizontally rotated and split, and obtain at least one specified level shooting angle.To horizontally rotate angle split time, when horizontally rotating angular values and being excessive, comparatively repeated segmentation can be carried out by horizontally rotating angle, being such as divided into 5 times or more, obtain at least 5 specified level shooting angle; When horizontally rotating angular values and being less, less segmentation can be carried out by horizontally rotating angle, being such as divided into 3 times or less, obtaining 3 specified level shooting angle at the most.

Wherein, after determining at least one specified level shooting angle, when obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle, following manner can be taked to realize:

The first step, present level shooting angle, continuously after shooting preset number two field picture, according at least one specified level shooting angle, controls capture apparatus and turns to next shooting angle.

Wherein, preset number can be 3 or 4 etc., and disclosure embodiment does not do concrete restriction to the size of preset number.When at least one specified level shooting angle is taken, can take according to order from left to right, also can take according to dextrosinistral order, disclosure embodiment does not do concrete restriction to this.A shooting angle photographs of specifying after preset number two field picture, control capture apparatus and turn to next shooting angle, again carry out the shooting of preset number two field picture.

See Fig. 6 a, carry out being shot for example with order from left to right, then, when present level shooting angle is taken, only can take dotted line with the part in left region target to be captured, dotted line can not be photographed in present level shooting angle with right region.Therefore, the next shooting angle that capture apparatus carries out turning to shown in Fig. 6 b need be controlled, to take in Fig. 6 a dotted line with the target to be captured in right region.

Second step, the object edge to be captured that identification should be taken in next shooting angle.

In the disclosed embodiments, before a shooting angle of specifying is taken, also need first to identify the current object edge to be captured that should take.Why doing like this is because eachly appearing in shooting picture per capita of need ensureing to participate in take pictures, and the shooting picture of different shooting angles does not overlap on a large scale.See Fig. 6 b, after capture apparatus turns to next shooting angle, can according to the image automatic identification obtained in a upper shooting angle the current object edge to be captured that should take, be also defined as object edge to be captured by dotted line.So in next shooting angle, just as shown in Figure 6 b from dotted line with right region take.

3rd step, when after the object edge to be captured determining to take, continuous shooting preset number two field picture in next shooting angle.

In the disclosed embodiments, after determining the current object edge to be captured that should take, just can take continuously from edge, again obtain preset number two field picture.

See Fig. 6 c, the image of top is the panoramic picture participating in the target to be captured of taking pictures.The photographic images of bottom left image for obtaining in the appointment shooting angle shown in Fig. 6 a, the photographic images of bottom right image for obtaining in the appointment shooting angle shown in Fig. 6 b.From Fig. 6 c, the image border of the two overlaps well, and after the two being carried out synthesis process, the composograph obtained is almost consistent with the image of top.Do not miss any one target to be captured, do not occur the target to be captured overlapped yet.

4th step, repeat above-mentioned steps, until complete in each specified level shooting angle photographs.

After repeating the above-mentioned first step to the 3rd step, just can obtain the preset number two field picture in the shooting angle of specifying at each.Also namely, the equal corresponding preset number two field picture of each shooting angle of specifying.

It should be noted that, except being divided into multiple shooting angle in the horizontal direction and repeatedly taking, see Fig. 7, also may there is the large contingent of taking pictures due to current participation, thus divide into many rows when erect-position.And capture apparatus is when taking, being limited to the shooting ability of capture apparatus, each people arranged can not being encompassed in the situation of finding a view in interface.Therefore, disclosure embodiment is also included in the step that vertical direction is repeatedly taken.Refer to following step 202e to step 202h.

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

This step with step 202a in like manner, repeats no more herein.

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

This step with step 202b in like manner, repeats no more herein.

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

This step with step 202c in like manner, repeats no more herein.

Step 202h, numerical values recited according to vertical rotation angle, determine that at least one specifies vertical shooting angle.

This step with step 202d in like manner, repeats no more herein.

Wherein, determining after at least one specifies vertical shooting angle, when obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle, following manner can taked to realize:

The first step, current vertical shooting angle, continuously after shooting preset number two field picture, is specified vertical shooting angle according at least one, controlled capture apparatus and turn to next shooting angle.

This process is identical with above-mentioned principle of carrying out taking in specified level shooting angle, repeats no more herein.

4th step, repeat above-mentioned steps, until specify vertical shooting angle photographs complete at each.

It should be noted that, specify shooting angle can refer to specified level shooting angle, also can refer to and specify vertical shooting angle, also can refer to horizontal shooting angle and vertical shooting angle, disclosure embodiment does not do concrete restriction to this, and disclosure embodiment is only to specify shooting angle to be illustrated for specified level shooting angle.

In addition, when carrying out image taking, also can judge whether the eyes of each target to be captured in current taken image are all in the state of opening according to image recognition technology in real time; If so, then subsequent treatment is proceeded; If not, then proceed shooting, until take successfully, detailed process is as follows:

Shooting angle is specified for each, judges to specify the eyes whether comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening; If specify the eyes not comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening, then control capture apparatus and re-start shooting, until specify the eyes comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening.

In step 203, Eye states recognition process is carried out to multiframe photographic images, obtains recognition result.

Wherein, multiframe photographic images is included in each and specifies the preset number two field picture that shooting angle obtains.Eye state comprises the state of opening and closure state.

In the disclosed embodiments, before Eye states recognition process is carried out to multiframe photographic images, training pattern can be set up by off-line in advance.Also namely, collect a large amount of face sample datas in advance, and analyzing and processing is carried out to a large amount of face sample datas, obtain training pattern.After obtaining multiframe photographic images, just can determine the eye state of each target to be captured in each two field picture according to this training pattern, obtain recognition result.

In step 204, according to recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state.

In the disclosed embodiments, preset number frame photographic images is all have taken owing to specifying in shooting angle at each, and specify each two field picture in shooting angle all to carry out Eye states recognition process to each, so can according to recognition result, specify at each and shooting angle chooses an eyeball of opening one's eyes and be in the minimum appointment image of the destination number to be captured of closure state.Also namely, each shooting angle is chosen the image that a frame eye closing number is minimum.There are how many to specify shooting angle, just can obtain how many frame and specify image.

In step 205, specify in image in multiframe and select eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image.

In the disclosed embodiments, after obtaining multiframe appointment image, all may there is difference in the number of specifying eyes in image to be in closure state due to each frame, for and follow-up carry out Images uniting process time, workload can be reduced as much as possible, also need specify in image in multiframe and choose synthesis primary image.When choosing synthesis primary image, if each frame is specified in image all contain whole targets to be captured, then direct eyes of choosing in multiple image are in the minimum image of the number of closure state, it can be used as synthesis primary image.If all comprise part target to be captured in each two field picture, then multiframe specified image to carry out splicing, obtain synthesizing primary image.Wherein, when objective eye to be captured is in closure state, the image photographed as shown in Figure 8.

In step 206, in synthesis primary image, Eye states recognition process is carried out to synthesis primary image, obtains the appointment photographic subjects that eyes are in closure state.

In the disclosed embodiments, after obtaining synthesis primary image, need first to carry out Eye states recognition process according to the recognition methods shown in above-mentioned steps 203 to synthesis primary image, determine to synthesize eyes in primary image and be in the appointment photographic subjects of closure state.So that in subsequent process, facial zone eyes in synthesis primary image being in the appointment photographic subjects of closure state is replaced.

In step 207, in the multiframe photographic images except synthesis primary image, the facial zone of specifying the eyes of photographic subjects to be in the state of opening is chosen.

In the disclosed embodiments, when the eyes choosing appointment photographic subjects are in the facial zone of the state of opening, both can have specified in image in multiframe and choose, also can choose in multiframe photographic images.When including whole target to be captured in each frame appointment image, can specify image from multiframe the facial zone chosen and specify the eyes of photographic subjects to be in the state of opening.When each frame specify in image include part target to be captured time, the facial zone of specifying the eyes of photographic subjects to be in the state of opening can be chosen from multiframe photographic images.Disclosure embodiment does not do concrete restriction to this.

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

In the disclosed embodiments, when synthesis primary image is synthesized with the facial zone of specifying the eyes of photographic subjects to be in the state of opening, the facial zone of specifying the eyes of photographic subjects to be in closure state in synthesis primary image can be removed, and the facial zone eyes of the appointment photographic subjects chosen being in the state of opening is filled into the corresponding region in synthesis primary image, and then obtain composograph.

It should be noted that, when performing the method that disclosure embodiment provides, above-mentioned steps 203 to step 208 also can by following step 210 and step 211 replace.Step 210 and step 211 as follows.

In step 210, in multiframe photographic images, determine that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening.

When determining that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening, the RM in above-mentioned steps 203 can be taked to process, repeat no more herein.

In step 211, if each eye of specifying shooting angle to comprise each target to be captured of a frame is all in the image of the state of opening, then specifies image corresponding to shooting angle to carry out synthesis process to each, obtain composograph.

In the disclosed embodiments, if each frame is specified in image and has been included whole targets to be captured, then after determining that each specifies shooting angle eyes of comprising each target to be captured of a frame to be all in the image of the state of opening, can using image corresponding for arbitrary appointment shooting angle as composograph.In addition, if each frame is specified in image included whole targets to be captured, then can determine any one specify shooting angle comprise each target to be captured of a frame be all in the image of the state of opening time, directly this image is defined as composograph.If each frame is specified in image included the target to be captured of part, then each specifies image corresponding to shooting angle to carry out splicing, obtains composograph.

It should be noted that, when performing the method that disclosure embodiment provides, after above-mentioned steps 210, also can comprise the steps 212.

In the step 212, if each eye of specifying shooting angle to comprise each target to be captured of multiframe is all in the appointment image of the state of opening, then specify in image in multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the image corresponding to each shooting angle carries out synthesis process, obtains composograph.

In the disclosed embodiments, if each frame is specified in image and has been included whole targets to be captured, then after determining that each specifies shooting angle eyes of comprising each target to be captured of multiframe to be all in the image of the state of opening, the image that the target data to be captured that is in smile state is maximum can be chosen in this multiple image, and it can be used as composograph.In addition, if each frame is specified in image and has been included whole targets to be captured, then can determine any one specify shooting angle comprise each target to be captured of multiframe be all in the image of the state of opening time, directly choose the image that the target to be captured that this appointment shooting angle is in smile state is maximum, and be defined as composograph.Image after synthesis can be as shown in Figure 9.If each frame is specified in image included the target to be captured of part, then determining that eyes that each specifies shooting angle to comprise each target to be captured of multiframe are all in the appointment image of the state of opening, then at the image that each specifies multiframe corresponding to shooting angle to specify in image to choose the target numbers to be captured that is in smile state maximum, and synthesis process is carried out to the image chosen in each shooting angle, obtain composograph as shown in Figure 9.

Figure 10 is the block diagram of a kind of image processing apparatus according to an exemplary embodiment.With reference to Figure 10, this device comprises screening-mode determination module 1001, photographic images acquisition module 1002, photographic images identification module 1003, specifies image to choose module 1004, Images uniting processing module 1005.

Wherein, screening-mode determination module 1001, is currently in screening-mode of taking a group photo greatly for determining; Photographic images acquisition module 1002 is connected with screening-mode determination module 1001, for obtaining the multiframe photographic images of target to be captured in multiple appointment shooting angle; Photographic images identification module 1003 is connected with photographic images acquisition module 1002, for carrying out Eye states recognition process to multiframe photographic images, obtains recognition result; Specify image to choose module 1004 to be connected with photographic images identification module 1003, for according to recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Images uniting processing module 1005 is chosen module 1004 with appointment image and is connected, and for specifying image to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening.

Alternatively, screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in shooting picture is greater than first threshold, determine currently to be in screening-mode of taking a group photo greatly; Or, under distant view scape is other, judge whether the edge of shooting picture exists incomplete target to be captured; When the edge of shooting picture exists incomplete target to be captured, determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in shooting picture is greater than first threshold, judge whether there is target to be captured outside the viewfinder range that shooting picture covers; When there is target to be captured outside the viewfinder range that shooting picture covers, determine currently to be in screening-mode of taking a group photo greatly.

Alternatively, this device also comprises:

First control module, rotates for controlling capture apparatus, until the distance of Far Left target to be captured is the first numerical value in the left hand edge line at interface of finding a view and the first shooting picture, and the primary importance information of records photographing equipment;

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

First rotational angle computing module, for according to primary importance information and second place information, what calculate capture apparatus horizontally rotates angle;

First shooting angle determination module, for according to the numerical values recited horizontally rotating angle, determines at least one specified level shooting angle.

Alternatively, photographic images acquisition module, after take preset number two field picture continuously in present level shooting angle, according at least one specified level shooting angle, controls capture apparatus and turns to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until complete in each specified level shooting angle photographs.

Alternatively, this device also comprises:

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

Second control module, rotates for controlling capture apparatus, until in the lower limb line at interface of finding a view and the 4th shooting picture bottom the distance of target to be captured be the first numerical value, 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, calculates the vertical rotation angle of capture apparatus;

Second shooting angle determination module, for the numerical values recited according to vertical rotation angle, determines that at least one specifies vertical shooting angle.

Alternatively, photographic images acquisition module, after take preset number two field picture continuously in current vertical shooting angle, specifies vertical shooting angle according at least one, controls capture apparatus and turns to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until specify vertical shooting angle photographs complete at each.

Alternatively, Images uniting processing module, in multiframe photographic images, determines that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening; When the eyes comprising each target to be captured of a frame are all in the image of the state of opening, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Alternatively, Images uniting processing module, time also for being all in the appointment image of the state of opening when the eyes comprising each target to be captured of multiframe, specify in image in multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

Alternatively, Images uniting processing module, selects eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image for specifying in image in multiframe; In synthesis primary image, Eye states recognition process is carried out to synthesis primary image, obtains the appointment photographic subjects that eyes are in closure state; In the multiframe photographic images except synthesis primary image, choose the facial zone of specifying the eyes of photographic subjects to be in the state of opening; Synthesis primary image and facial zone are synthesized, obtains composograph.

Alternatively, this device also comprises:

Specifying image judge module, for specifying shooting angle for each, judging to specify the eyes whether comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening;

3rd control module, for when specifying the eyes not comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening, control capture apparatus and re-start shooting, until specify the eyes comprising each target to be captured at least one frame photographic images corresponding to shooting angle to be all in the appointment image of the state of opening.

The device that disclosure embodiment provides, determine current be in large group photo screening-mode after, obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle, and Eye states recognition process is carried out to described multiframe photographic images, according to the recognition result obtained, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Afterwards, image is specified to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening, due under large group photo screening-mode, can automatically process the target to be captured that eyes in photographic images are in closure state, thus obtain the composograph that each target to be captured is all in eyes-open state, therefore image processing operations is comparatively intelligent and easy, saves manpower and image processing time.

About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.

Figure 11 is the block diagram of a kind of equipment 1100 for image procossing according to an exemplary embodiment.Such as, equipment 1100 can be mobile phone, digital broadcast terminal, flat-panel devices, personal digital assistant etc.

With reference to Figure 11, equipment 1100 can comprise following one or more assembly: processing components 1102, memory 1104, power supply module 1106, multimedia groupware 1108, audio-frequency assembly 1110, I/O (Input/Output, I/O) interface 1112, sensor cluster 1114, and communications component 1116.

The integrated operation of the usual control appliance 1100 of processing components 1102, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 1102 can comprise one or more processor 1120 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 1102 can comprise one or more module, and what be convenient between processing components 1102 and other assemblies is mutual.Such as, processing components 1102 can comprise multi-media module, mutual with what facilitate between multimedia groupware 1108 and processing components 1102.

Memory 1104 is configured to store various types of data to be supported in the operation of equipment 1100.The example of these data comprises for any application program of operation on equipment 1100 or the instruction of method, contact data, telephone book data, message, picture, video etc.Memory 1104 can be realized by the volatibility of any type or non-volatile memory device or their combination, as SRAM (Static Random Access Memory, static RAM), EEPROM (Electrically-Erasable Programmable Read-Only Memory, Electrically Erasable Read Only Memory), EPROM (Erasable Programmable Read Only Memory, Erasable Programmable Read Only Memory EPROM), PROM (Programmable Read-Only Memory, programmable read only memory), ROM (Read-Only Memory, read-only memory), magnetic memory, flash memory, disk or CD.

The various assemblies that power supply module 1106 is equipment 1100 provide electric power.Power supply module 1106 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for equipment 1100 and be associated.

Multimedia groupware 1108 is included in the screen providing an output interface between described equipment 1100 and user.In certain embodiments, screen can comprise LCD (Liquid Crystal Display, liquid crystal display) and TP (Touch Panel, touch panel).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 1108 comprises a front-facing camera and/or post-positioned pick-up head.When equipment 1100 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.

Audio-frequency assembly 1110 is configured to export and/or input audio signal.Such as, audio-frequency assembly 1110 comprises a MIC (Microphone, microphone), and when equipment 1100 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The audio signal received can be stored in memory 1104 further or be sent via communications component 1116.In certain embodiments, audio-frequency assembly 1110 also comprises a loud speaker, for output audio signal.

I/O interface 1112 is for providing interface between processing components 1102 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.

Sensor cluster 1114 comprises one or more transducer, for providing the state estimation of various aspects for equipment 1100.Such as, sensor cluster 1114 can detect the opening/closing state of equipment 1100, the relative positioning of assembly, such as assembly is display and the keypad of equipment 1100, the position of all right checkout equipment 1100 of sensor cluster 1114 or equipment 1100 assemblies changes, the presence or absence that user contacts with equipment 1100, the variations in temperature of equipment 1100 orientation or acceleration/deceleration and equipment 1100.Sensor cluster 1114 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor cluster 1114 can also comprise optical sensor, as CMOS (Complementary Metal Oxide Semiconductor, CMOS (Complementary Metal Oxide Semiconductor)) or CCD (Charge-coupled Device, charge coupled cell) imageing sensor, for using in imaging applications.In certain embodiments, this sensor cluster 1114 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.

Communications component 1116 is configured to the communication of wired or wireless mode between equipment of being convenient to 1100 and other equipment.Equipment 1100 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communications component 1116 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communications component 1116 also comprises NFC (Near Field Communication, near-field communication) module, to promote junction service.Such as, can based on RFID (Radio Frequency Identification in NFC module, radio-frequency (RF) identification) technology, IrDA (Infra-red Data Association, Infrared Data Association) technology, UWB (Ultra Wideband, ultra broadband) technology, BT (Bluetooth, bluetooth) technology and other technologies realize.

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

In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the memory 1104 of instruction, above-mentioned instruction can perform said method by the processor 1120 of equipment 1100.Such as, described non-transitory computer-readable recording medium can be ROM, RAM (Random Access Memory, random access memory), CD-ROM (Compact Disc Read-Only Memory, compact disc read-only memory), tape, floppy disk and optical data storage devices etc.

A kind of non-transitory computer-readable recording medium, when the instruction in storage medium is performed by the processor of mobile terminal, make mobile terminal can perform a kind of image processing method, the method comprises:

Determine currently to be in screening-mode of taking a group photo greatly;

Eye states recognition process is carried out to multiframe photographic images, obtains recognition result;

According to recognition result, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state;

Next shooting angle identifies the object edge to be captured that should take;

If each eye of specifying shooting angle to comprise each target to be captured of a frame is all in the image of the state of opening, then specifies image corresponding to shooting angle to carry out synthesis process to each, obtain composograph.

If each eye of specifying shooting angle to comprise each target to be captured of multiframe is all in the appointment image of the state of opening, then specify in image in multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the image corresponding to each shooting angle carries out synthesis process, obtains composograph.

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

The non-transitory computer-readable recording medium that disclosure embodiment provides, determine current be in large group photo screening-mode after, obtain the multiframe photographic images of target to be captured in multiple appointment shooting angle, and Eye states recognition process is carried out to described multiframe photographic images, according to the recognition result obtained, specify at least one frame photographic images corresponding to shooting angle at each, choose eyes and be in the minimum appointment image of the destination number to be captured of closure state; Afterwards, image is specified to carry out synthesis process to multiframe, the eyes obtaining each target to be captured are all in the composograph of the state of opening, due under large group photo screening-mode, can automatically process the target to be captured that eyes in photographic images are in closure state, thus obtain the composograph that each target to be captured is all in eyes-open state, therefore image processing operations is comparatively intelligent and easy, saves manpower and image processing time.

Those skilled in the art, at consideration specification and after putting into practice invention disclosed herein, will easily expect other embodiment of the present invention.The application is intended to contain any modification of the present invention, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present invention and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Specification and embodiment are only regarded as exemplary, and true scope of the present invention and spirit are pointed out by claim below.

Should be understood that, the present invention is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.Scope of the present invention is only limited by appended claim.

Claims

1. an image processing method, is characterized in that, described method comprises:

Determine currently to be in screening-mode of taking a group photo greatly;

2. method according to claim 1, is characterized in that, describedly determines currently to be in screening-mode of taking a group photo greatly, comprising:

3. method according to claim 1, is characterized in that, describedly determines currently to be in screening-mode of taking a group photo greatly, comprising:

4. method according to claim 1, is characterized in that, before the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, described method also comprises:

5. method according to claim 4, is characterized in that, the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, comprising:

Next shooting angle identifies the object edge to be captured that should take;

6. method according to claim 1, is characterized in that, before the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, described method also comprises:

7. method according to claim 6, is characterized in that, the multiframe photographic images of described acquisition target to be captured in multiple appointment shooting angle, comprising:

Next shooting angle identifies the object edge to be captured that should take;

8. the method according to claim arbitrary in claim 1 to 7, is characterized in that, described to multiframe specify image carry out synthesis process, the eyes obtaining each target to be captured are all in the composograph of the state of opening, and comprising:

9. method according to claim 8, is characterized in that, after the described eyes determining whether each appointment shooting angle comprises each target to be captured are all in the image of the state of opening, described method also comprises:

10. the method according to claim arbitrary in claim 1 to 7, is characterized in that, described to multiframe specify image carry out synthesis process, the eyes obtaining each target to be captured are all in the composograph of the state of opening, and comprising:

11. methods according to claim 1, is characterized in that, describedly specify at least one frame photographic images corresponding to shooting angle at each, and choose after eyes are in the minimum appointment image of the destination number to be captured of closure state, described method also comprises:

12. 1 kinds of image processing apparatus, is characterized in that, described device comprises:

13. devices according to claim 12, is characterized in that, described screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in described shooting picture is greater than described first threshold, determine currently to be in screening-mode of taking a group photo greatly; Or, under distant view scape is other, judge whether the edge of described shooting picture exists incomplete target to be captured; When the edge of described shooting picture exists incomplete target to be captured, determine currently to be in screening-mode of taking a group photo greatly.

14. devices according to claim 12, is characterized in that, described screening-mode determination module, for judging whether the destination number to be captured in shooting picture is greater than first threshold; When the destination number to be captured in described shooting picture is greater than described first threshold, judge whether there is target to be captured outside the viewfinder range that described shooting picture covers; When there is target to be captured outside the viewfinder range that described shooting picture covers, determine currently to be in screening-mode of taking a group photo greatly.

15. devices according to claim 12, is characterized in that, described device also comprises:

16. devices according to claim 15, it is characterized in that, described photographic images acquisition module, after take preset number two field picture continuously in present level shooting angle, according at least one specified level shooting angle described, control described capture apparatus and turn to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, described next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until complete in each specified level shooting angle photographs.

17. devices according to claim 12, is characterized in that, described device also comprises:

18. devices according to claim 17, it is characterized in that, described photographic images acquisition module, after take preset number two field picture continuously in current vertical shooting angle, according to described at least one specify vertical shooting angle, control described capture apparatus and turn to next shooting angle; Next shooting angle identifies the object edge to be captured that should take; When after the object edge to be captured determining to take, described next shooting angle takes preset number two field picture continuously; Repeat above-mentioned steps, until specify vertical shooting angle photographs complete at each.

19. according to claim 12 to the device described in arbitrary claim in 18, it is characterized in that, described Images uniting processing module, in described multiframe photographic images, determines that each specifies the eyes whether shooting angle comprising each target to be captured to be all in the image of the state of opening; When the eyes comprising each target to be captured of a frame are all in the image of the state of opening, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

20. devices according to claim 19, it is characterized in that, described Images uniting processing module, time also for being all in the appointment image of the state of opening when the eyes comprising each target to be captured of multiframe, specify in image in described multiframe and choose the maximum image of the target numbers to be captured that is in smile state, the described image corresponding to each shooting angle carries out synthesis process, obtains described composograph.

21. according to claim 12 to the device described in arbitrary claim in 18, it is characterized in that, described Images uniting processing module, selects eyes to be in the minimum image of the destination number to be captured of closure state as synthesis primary image for specifying in image in described multiframe; In described synthesis primary image, Eye states recognition process is carried out to described synthesis primary image, obtain the appointment photographic subjects that eyes are in closure state; In the multiframe photographic images except synthesis primary image, the eyes choosing described appointment photographic subjects are in the facial zone of the state of opening; Described synthesis primary image and described facial zone are synthesized, obtains described composograph.

22. devices according to claim 12, is characterized in that, described device also comprises:

23. 1 kinds of image processing equipments, is characterized in that, described equipment comprises:

Processor;

For the memory of storage of processor executable instruction;