CN108513069A

CN108513069A - Image processing method, device, storage medium and electronic equipment

Info

Publication number: CN108513069A
Application number: CN201810276764.1A
Authority: CN
Inventors: 何新兰
Original assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Current assignee: Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date: 2018-03-30
Filing date: 2018-03-30
Publication date: 2018-09-07
Anticipated expiration: 2038-03-30
Also published as: CN108513069B

Abstract

The embodiment of the present application discloses a kind of image processing method, device, storage medium and electronic equipment, wherein the embodiment of the present application obtains synchronous acquisition, Same Scene focal length scene image and wide-angle scene image first；Then recognition of face is carried out to focal length scene image, obtains the face characteristic of focal length scene image；The face characteristic of focal length scene image and wide-angle scene image are bound again；The finally face characteristic bound in wide-angle scene image carries out default processing to wide-angle scene image.When this programme is applied to remote portrait or more people group photo, can be small by viewfinder range but focal length scene image that portrait accounting is larger extract the face characteristic of personage in scene to be captured, it is later that the face characteristic extracted and viewfinder range is big but portrait accounts for smaller wide-angle scene image, for handling the wide-angle scene image, so as to overcome the problems, such as that face characteristic extraction is difficult, achieve the purpose that improve image procossing accuracy.

Description

Image processing method, device, storage medium and electronic equipment

Technical field

This application involves technical field of image processing, and in particular to a kind of image processing method, device, storage medium and electricity Sub- equipment.

Background technology

Such as mobile phone electronic equipment is usually that user is provided with camera function, at the hardware such as camera module and image Adjustment method is constantly progressive, and the shooting function of electronic equipment is also stronger and stronger, and user is also more and more continually set using electronics It is standby to take pictures.

Currently, electronic equipment still further provides image processing function other than providing the camera function on basis, than Such as, the face in image can be beautified and be modified.And it is the people recognized in image to realize the premise of image procossing Face feature, still, electronic equipment are shot in the personage farther out that adjusts the distance, or when carrying out more people group photo, and shooting obtains Image in face can be smaller, it is difficult to accurately extract face characteristic, influence subsequently to the image carry out image procossing standard Exactness.

Invention content

The embodiment of the present application provides a kind of image processing method, device, storage medium and electronic equipment, can improve figure As the accuracy of processing.

In a first aspect, a kind of image processing method for providing of the embodiment of the present application, including：

Obtain synchronous acquisition, Same Scene focal length scene image and wide-angle scene image；

Recognition of face is carried out to the focal length scene image, obtains the face characteristic of the focal length scene image；

The face characteristic and the wide-angle scene image are bound；

According to the face characteristic bound in the wide-angle scene image, default processing is carried out to the wide-angle scene image.

Second aspect, a kind of image processing apparatus for providing of the embodiment of the present application, including：

Image collection module, for obtaining synchronous acquisition, Same Scene focal length scene image and wide-angle scene figure Picture；

Picture recognition module obtains the focal length scene image for carrying out recognition of face to the focal length scene image Face characteristic；

Feature binding module, for binding the face characteristic and the wide-angle scene image；

Image processing module, for the face characteristic bound in the wide-angle scene image, to the wide-angle scene Image carries out default processing.

The third aspect, storage medium provided by the embodiments of the present application, is stored thereon with computer program, when the computer When program is run on computers so that the computer executes the image processing method provided such as the application any embodiment.

Fourth aspect, the embodiment of the present application provides a kind of electronic equipment, including central processing unit and memory, described to deposit Reservoir has computer program, and the central processing unit is by calling the computer program, for executing such as any reality of the application The image processing method of example offer is provided.

The embodiment of the present application obtains synchronous acquisition, Same Scene focal length scene image and wide-angle scene figure first Picture；Then recognition of face is carried out to focal length scene image, obtains the face characteristic of focal length scene image；Again by focal length scene image Face characteristic and wide-angle scene image bind；The finally face characteristic bound in wide-angle scene image, to wide-angle scene Image carries out default processing.Technical solution provided by the embodiments of the present application is applied to remote portrait or more people close When shadow, can be small by viewfinder range but focal length scene image that portrait accounting is larger extract the people of personage in scene to be captured Face feature, it is later that the face characteristic extracted and viewfinder range is big but portrait accounts for smaller wide-angle scene image, for pair The wide-angle scene image is handled, and so as to overcome the problems, such as that face characteristic extraction is difficult, it is accurate to reach raising image procossing The purpose of degree.

Description of the drawings

In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some embodiments of the present application, for For those skilled in the art, without creative efforts, it can also be obtained according to these attached drawings other attached Figure.

Fig. 1 is a flow diagram of image processing method provided by the embodiments of the present application.

Fig. 2 is the installation position schematic diagram of focal length camera and wide-angle camera in the embodiment of the present application.

Fig. 3 is the focal length scene image and wide-angle scene image that scene to be captured is collected in the embodiment of the present application Exemplary plot.

Fig. 4 is a kind of operation chart of binding face characteristic in the embodiment of the present application.

Fig. 5 is the operation chart of another binding face characteristic in the embodiment of the present application.

Fig. 6 is the schematic diagram for determining pending image in the embodiment of the present application from multiple wide-angle scene images.

Fig. 7 is the operation chart for determining pending face image in the embodiment of the present application from pending image.

Fig. 8 is the operation chart for obtaining target face image in the embodiment of the present application from other wide-angle scene images.

Fig. 9 is a kind of operation signal that pending face image is replaced with to target face image in the embodiment of the present application Figure.

Figure 10 is the operation chart for obtaining target face image in the embodiment of the present application from face image library.

Figure 11 is that pending face image is replaced with the operation of target face image and shows by another kind in the embodiment of the present application It is intended to.

Figure 12 is the operation chart for obtaining target face image in the embodiment of the present application from target electronic device.

Figure 13 is another flow diagram of the image processing method provided in the embodiment of the present application.

Figure 14 is a structural schematic diagram of image processing apparatus provided by the embodiments of the present application.

Figure 15 is a structural schematic diagram of electronic equipment provided by the embodiments of the present application.

Figure 16 is another structural schematic diagram of electronic equipment provided by the embodiments of the present application.

Figure 17 is a refinement structural schematic diagram of image processing circuit in the embodiment of the present application.

Figure 18 is another refinement structural schematic diagram of image processing circuit in the embodiment of the present application.

Specific implementation mode

Schema is please referred to, wherein identical component symbol represents identical component, the principle of the application is to implement one It is illustrated in computing environment appropriate.The following description be based on illustrated by the application specific embodiment, should not be by It is considered as limitation the application other specific embodiments not detailed herein.

In the following description, the specific embodiment of the application will be with reference to by the step performed by one or multi-section computer And symbol illustrates, unless otherwise stating clearly.Therefore, these steps and operation will have to mention for several times is executed by computer, this paper institutes The computer execution of finger includes by representing with the computer processing unit of the electronic signal of the data in a structuring pattern Operation.This operation is converted at the data or the position being maintained in the memory system of the computer, reconfigurable Or in addition change the running of the computer in a manner of known to the tester of this field.The data structure that the data are maintained For the provider location of the memory, there is the specific feature defined in the data format.But the application principle is with above-mentioned text Word illustrates that be not represented as a kind of limitation, this field tester will appreciate that plurality of step as described below and behaviour Also it may be implemented in hardware.

Term as used herein " module " can regard the software object to be executed in the arithmetic system as.It is as described herein Different components, module, engine and service can be regarded as the objective for implementation in the arithmetic system.And device as described herein and side Method can be implemented in the form of software, can also be implemented on hardware certainly, within the application protection domain.

Term " first ", " second " and " third " in the application etc. is for distinguishing different objects, rather than for retouching State particular order.In addition, term " comprising " and " having " and their any deformations, it is intended that cover and non-exclusive include. Such as contain the step of process, method, system, product or the equipment of series of steps or module is not limited to list or Module, but some embodiments further include the steps that do not list or module or some embodiments further include for these processes, Method, product or equipment intrinsic other steps or module.

Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and Implicitly understand, embodiment described herein can be combined with other embodiments.

The embodiment of the present application provides a kind of image processing method, and the executive agent of the image processing method can be the application The image processing apparatus that embodiment provides, or it is integrated with the electronic equipment of the image processing apparatus, wherein the image procossing fills It sets and the mode of hardware or software may be used realizes.Wherein, electronic equipment can be smart mobile phone, tablet computer, palm electricity The equipment such as brain, laptop or desktop computer.

Fig. 1 is please referred to, Fig. 1 is the flow diagram of image processing method provided by the embodiments of the present application.The application is implemented The detailed process for the image processing method that example provides can be as follows：

In a step 101, focal length scene image that obtain synchronous acquisition, Same Scene and wide-angle scene image.

Fig. 2 is please referred to, in the embodiment of the present application, electronic equipment includes focal length camera and wide-angle camera, such as Fig. 2 institutes In a kind of set-up mode shown, focal length camera and wide-angle camera horizontal alignment are set to the same plane of electronic equipment, and There is a certain distance between focal length camera and wide-angle camera.In addition, electronic equipment is configured with focal length image buffer storage queue With wide angle picture buffer queue, wherein the queue of focal length image buffer storage is for caching focal length camera the image collected, wide-angle figure As buffer queue is for caching wide-angle camera the image collected.It should be noted that in the specific implementation, focal length camera It can be according to actual needs configured by those skilled in the art with the set-up mode of wide-angle camera.

In the embodiment of the present application, electronic equipment is taken pictures in startup after class application, by synchronous averaging focal length camera and extensively Angle camera, and the image of focal length camera and wide-angle camera according to identical frame per second synchronous acquisition scene to be captured is controlled, Respectively obtain the focal length scene image and wide-angle scene image of scene to be captured.Wherein, focal length camera is by collected focal length Scene image is stored in focal length image buffer storage queue, and wide-angle camera delays collected wide-angle scene image deposit wide angle picture It deposits in queue.

For example, please refer to Fig. 3, in scene to be captured shown in Fig. 3, including penta 3 differences of personage third, personage's fourth and personage Personage, at certain acquisition moment, electronic equipment collects the focal length scene image of the scene to be captured by focal length camera, leads to Cross the wide-angle scene image that wide-angle camera collects the scene to be captured, it is clear that, the portrait in focal length scene image Relative to the portrait bigger in wide-angle scene image, it is easier to recognize.

In the embodiment of the present application, electronic equipment is in the image taking request for receiving triggering, from focal length scene image team In row and wide-angle scene image queue, focal length camera and wide-angle camera synchronous acquisition, Same Scene are extracted respectively Focal length scene image and wide-angle scene image.

Optionally, in one embodiment, focal length scene image that obtain synchronous acquisition, Same Scene and wide-angle scene Image may include：

Multiple focal length scene images and wide-angle scene image of the acquisition of acquisition timing synchronization, Same Scene are obtained, are obtained To focal length scene image set and wide-angle scene image collection.

Wherein, wide-angle field in the number of focal length scene image and wide-angle scene image collection in focal length scene image set The number of scape image is identical.The target number for obtaining focal length scene image/wide-angle focal length image can be according to focal length camera/wide The frame per second information of angle camera is determined.

Specifically, electronic equipment obtains focal length camera/wide-angle and takes the photograph first in the image taking request for receiving triggering As the frame per second information of head, wherein frame per second information is acquired within the unit interval and shown up for describing focal length camera/wide-angle camera The number of scape image illustrates focal length camera acquisition field to be captured per second for example, when the frame per second information got is 30fps 30 focal length scene images of scape, 30 wide-angle scene images of wide-angle camera acquisition scene to be captured per second；For another example, exist When the frame per second information got is 15fps, illustrate 15 focal length scene images of focal length camera acquisition scene to be captured per second, 15 wide-angle scene images of wide-angle camera acquisition scene to be captured per second.

Wherein, the main reason for influencing focal length camera/wide-angle camera frame per second information is environmental light brightness, works as ambient light When brightness higher (electronic equipment is in light environment in other words), focal length camera/wide-angle camera can be in the shorter time Interior (such as 30ms) completes exposure, so that it can acquire scene image with higher frame per second；And when environmental light brightness is relatively low When (electronic equipment is in half-light environment in other words), focal length camera/wide-angle camera needs to spend longer time (such as 40ms-60ms, or more) complete to expose, so that it is only capable of acquiring scene image with lower frame per second.

Later, according to the frame per second information of focal length camera/wide-angle camera, the target of the corresponding frame per second information is determined Number, wherein target number and frame per second information can be proportional, for example, the frame per second in focal length camera/wide-angle camera is believed Breath is 30fps, it may be determined that target number is 8, can be with when the frame per second information of focal length camera/wide-angle camera is 15fps Determine that target number is 6.

After determining target number, from the queue of focal length image buffer storage and wide angle picture buffer queue extracting quantity is The focal length scene image and wide-angle scene image of target number, wherein the focal length at acquisition moment identical (synchronous acquisition in other words) One image group of scene image and wide-angle scene image construction, is obtained the image group of target number.

For example, determine target number be " 4 " when, extracted from focal length image buffer storage queue acquisition the moment be respectively 4 focal length scene images of t1, t2, t3 and t4, extracted from wide angle picture buffer queue acquisition the moment be respectively t1, 4 wide-angle scene images of t2, t3 and t4, will obtain 4 image groups in this way, respectively corresponding acquisition moment t1, t2, t3 and t4。

In a step 102, recognition of face is carried out to the focal length scene image got, obtains the face of focal length scene image Feature；

In the embodiment of the present application, when the focal length scene image got is multiple, then multiple length to getting respectively Burnt scene image carries out recognition of face；When getting focal length scene image and being only one, then a focal length field to getting Scape image carries out recognition of face.

Wherein, for face characteristic for describing the face image that focal length scene image is included, including but not limited to face is big Small, eyes opening degree and expression type (such as anger is detested, is frightened, is glad, is sad and startled) etc..

It should be noted that for which kind of face recognition technology to carry out recognition of face the application to focal length scene image using Embodiment is not particularly limited this, and those skilled in the art can select suitable face recognition technology according to actual needs.

In step 103, the face characteristic of focal length scene image and wide-angle scene image are bound；

Wherein, it after completing the recognition of face to getting focal length scene image, will be identified from focal length scene image To face characteristic with its acquire the moment identical wide-angle scene image bind.

For example, please referring to Fig. 4, focal length scene image and wide-angle focal length image that the acquisition moment is t1 are got, later, from The face characteristic and acquisition moment that identifies face characteristic in the focal length scene image that the acquisition moment is t1, and will identify that are same It is bound for the wide-angle scene image of t1, the face characteristic as the wide-angle scene image.

For another example, Fig. 5 is please referred to, 4 image groups that the acquisition moment is respectively t1, t2, t3 and t4 are got, later, When the face characteristic 1 that identifies face characteristic 1 from the focal length scene image that the acquisition moment is t1, and will identify that is with acquisition Quarter is all the wide-angle scene image binding of t1, face characteristic 2 is identified from the focal length scene image that the acquisition moment is t2, and will The face characteristic 2 identified is bound with the wide-angle scene image that the acquisition moment is all t2, from the focal length field that the acquisition moment is t3 The face characteristic 3 that identifies face characteristic 3 in scape image, and will identify that and the wide-angle scene image that the acquisition moment is all t3 Binding, from the focal length scene image that the acquisition moment is t4 the face characteristic 4 that identifies face characteristic 4, and will identify that with The acquisition moment is all the wide-angle scene image binding of t4.

At step 104, the face characteristic bound in wide-angle scene image carries out default place to wide-angle scene image Reason.

In the embodiment of the present application, after the binding for completing face characteristic, further according to bound in wide-angle scene image Face characteristic, default processing is carried out to wide-angle scene image.It can obtained specifically, in an optional embodiment When the wide-angle scene image arrived is multiple, according to the face characteristic bound in wide-angle scene image, wide-angle scene image is carried out Default processing, including：

According to the face characteristic bound in each wide-angle scene image, determine it is including in each wide-angle scene image, meet it is pre- If the number of the matching face image of condition；

To include to match the largest number of wide-angle scene images of face image as pending image；

According to the face characteristic bound in pending image, default processing is carried out to pending image.

Wherein, preset condition can be configured according to actual photographed demand, for example, when carrying out more people's group photos, if desired Everybody all startled expression is shot, then can be configured preset condition to " expression type is startled "；For another example, more people's conjunctions are being carried out When shadow, if desired shoot the expression that everybody opens eyes and smiles, then can configure default face feature to " expression type is to smile, And open eyes ".

For example, please referring to Fig. 6,4 wide-angle scene images are got altogether, respectively：Wide-angle scene image A, wide-angle scene Image B, wide-angle scene image C and wide-angle scene image D are wrapped in the scene to be captured corresponding to this 4 wide-angle scene images Penta 3 different personages of the third fourth are included, and preset condition is configured as " expression is to laugh ", it is each according to this 4 wide-angle scene images From the face characteristic of binding, determines that wide-angle scene image A includes a matching face image (i.e. third face image), determine There is no matching face image in wide-angle scene image B, determine that wide-angle scene image C includes two and matches face images (i.e. Third face image and the face image of fourth), determine that wide-angle scene image D includes matching face image (i.e. penta face Portion's image), it is clear that, the number for the matching face image that wide-angle scene image C includes is most, therefore by wide-angle scene image C As pending image.

After determining pending image, you can according to the face characteristic bound in pending image, wait locating to determining Reason image carries out default processing, can be specifically, face characteristic bound in pending image, carries out pending image pre- If processing, including：

According to the face characteristic bound in pending image, determines and do not meet the pending of preset condition in pending image Face image；

From other wide-angle scene images in addition to pending image, the target face of corresponding pending face image is obtained Portion's image, which meets preset condition, and belongs to identical personage with pending face image；

Pending face image is replaced with into target face image.

Wherein, after determining pending image in the multiple wide-angle scene images got, further from waiting for Pending face image is determined in reason image, wherein the pending face image does not meet preset condition.

For example, please refer to Fig. 7, the pending image determined include the face image of personage third, personage's fourth face's figure Picture and the face image of personage penta, as shown in fig. 7, the face characteristic bound in pending image, determines that the third face schemes The expression type of picture is " laugh ", and the expression type of fourth face image is similarly " laugh ", and the expression type of penta face image For " dejected ", if preset condition is " expression type be laugh ", the third face image and fourth face image meet preset condition, and penta Face image does not meet preset condition, therefore, penta face image is determined as pending face image.

Pending face image among determining pending image, further from other in addition to pending image In wide-angle scene image, obtain the target face image of corresponding pending face image, wherein the target face image with wait locating Reason face image belongs to identical personage, and the target face image meets preset condition.For example, Fig. 8 and Fig. 6 are please referred to, for In four wide-angle scene images shown in fig. 6, wide-angle scene image C is confirmed as pending image, wherein penta face image Expression type is " dejected ", is not inconsistent with preset condition " expression type is to laugh ", is further defined as pending face image. Later, (it is herein scene image A, field in other wide-angle scene images in addition to pending image (being herein scene image C) Scape image B and scene image D) in, search whether that there are penta face image (the i.e. faces of personage penta that expression type is " laugh " Portion's image), it is clear that, as shown in fig. 6, in wide-angle scene image D there are expression type be " laugh " penta face image, this When, penta face image in wide-angle scene image D is determined as target face image, and extracted from wide-angle scene image D Penta face image is used as subsequent processing.

After the target face image for getting corresponding pending face image, you can replace pending face image For target face image.For example, incorporated by reference to reference to Fig. 9 and Fig. 6, it is (i.e. wide getting four wide-angle scene images shown in fig. 6 Angle scene image A, wide-angle scene image B, wide-angle scene image C and wide-angle scene image D) after, by wide-angle scene image C It is determined as pending image, and further that penta face image (i.e. the face image of personage penta) in wide-angle scene image C is true It is set to pending face image；Later, penta face image in wide-angle scene image D is determined as target face image；Later, Penta face image in wide-angle scene image C is replaced with into penta face image in wide-angle scene image D, to obtain at replacement Wide-angle scene image C after reason, as shown in figure 9, in replaced wide-angle scene image C, the expression class of each personage's face image Type is " laugh ", meets preset condition " expression type is to laugh ".

In the embodiment of the present application, after completing image and replacing, you can clapped replaced pending image as image Take the photograph the result images of request.

Optionally, in one embodiment, after pending face image being replaced with target face image, further include：

Replaced pending image is carried out at noise reduction according to other wide-angle scene images in addition to pending image Reason.

Wherein it is possible to carry out noise reduction process to pending image by the way of multiframe noise reduction.For example, getting 4 altogether Wide-angle scene image, respectively wide-angle scene image A, wide-angle scene image B, wide-angle scene image C, wide-angle scene image D, In, wide-angle scene image D is confirmed as pending image, then can be according to according to wide-angle scene image A, wide-angle scene image B and wide-angle scene image C carries out multiframe noise reduction to wide-angle scene image D.

Specifically, when carrying out multiframe noise reduction, it can be first by wide-angle scene image A, wide-angle scene image D, wide-angle scene Image B and the C alignment of wide-angle scene image, and obtain the pixel value of each group of snap to pixels.If the picture of same group of snap to pixels Plain value is not much different, then the pixel value mean value of this group of snap to pixels can be calculated, then replaces wide-angle with the pixel value mean value The pixel value of the respective pixel of scene image D.If the pixel value difference of same group of snap to pixels is more, then can not be to wide-angle Pixel value in scene image D is adjusted.

For example, in the pixel P1 in wide-angle scene image A, the pixel P2 in wide-angle scene image D, wide-angle scene image B Pixel P3 and wide-angle scene image C in pixel P4 be one group of pixel being mutually aligned, wherein the pixel value of P1 be 101, The pixel value that the pixel value that the pixel value of P2 is 102, P3 is 103, P4 is 104, then the pixel for the pixel that this group is mutually aligned It is 102.5 to be worth mean value, then the pixel value of the P2 pixels in wide-angle scene image D can be adjusted to by terminal by 102 102.5, to carry out noise reduction process to the P2 pixels in wide-angle scene image D.If the pixel value of P1 is the pixel value of 80, P2 The pixel value that 102, P3 pixel value is 83, P4 is 90, then the pixel value difference due to them is more, terminal can not at this time The pixel value of P2 is adjusted, i.e. the pixel value holding 102 of P2 is constant.

Optionally, in one embodiment, it from other wide-angle scene images in addition to pending image, obtains correspondence and waits for After the target face image for handling face image, further include：

When obtaining the failure of target face image from other wide-angle scene images, local preset face image library is judged In whether be stored with target face image；

When being stored with target face image in face image library, the target face figure stored in face image library is extracted Picture.

It is the case where in view of obtaining the failure of target face image from other wide-angle scene images, provided herein a kind of alternative , obtain target face image scheme.

Specifically, can be locally pre-created in a face image library in electronic equipment, it is used in the face image library The face image that storage electronic equipment is got.For example, electronic equipment is every time shooting outer scene, corresponding be somebody's turn to do is obtained After the wide-angle scene image of outer scene, recognition of face is carried out to the wide-angle scene image, and will be from wide-angle scene image The face image identified is stored into face image library.

Correspondingly, when obtaining the failure of target face image from other wide-angle scene images, it can be local preset The target face image for being stored with corresponding pending face image is searched whether in face image library.Wherein, target face image Belong to identical personage with pending face image, and target face image meets preset condition.

If the target face image of corresponding pending face image is found in face image library, from face image library In extract the target face image of corresponding pending face image.For example, incorporated by reference to referring to Fig.1 0 and Fig. 6, shown in Fig. 6 Pending image in the pending face image (i.e. penta face image) determined, correspondence is extracted from face image library and is waited for Handle face image target face image (the target face image be before from history shoot certain image in identify, and It is stored in face image library), as shown in Figure 10, the target face image and pending face image extracted belongs to same person Object belongs to personage penta, and the expression type of target face image is " laugh ", meets preset condition " the expression class of configuration Type is to laugh ".

Can specifically, the target face image stored in extraction face image library, including：

When being stored with multiple target face images in face image library, the deposit moment of each target face image is obtained；

It extracts in face image library, the deposit moment is apart from current time nearest target face image.

For example, finding the target face image of 3 pending images of correspondence, respectively target face in face image library Portion's image 1, target face image 2 and target face image 3, and the deposit moment for getting target face image 1 is t1, is obtained The deposit moment to target face image 2 is t2, and the deposit moment for getting target face image 3 is t3, if deposit moment t1 Apart from current time when it is 1 day a length of, deposit moment t2 apart from current time when it is 2 days a length of, deposit moment t3 distance is current Moment when it is 7 days a length of, it is clear that, the deposit moment of target face image 1 is nearest apart from current time, at this time from face image Target image 1 is extracted in library is used as subsequent processing.

Can be specifically, since target face image at this time be extracted from face image library, which may It is collected from different photographed scenes, and photographed scene is different, illumination also differs, therefore, to promote image procossing Pending face image is replaced with target face image by image effect afterwards, including：

Obtain the Lighting information of pending face image；

The Lighting information got is migrated to target face image；

Pending face image is replaced with into the target face image after migration.

Wherein, when carrying out the migration of Lighting information, suitable illumination migration algorithm can be chosen according to actual needs, it will The Lighting information of pending image is migrated to target face image.Wherein, optional illumination migration algorithm includes but not limited to：Base Illumination migration algorithm in quotient graph, the illumination migration algorithm based on 3D models, based on filtering decompose illumination migration algorithm and Illumination migration algorithm based on eigen decomposition etc..

After the migration for completing Lighting information, determining pending face image is replaced with into the target face after migration Image so that in replaced pending image, all face images meet preset condition, and Lighting information is consistent.

For example, please referring to Figure 11, the Lighting information of certain determining pending face image is migrated to its corresponding target After face image, target face image and the pending face image obtain identical lighting effect and later wait for determining Processing face image replace with migration after target face image so that in replaced pending image, all faces Image meets preset condition, and Lighting information is consistent.

It should be noted that for using which kind of illumination migration algorithm, the embodiment of the present application to be not particularly limited, it can be by this Field technology personnel choose according to actual needs, can be the illumination migration algorithms listed by the embodiment of the present application, also may be used To be illumination migration algorithm unlisted in the embodiment of the present application.

Optionally, in one embodiment, judge whether be stored with target face image in local preset face image library Later, further include：

When not being stored with the target face image of corresponding pending face image in face image library, pending face is obtained The corresponding people information of portion's image；

It sends image and obtains request to the target electronic device corresponding to the people information got, wherein image obtains Request is used to indicate the target face image that target electronic device searches and returns to corresponding pending face image；

Receive the target face image that target electronic device returns.

In view of obtaining the case where target face image fails from local face image library, local face image that is to say When not being stored with the target face image of corresponding pending face image in library, another acquisition target face provided herein The scheme of image.

Specifically, completing the lookup to face image library, and corresponding pending face is not found in face image library When the target face image of portion's image, the target face for not being stored with corresponding pending face image in face image library that is to say When image, the corresponding people information of pending face image is obtained, in other words, determines that " who " the pending face image be Face image.

After acquiring the corresponding people information of pending face image, further believed according to the personage locally to prestore The incidence relation (incidence relation is for describing which user an electronic equipment belongs to) of breath and electronic equipment, determination obtains Get target electronic device corresponding to people information.For example, please referring to Fig. 6, for pending image shown in fig. 6, it is determined In pending face image be penta face image, at this time by get penta face image for people information be " personage Penta ", and further determine that the mobile phone of personage penta is target electronic device.

After determining target electronic device, generates image according to the message format made an appointment and obtain request, and will give birth to At image obtain request be sent to determining target electronic device.Wherein, image acquisition request is used to indicate target electronic and sets It is for future reference to look for it locally with the presence or absence of the target face image for corresponding to pending face image, if finding, what return was found Target face image.Specifically, target electronic device has locally also been pre-created face's image library, asked receiving image acquisition When asking, the instruction of request is obtained according to the image, is searched in its local face image library, waits locating if finding correspondence The target face image of face image is managed, then is returned to the target face image found.

Correspondingly, after sending image to target electronic device and obtaining request, the mesh that target electronic device returns is received Mark face image.

For example, please referring to Figure 12, on the one hand, electronic equipment is getting the (conjunction of diagram penta 3 people of the third fourth of pending image Shadow image) after, determine that penta face image in pending image is pending face image, by local face image Library is searched, and does not find the target face image of corresponding pending face image, and the mobile phone for determining penta at this time is target electricity Sub- equipment, and send image and obtain request to the target electronic device；On the other hand, target electronic device is being received from electricity It after the image of sub- equipment obtains request, is searched in local face image library, and finds corresponding pending face The target face image found is back to electronic equipment by the target face image of image at this time.

It can be specifically, in an optional embodiment, when the wide-angle scene image got is one, according to wide Face characteristic bound in the scene image of angle carries out default processing to wide-angle scene image, including：

According to the face characteristic bound in wide-angle scene image, determines in the wide-angle scene image and do not meet preset condition Pending face image；

From local preset face image library, obtain the target face image for corresponding to pending face image；

Determining pending face image is replaced with to the target face image got.

For example, the wide-angle scene image got includes the face image of personage third, the face image of personage's fourth and people The face image of object penta determines that the expression type of the third face image is according to the face characteristic bound in the wide-angle scene image The expression type of " laugh ", fourth face image is similarly " laugh ", and the expression type of penta face image is " dejected ", if default Condition is " expression type is to laugh ", then the third face image and fourth face image meet preset condition, and penta face image is not met Therefore penta face image is determined as pending face image by preset condition.

It, can be in local preset face image library after determining pending face image in wide-angle scene image In search whether to be stored with the target face image of corresponding pending face image, wherein the target face image with it is pending Face image belongs to identical personage, and target face image meets preset condition.

After the target face image for getting corresponding pending face image, you can replace pending face image For target face image.Since target face image is extracted from face image library at this time, which may be from It is collected in different photographed scenes, and photographed scene is different, illumination also differs, therefore, by determining pending face Portion's image replaces with the target face image got, first migrates the Lighting information of pending face image to target face figure Picture, then pending face image is replaced with into the target face image after migration, so that replaced wide-angle scene image In, all face images meet preset condition, and Lighting information is consistent.

From the foregoing, it will be observed that technical solution provided by the embodiments of the present application is applied to remote portrait or more people conjunction When shadow, can be small by viewfinder range but focal length scene image that portrait accounting is larger extract the people of personage in scene to be captured Face feature, it is later that the face characteristic extracted and viewfinder range is big but portrait accounts for smaller wide-angle scene image, for pair The wide-angle scene image is handled, and so as to overcome the problems, such as that face characteristic extraction is difficult, it is accurate to reach raising image procossing The purpose of degree.

Below by the basis of the method that above-described embodiment describes, further Jie is done to the image processing method of the application It continues.Figure 13 is please referred to, which may include：

In step 201, the multiple images group of Same Scene is obtained, each image group includes acquisition moment identical focal length Scene image and wide-angle scene image.

In step 202, the face characteristic of focal length scene image in each image group, and each focal length field that will be got are obtained The face characteristic of scape image is bound with the wide-angle scene image in its group.

For example, please referring to Fig. 5,4 image groups that the acquisition moment is respectively t1, t2, t3 and t4 are got, later, from The face characteristic 1 that identifies face characteristic 1 in the focal length scene image that the acquisition moment is t1, and will identify that and acquisition moment It is all the wide-angle scene image binding of t1, face characteristic 2 is identified from the focal length scene image that the acquisition moment is t2, and will know The face characteristic 2 not gone out is bound with the wide-angle scene image that the acquisition moment is all t2, from the focal length scene that the acquisition moment is t3 The face characteristic 3 that identifies face characteristic 3 in image, and will identify that is tied up with the wide-angle scene image that the acquisition moment is all t3 It is fixed, it the face characteristic 4 that identifies face characteristic 4 from the focal length scene image that the acquisition moment is t4, and will identify that and adopts The collection moment is all the wide-angle scene image binding of t4.

In step 203, the face characteristic bound in each wide-angle scene image is determined and is wrapped in each wide-angle scene image The number of matching face image containing, meeting preset condition.

In step 204, will include to match the largest number of wide-angle scene images of face image as pending image.

In step 205, the pending face image that preset condition is not met in pending image is determined.

In step 206, from other wide-angle scene images in addition to pending image, corresponding pending face is obtained The target face image of image, which meets preset condition, and belongs to identical personage with pending face image.

In step 207, pending face image is replaced with into target face image.

In one embodiment, a kind of image processing apparatus 400 is additionally provided, 4, Figure 14 is please referred to Fig.1 and implements for the application The structural schematic diagram for the image processing apparatus 400 that example provides.Wherein the image processing apparatus 400 is applied to electronic equipment, the figure As processing unit 400 includes image collection module 401, picture recognition module 402, feature binding module 403 and image procossing Module 404 is as follows：

Image collection module 401, for obtaining synchronous acquisition, Same Scene focal length scene image and wide-angle scene Image；

Picture recognition module 402 obtains focal length scene graph for carrying out recognition of face to the focal length scene image got The face characteristic of picture；

Feature binding module 403, for binding the face characteristic of focal length scene image and wide-angle scene image；

Image processing module 404, for face characteristic bound in wide-angle scene image, to wide-angle scene image into The default processing of row.

In one embodiment, when the wide-angle scene image that image collection module 401 is got is multiple, image procossing mould Block 404, is specifically used for：

In one embodiment, image processing module 404, also particularly useful for：

Pending face image is replaced with into target face image.

In one embodiment, image processing apparatus 400 further includes noise reduction process module, is used for：

In one embodiment, image processing module 404 are additionally operable to：

When obtaining the failure of target face image from other wide-angle scene images in addition to pending image, this is judged Whether ground is stored with target face image in preset face image library；

In one embodiment, image processing module 404 are specifically used for：

Obtain the Lighting information of pending face image；

The Lighting information got is migrated to target face image；

Pending face image is replaced with into the target face image after migration.

In one embodiment, image processing module 404 are additionally operable to：

When not being stored with target face image in face image library, the corresponding personage's letter of pending face image is obtained Breath；

It sends image and obtains request to the corresponding target electronic device of the people information, which obtains request and be used to indicate Target electronic device searches and returns to target face image；

Receive the target face image that target electronic device returns.

When it is implemented, the above modules can be used as independent entity to realize, arbitrary combination can also be carried out, as Same or several entities realize that the specific implementation of above each unit can be found in the embodiment of front, and details are not described herein.

From the foregoing, it will be observed that the present embodiment image processing apparatus can be by the acquisition synchronous acquisition of image collection module 401, same The focal length scene image and wide-angle scene image of scene；By picture recognition module 402 to the focal length scene image that gets into Row recognition of face obtains the face characteristic of focal length scene image；It is by feature binding module 403 that the face of focal length scene image is special Sign is bound with wide-angle scene image；By face characteristic of the image processing module 404 bound in wide-angle scene image, to wide-angle Scene image carries out default processing.Technical solution provided by the embodiments of the present application is applied to remote portrait or more When people takes a group photo, can be small by viewfinder range but focal length scene image that portrait accounting is larger extract personage in scene to be captured Face characteristic, it is later that the face characteristic extracted and viewfinder range is big but portrait accounts for smaller wide-angle scene image, use It is handled in the wide-angle scene image, so as to overcome the problems, such as that face characteristic extraction is difficult, reaches raising image procossing The purpose of accuracy.

The embodiment of the present application also provides a kind of electronic equipment.5 are please referred to Fig.1, electronic equipment 500 includes central processing unit 501 and memory 502.Wherein, central processing unit 501 is electrically connected with memory 502.

The central processing unit 500 is the control centre of electronic equipment 500, entirely electric using various interfaces and connection The various pieces of sub- equipment by the computer program of operation or load store in memory 502, and are called and are stored in Data in reservoir 502 execute the various functions of electronic equipment 500 and handle data, to realize to the accurate of user's gender Identification.

The memory 502 can be used for storing software program and module, and central processing unit 501 is stored in by operation The computer program and module of reservoir 502, to perform various functions application and data processing.Memory 502 can be main Including storing program area and storage data field, wherein storing program area can storage program area, the meter needed at least one function Calculation machine program (such as sound-playing function, image player function etc.) etc.；Storage data field can be stored to be made according to electronic equipment With the data etc. created.In addition, memory 502 may include high-speed random access memory, can also include non-volatile Memory, such as at least one disk memory, flush memory device or other volatile solid-state parts.Correspondingly, it stores Device 502 can also include Memory Controller, to provide access of the central processing unit 501 to memory 502.

In the embodiment of the present application, the central processing unit 501 in electronic equipment 500 is stored in memory 502 by operation In computer program, execute the image processing method in any of the above-described embodiment, such as：Acquisition synchronous acquisition, same field The focal length scene image and wide-angle scene image of scape；Recognition of face is carried out to the focal length scene image got, obtains focal length The face characteristic of scene image；The face characteristic of obtained focal length scene image and wide-angle scene image are bound；According to angle Face characteristic bound in scape image carries out default processing to wide-angle scene image.

Also referring to Figure 16, in some embodiments, electronic equipment 500 can also include：Display 503, radio frequency Circuit 504, voicefrequency circuit 505, power supply 506, image processing circuit 507 and graphics processor 508.Wherein, display 503, Radio circuit 504, voicefrequency circuit 505 and power supply 506 are electrically connected with central processing unit 501 respectively.

Display 503 is displayed for information input by user or the information of user and various figures is supplied to use Family interface, these graphical user interface can be made of figure, text, icon, video and its arbitrary combination.Display 503 May include display panel, in some embodiments, may be used liquid crystal display (Liquid Crystal Display, LCD) or the forms such as Organic Light Emitting Diode (Organic Light-Emitting Diode, OLED) configure display surface Plate.

Radio circuit 504 can be used for transceiving radio frequency signal, to be set by radio communication with the network equipment or other electronics It is standby to establish wireless telecommunications, the receiving and transmitting signal between the network equipment or other electronic equipments.

Voicefrequency circuit 505 can be used for providing the audio interface between user and electronic equipment by loud speaker, microphone.

Power supply 506 is used to all parts power supply of electronic equipment 500.In some embodiments, power supply 506 can be with It is logically contiguous by power-supply management system and central processing unit 501, to realize management charging by power-supply management system, put The functions such as electricity and power managed.

Image processing circuit 507 can utilize hardware and or software component to realize, it may include define ISP (Image Signal Processing, picture signal processing) pipeline various processing units, please refer to Figure 17, in one embodiment, figure As processing circuit 507 includes ISP processors 5071 and control logic device 5072.Camera 5073 capture image data first by The processing of ISP processors 5071, ISP processors 5071 analyze image data can be used for determining and/or camera to capture The image statistics of 5073 one or more control parameters.Camera 5073 may include thering is one or more lens 50731 and imaging sensor 50732 camera.Imaging sensor 50732 may include that (such as Bayer is filtered colour filter array Mirror), imaging sensor 50732 can obtain the luminous intensity captured with each imaging pixel of imaging sensor 50732 and wavelength letter Breath, and the one group of raw image data that can be handled by ISP processors 5071 is provided.Sensor 5074 (such as gyroscope) can be based on passing The parameter (such as stabilization parameter) of the image procossing of acquisition is supplied to ISP processors 5071 by 5074 interface type of sensor.Sensor 5074 interfaces can be connect using SMIA (Standard Mobile Imaging Architecture, Standard Mobile Imager framework) The combination of mouth, other serial or parallel camera interfaces or above-mentioned interface.

In addition, raw image data can be also sent to sensor 5074 by imaging sensor 50732, sensor 5074 can base It is supplied to ISP processors 5071 or sensor 5074 by original graph raw image data in 5074 interface type of sensor As in data storage to video memory 5075.

ISP processors 5071 handle raw image data pixel by pixel in various formats.For example, each image pixel can Bit depth with 8,10,12 or 14 bits, ISP processors 5071 can carry out raw image data at one or more images Reason operation, statistical information of the collection about image data.Wherein, image processing operations can be by identical or different bit depth precision It carries out.

ISP processors 5071 can also receive image data from video memory 5075.For example, 5074 interface of sensor will be former Beginning image data is sent to video memory 5075, and the raw image data in video memory 5075 is available to ISP processing Device 5071 is for processing.Video memory 5075 can be only in a part, storage device or electronic equipment for memory device Vertical private memory, and may include DMA (Direct Memory Access, direct direct memory access (DMA)) feature.

50732 interface of imaging sensor is come from when receiving or from 5074 interface of sensor or from video memory When 5075 raw image data, ISP processors 5071 can carry out one or more image processing operations, such as time-domain filtering.Place Image data after reason can be transmitted to video memory 5075, to carry out other processing before shown.ISP processors 5071 from video memory 5075 receive processing data, and to the processing data progress original domain in and RGB and YCbCr face Image real time transfer in the colour space.Treated that image data may be output to display 503 for ISP processors 5071, for Family is watched and/or is further processed by graphics engine or image processor 507.In addition, the output of ISP processors 5071 can also be sent out Video memory 5075 is given, and display 503 can read image data from video memory 5075.In one embodiment, Video memory 5075 can be configured as realizing one or more frame buffers.In addition, the output of ISP processors 5071 is transmittable To encoder/decoder 5076, so as to encoding/decoding image data.The image data of coding can be saved, and aobvious being shown in It is decompressed before showing in 503 equipment of device.Encoder/decoder 5076 can be realized by CPU or GPU or coprocessor.

The statistical data that ISP processors 5071 determine, which can be transmitted, gives control logic device Unit 5072.For example, statistical data can Including the images such as automatic exposure, automatic white balance, automatic focusing, flicker detection, black level compensation, 50731 shadow correction of lens 50732 statistical information of sensor.Control logic device 5072 may include executing one or more routines (such as firmware) processor and/ Or microcontroller, one or more routines can be determined according to the statistical data of reception at control parameter and the ISP of camera 5073 Manage the control parameter of device 5071.For example, the control parameter of camera 5073 may include that 5074 control parameter of sensor (for example increases Benefit, the time of integration of spectrum assignment, stabilization parameter etc.), camera flash control parameter, 50731 control parameter of lens it is (such as poly- Burnt or zoom focal length) or these parameters combination.ISP control parameters may include for automatic white balance and color adjustment (ratio Such as, during RGB processing) 50731 shadow correction parameter of gain level and color correction matrix and lens etc..

The display data that image processor 508 shows electronic equipment carries out conversion driving, and to display 503 provide line scan signals, control the correct display of display 503.

Further, on the basis of image processing circuit 507 of above-described embodiment description, to the image processing circuit 507 are described further, and please refer to Figure 18, and difference lies in camera 5073 includes focal length camera with above-described embodiment 507301 and wide-angle camera 507302, focal length camera 507301 includes the first lens 507311 and the first imaging sensor 507321, wide-angle camera 507302 includes the second lens 507312 and the second imaging sensor 507322.

Wherein, to the performance parameter of focal length camera 507301 and wide-angle camera 507302 (for example, focal length, aperture are big Small, resolving power etc.) do not do any restrictions.Focal length camera 507301 and wide-angle camera 507302 may be disposed at electronic equipment Same plane in, for example, the back or front in electronic equipment is arranged simultaneously.Mounting distance of the dual camera in electronic equipment It can be determined according to the size determination of electronic equipment and/or shooting effect etc., for example, in order to make focal length camera 507301 and wide-angle The picture material degree of overlapping that camera 507302 is shot is high, can install focal length camera 507301 and wide-angle camera 507302 The closer obtain the better, for example, within 10mm.

The embodiment of the present application also provides a kind of storage medium, and storage medium is stored with computer program, works as computer program When running on computers so that computer executes the image processing method in any of the above-described embodiment, such as：Acquisition, which synchronizes, adopts Focal length scene image and wide-angle scene image of collection, Same Scene；Face knowledge is carried out to the focal length scene image got Not, the face characteristic of focal length scene image is obtained；The face characteristic of obtained focal length scene image is tied up with wide-angle scene image It is fixed；According to the face characteristic bound in the scene image of angle, default processing is carried out to wide-angle scene image.

In the embodiment of the present application, storage medium can be magnetic disc, CD, read-only memory (Read Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..

In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment Point, it may refer to the associated description of other embodiment.

It should be noted that for the image processing method of the embodiment of the present application, this field common test personnel can be with The all or part of flow for understanding the image processing method for realizing the embodiment of the present application, is that can be controlled by computer program Relevant hardware is completed, and computer program can be stored in a computer read/write memory medium, be such as stored in electronic equipment Memory in, and by the electronic equipment at least one central processing unit execute, may include in the process of implementation such as image The flow of the embodiment of processing method.Wherein, storage medium can be magnetic disc, CD, read-only memory, random access memory Deng.

For the image processing apparatus of the embodiment of the present application, each function module can be integrated in a processing chip In, can also be that modules physically exist alone, can also two or more modules be integrated in a module.It is above-mentioned The form that hardware had both may be used in integrated module is realized, can also be realized in the form of software function module.Integrated mould If block is realized in the form of software function module and when sold or used as an independent product, can also be stored in a meter In calculation machine read/write memory medium, storage medium is for example read-only memory, disk or CD etc..

A kind of image processing method, device, storage medium and the electronic equipment that the embodiment of the present application is provided above into It has gone and has been discussed in detail, specific examples are used herein to illustrate the principle and implementation manner of the present application, the above implementation The explanation of example is merely used to help understand the present processes and its core concept；Meanwhile for those skilled in the art, according to According to the thought of the application, there will be changes in the specific implementation manner and application range, and to sum up, the content of the present specification is not answered It is interpreted as the limitation to the application.

Claims

1. a kind of image processing method, which is characterized in that including：

The face characteristic and the wide-angle scene image are bound；

2. image processing method as described in claim 1, which is characterized in that the wide-angle scene image got be it is multiple When, according to the face characteristic bound in the wide-angle scene image, carrying out default processing to the wide-angle scene image includes：

According to the face characteristic bound in each wide-angle scene image, determine it is including in each wide-angle scene image, meet default item The number of the matching face image of part；

According to the face characteristic bound in the pending image, default processing is carried out to the pending image.

3. image processing method as claimed in claim 2, which is characterized in that according to the face bound in the pending image Feature carries out default processing to the pending image, including：

According to the face characteristic bound in the pending image, determines in the pending image and do not meet waiting for for preset condition Handle face image；

From other wide-angle scene images in addition to the pending image, the mesh of the corresponding pending face image is obtained Face image is marked, the target face image meets the preset condition, and belongs to same person with the pending face image Object；

The pending face image is replaced with into the target face image.

4. image processing method as claimed in claim 3, which is characterized in that replace with the pending face image described After target face image, further include：

Noise reduction process is carried out to the replaced pending image according to other wide-angle scene images.

5. image processing method as described in claim 3 or 4, which is characterized in that from its in addition to the pending image In its wide-angle scene image, after the target face image for obtaining the corresponding pending face image, further include：

When obtaining the target face image failure from other wide-angle scene images, local preset face's figure is judged As whether being stored with the target face image in library；

When being stored with the target face image in the face image library, extract stored in the face image library it is described Target face image.

6. image processing method as claimed in claim 5, which is characterized in that replace with the pending face image described Target face image, including：

Obtain the Lighting information of the pending face image；

The Lighting information got is migrated to the target face image；

The pending face image is replaced with into the target face image after migration.

7. image processing method as claimed in claim 5, which is characterized in that judge in local preset face image library whether It is stored with after the target face image, including：

When not being stored with the target face image in the face image library, it is corresponding to obtain the pending face image People information；

It sends image and obtains request to the corresponding target electronic device of the people information, described image obtains request and is used to indicate The target electronic device searches and returns to the target face image；

Receive the target face image that the target electronic device returns.

8. a kind of image processing apparatus, which is characterized in that including：

Image collection module, for obtaining synchronous acquisition, Same Scene focal length scene image and wide-angle scene image；

Picture recognition module obtains the people of the focal length scene image for carrying out recognition of face to the focal length scene image Face feature；

Image processing module, for the face characteristic bound in the wide-angle scene image, to the wide-angle scene image Carry out default processing.

9. a kind of storage medium, is stored thereon with computer program, which is characterized in that when the computer program on computers When operation so that the computer executes image processing method as described in any one of claim 1 to 7.

10. a kind of electronic equipment, including central processing unit and memory, the memory are stored with computer program, feature It is, the central processing unit is by calling the computer program, for executing such as claim 1-7 any one of them figures As processing method.