CN109919866A - Image processing method, device, medium and electronic equipment - Google Patents
Image processing method, device, medium and electronic equipment Download PDFInfo
- Publication number
- CN109919866A CN109919866A CN201910140134.6A CN201910140134A CN109919866A CN 109919866 A CN109919866 A CN 109919866A CN 201910140134 A CN201910140134 A CN 201910140134A CN 109919866 A CN109919866 A CN 109919866A
- Authority
- CN
- China
- Prior art keywords
- facial image
- processed
- face
- light intensity
- facial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 38
- 230000001815 facial effect Effects 0.000 claims abstract description 279
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims description 36
- 206010040829 Skin discolouration Diseases 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003702 image correction Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 3
- 210000004709 eyebrow Anatomy 0.000 description 27
- 230000006870 function Effects 0.000 description 24
- 210000001331 nose Anatomy 0.000 description 20
- 210000000056 organ Anatomy 0.000 description 13
- 238000004040 coloring Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 210000001508 eye Anatomy 0.000 description 7
- 210000004209 hair Anatomy 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 6
- 210000000214 mouth Anatomy 0.000 description 5
- 230000006854 communication Effects 0.000 description 4
- 210000000887 face Anatomy 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the present disclosure provides a kind of image processing method, device, medium and electronic equipment, belongs to electric technical field of data processing.The image processing method includes: the facial image to be processed for obtaining target object；If the facial image to be processed is in improper light intensity scene, target face characteristic information of the target object under normal light high field scape is obtained in the facial feature information under different light intensity scenes according to the target object；And the facial image to be processed is corrected according to the target face characteristic information.The technical solution of the embodiment of the present disclosure can use target face characteristic information of the target object under normal light high field scape, to be processed facial image of the amendment under improper light intensity scene, so as to improve the image quality of the facial image to be processed.
Description
Technical field
This disclosure relates to electric technical field of data processing, in particular to a kind of image processing method, device, medium
And electronic equipment.
Background technique
Currently, popularizing with mobile terminal, more and more users carry out self-timer using mobile terminal.In daily life
In, if the image quality of self-timer is higher under bright and clear scene；And under the weaker scene of light, the imaging of self-timer
Quality is lower, shows as the problems such as noise on image increases, lines are fuzzy.
Settling mode in the related technology is to increase flash lamp by the front camera of mobile terminal, is increased by flash lamp
The light intensity of strong environment, to improve image quality.
But the program has the disadvantage in that flash lamp is that part increases light and environment light is different, to lead
The problems such as causing imaging unnatural, showing as uneven brightness of image or overexposure.
Therefore, it is necessary to a kind of new image processing method, device, medium and electronic equipments.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The embodiment of the present disclosure is designed to provide a kind of image processing method, device, medium and electronic equipment, Jin Erzhi
It is few to overcome the technical problem that image image quality is poor under improper light intensity scene present in the relevant technologies to a certain extent.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of image processing method is provided, comprising: obtain the people to be processed of target object
Face image；If the facial image to be processed is in improper light intensity scene, according to the target object in different light intensity fields
Facial feature information under scape obtains target face characteristic information of the target object under normal light high field scape；And according to institute
It states target face characteristic information and corrects the facial image to be processed.
According to one aspect of the disclosure, a kind of image processing apparatus is provided, comprising: facial image obtains module, configuration
For the facial image to be processed for obtaining target object；Face feature obtains module, if being configured at the facial image to be processed
In improper light intensity scene, then the facial feature information according to the target object under different light intensity scenes obtains the target
Target face characteristic information of the object under normal light high field scape；And facial image correction module, it is configured to according to the target
Facial feature information corrects the facial image to be processed.
According to one aspect of the disclosure, a kind of computer-readable medium is provided, computer program is stored thereon with, it is described
Image processing method described in any of the above-described embodiment is realized when program is executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided, comprising: one or more processors；Storage device,
For storing one or more programs, when one or more of programs are executed by one or more of processors, so that
One or more of processors realize image processing method described in any of the above-described embodiment.
The technical solution that the embodiment of the present disclosure provides can include the following benefits:
In the technical solution provided by some embodiments of the present disclosure, it is in the facial image to be processed of target object
In the case where improper light intensity scene, face feature of the pre-stored target object under different light intensity scenes can be passed through
Information obtains target face characteristic information of the target object under normal light high field scape, and can pass through the target pair in turn
The function of correcting the facial image to be processed is realized as the target face characteristic information under normal light high field scape, in this way, can
To improve the image quality of improper light intensity scene servant's face image.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.In the accompanying drawings:
Fig. 1 diagrammatically illustrates the flow chart of the image processing method of one embodiment according to the disclosure；
Fig. 2 diagrammatically illustrates the flow chart of image processing method according to another embodiment of the present disclosure；
Fig. 3 diagrammatically illustrates the flow chart of one embodiment of step S120 and step S130 in Fig. 1；
Fig. 4 diagrammatically illustrates the flow chart of the image processing method of another embodiment according to the disclosure；
Fig. 5 diagrammatically illustrates the flow chart of the image processing method of the further embodiment according to the disclosure；
Fig. 6 diagrammatically illustrates the flow chart of the image processing method of the further embodiment according to the disclosure；
Fig. 7 diagrammatically illustrates the block diagram of the image processing apparatus of one embodiment according to the disclosure；
Fig. 8 shows the structural schematic diagram for being suitable for the computer system for the electronic equipment for being used to realize the embodiment of the present disclosure.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
Fig. 1 diagrammatically illustrates the flow chart of the image processing method of one embodiment according to the disclosure.At the image
The executing subject of reason method can be the equipment with calculation processing function, such as server and/or mobile terminal.
As shown in Figure 1, the image processing method that disclosure embodiment provides may comprise steps of.
In step s 110, the facial image to be processed of target object is obtained.
In the exemplary embodiment, the facial image to be processed can by the imaging device on electronic equipment for example before
It sets camera and/or rear camera obtains, the acquisition modes of the facial image to be processed are not made in the embodiment of the present disclosure
It limits.
In certain embodiments, the electronic equipment may include mobile phone, tablet computer, Intelligent bracelet, smartwatch, intelligence
The energy helmet, intelligent glasses, laptop etc., are not intended to be limited in any herein.In following illustration, with the electronics
Equipment be mobile phone for be illustrated.Wherein, the target object can be the owner or user of the electronic equipment,
Such as user obtains the facial image to be processed to oneself self-timer by the smart phone of oneself.
It should be noted that the facial image to be processed can be the one of the camera shooting preservation of the electronic equipment
Frame image is also possible to facial image picture to be processed described in the frame shown in view-finder during camera shooting image, also
Can be camera shooting video during the video a certain frame image, etc., the disclosure is not construed as limiting this.
In the step s 120, if the facial image to be processed is in improper light intensity scene, according to the target pair
It is special as obtaining target face of the target object under normal light high field scape in the facial feature information under different light intensity scenes
Reference breath.
In the exemplary embodiment, improper light intensity scene here is the normal light under the normal exposure relative to image
It for high field scape, such as may include any one in half-light scene, overexposure scene, backlight scene etc..
Specifically, judge whether the facial image to be processed is in the improper light intensity scene, analysis can be passed through
Brightness value, contrast or gray value of the image to be processed etc. obtain.Here it illustrates by taking the analysis of gray value as an example
Explanation.
In the exemplary embodiment, the method can also include: the gray value for obtaining the facial image to be processed.
Specifically, recognition of face can be carried out to the facial image to be processed, determines human face region therein, the face
Region refer to include in the facial image to be processed face part region, which can be where face boundary rectangle
Region, is also possible to the region etc. of facial contour, the disclosure to the concrete shape of human face region with no restrictions, as long as the face area
Domain includes face.It wherein, include multiple pixels in the human face region, and each pixel has gray value.Root
The gray value for obtaining the facial image to be processed is calculated according to the gray value of multiple pixels in the human face region, such as is sought
Gray value of the average value of the gray value of multiple pixels in the human face region as the facial image to be processed, but this public affairs
It opens to the mathematical algorithm for the gray value for specifically seeking the facial image to be processed without limiting.
It is understood that directly the gray value of each pixel in the facial image to be processed can also be averaged
It is worth the gray value as the facial image to be processed, the disclosure is not construed as limiting this.
In the exemplary embodiment, if the gray value that the method can also include: the facial image to be processed is less than
First gray threshold then can be determined that the facial image to be processed is in the half-light scene.
In the exemplary embodiment, if the gray value that the method can also include: the facial image to be processed is greater than
Second gray threshold then can be determined that the facial image to be processed is in the overexposure scene.
In the exemplary embodiment, second gray threshold is greater than first gray threshold.
Wherein, the specific value of first gray threshold and second gray threshold can be according to concrete application scene
It is independently set, the disclosure is not construed as limiting this.
In the embodiment of the present disclosure, the backlight scene refer to the target object that is taken light source and the electronic equipment it
Between state.Under backlight scene, since background parts brightness is higher, the target object being taken exposure is be easy to cause not fill
Point, picture imaging effect is poor.Electronic equipment can shoot after opening camera shooting class application program and obtain the face figure to be processed
Picture, so as to obtain the grey level histogram of the facial image to be processed.Under backlight scene, in the grey level histogram of image
(assuming that being 0-255 with the value range of gray value, the gray value close to 0 is divided to for minimum tonal gradation and highest tonal gradation
Minimum tonal gradation is divided to highest tonal gradation close to 255 gray value) on pixel distribution it is higher, i.e. the gray scale of image is straight
Pixel is mainly distributed on the tonal gradation of two sides in histogram in square figure, and the tonal gradation among histogram is distributed less；
And under non-backlight scene, pixel is mainly distributed on the tonal gradation among histogram in the grey level histogram of image.Therefore, exist
It, can be by analyzing described in the distribution situation judgement of grey level histogram after the grey level histogram for getting the facial image to be processed
Whether facial image to be processed is in the backlight scene.
In the exemplary embodiment, after the grey level histogram for getting the facial image to be processed, can will it is described to
The gray scale of processing facial image is divided into the tonal gradation of preset quantity, if the ratio in the pixel quantity of specified tonal gradation is super
Preset value is crossed, then can be determined that the facial image to be processed is in the backlight scene.For example, can be by the people to be processed
The grey level histogram of face image according to 0-255 gray value at equal intervals or unequal interval be divided into 1,2,3,4,5,6,7,8,9,
10 grades, if the facial image to be processed the total pixel of the sum of pixel quantity of 1,2,9,10 this 4 grades Zhan 50% with
On, then it can be determined that the facial image to be processed is in backlight scene, specific value here is only used for for example, gray scale
Specific divide of grade can be designed according to actual needs with the specific value of the preset value.
Similar, it in other embodiments, can also be according to the distribution of the grey level histogram of the facial image to be processed
Situation judges whether the facial image to be processed is in the half-light scene and/or the overexposure scene.For example, if it is described to
The grey level histogram of facial image is handled 50% or more of the total pixel of the sum of pixel quantity of 1 and 2 this 2 grades Zhan, then may be used
To determine that the facial image to be processed is in the half-light scene.For another example if the gray scale of the facial image to be processed is straight
Square figure then can be determined that the face to be processed 50% or more of the total pixel of the sum of pixel quantity of 9 and 10 this 2 grades Zhan
Image is in the overexposure scene.
The facial image to be processed acquired under the improper light intensity scene, due to brightness is too dark or brightness too
Height, image quality is poor, such as the facial image shot under half-light scene, can not clearly show that the features such as facial contour are thin
Section.In the following embodiments, it is illustrated by taking the facial image to be processed shot under half-light scene as an example, mistake
The processing for exposing scene or backlight scene is similar in this, is referred to handle.
In the exemplary embodiment, the facial feature information may include the target object under different light intensity scenes
Face mask information, in facial skin colouring information etc. any one or it is a variety of.
In the exemplary embodiment, the face mask information may include that face overall profile line information, face are each
In shape information of a organ (such as nose, mouth, eyebrow, ear, eyes, hair etc.) etc. any one or it is a variety of.
In the exemplary embodiment, the facial skin colouring information may include that skin of face colouring information, face are each
In a organ (such as nose, mouth, eyebrow, ear, eyes, hair etc.) colouring information etc. any one or it is a variety of.
In the embodiment of the present disclosure, non-half-light scene, non-overexposure scene and non-backlight scene can be referred to as normal light intensity
Scene, wherein the judgment method of half-light scene, overexposure scene and backlight scene is referred to above-described embodiment.From the target pair
As extracting the target face characteristic information under normal light high field scape in the facial feature information under different light intensity scenes.
In the exemplary embodiment, the target face characteristic information may include target face profile information.The mesh
Mark face mask information can be the characteristic information of target face profile, and (such as the nose of target object is under normal light high field scape
Characteristic parameter), being also possible to the original image information of target face profile, (such as the nose of target object is in normal light high field
Original unlock facial image under scape).
In step s 130, the facial image to be processed is corrected according to the target face characteristic information.
Wherein, the facial image to be processed is corrected according to the target face characteristic information, may include: according to
Target face profile information corrects the position to be modified of the face mask of the facial image to be processed.
In the exemplary embodiment, the method can also include: according to the target face profile information, determine described in
The position to be modified of the face mask of facial image to be processed；From the face mask information under the different light intensity scenes, obtain
It takes and is under same light high field scape with the facial image to be processed and corresponding with the position to be modified unlocks face mask
Information；If the unlock face mask information matches with the position to be modified, it is determined that the facial image to be processed
The position to be modified of face mask is in the positive status to be repaired；If the unlock face mask information and the position to be modified
It mismatches, it is determined that the position to be modified of the face mask of the facial image to be processed is not at the positive status to be repaired.
In the exemplary embodiment, the unlock face under same light high field scape is in the facial image to be processed in acquisition
Before contouring information, if can also include: the light intensity of the facial image to be processed less than the first Intensity threshold or be greater than
Second Intensity threshold then adjusts the brightness of the facial image to be processed.
In the exemplary embodiment, first Intensity threshold is less than second Intensity threshold.The first light intensity threshold
Value and the specific value of second Intensity threshold can independently be set according to actual needs, and the disclosure does not limit this
It is fixed.
In the exemplary embodiment, the facial feature information may include the target object under different light intensity scenes
Facial skin colouring information.Wherein, if the method can also include: the facial skin color of the facial image to be processed
There are noises, then from the facial skin colouring information under the different light intensity scenes, the determining and facial image to be processed
Target face skin color information under same light high field scape；It is described wait locate according to purported skin colouring information amendment
Manage the facial skin color of facial image.
The image processing method that disclosure embodiment provides is in improper in the facial image to be processed of target object
In the case where light intensity scene, can by facial feature information of the pre-stored target object under different light intensity scenes,
Target face characteristic information of the target object under normal light high field scape is obtained, and in turn can be by the target object just
Target face characteristic information under ordinary light high field scape corrects the function of the facial image to be processed to realize, in this way, can be improved
The image quality of improper light intensity scene servant's face image.
Fig. 2 diagrammatically illustrates the flow chart of image processing method according to another embodiment of the present disclosure.The image
The executing subject of processing method can be the equipment with calculation processing function, such as server and/or mobile terminal.
As shown in Fig. 2, with above-mentioned embodiment illustrated in fig. 1 the difference is that, disclosure embodiment provide image
Processing method can also include the following steps.
In step S210, facial image of the target object under different light intensity scenes is acquired.
In the exemplary embodiment, the method can be applied to electronic equipment, and the electronic equipment can have preposition
Camera, and the electronic equipment can have face unlocking function.
In the exemplary embodiment, facial image of the target object under different light intensity scenes is acquired, may include:
When the electronic equipment opens the face unlocking function, the target object is acquired in difference by the front camera
Facial image under light intensity scene.
By taking the electronic equipment is smart phone as an example, the function of smart phone is stronger and stronger, on many smart phones
The function of having face to unlock carries out human face scanning generally by the front camera installed on smart phone.
It should be noted that, although facial image when electronic equipment carries out face unlock is acquired in above-described embodiment, but
It's not limited to that for the disclosure, for example, in other embodiments, can also acquire owner or the use of the electronic equipment
Person carries out facial image when self-timer, or the acquisition electronic equipment uses the facial image of any way shooting, then right
The facial image of acquisition carries out recognition of face, judgement wherein whether include the target object face, made if including
For the facial image.
In the exemplary embodiment, the different light intensity scenes can be according to point of the grey level histogram of the facial image
Cloth situation judges the light intensity scene locating for it.Specifically, the gray scale of facial image can be divided into the gray scale of predetermined quantity
Grade, using the maximum tonal gradation of accounting in the grey level histogram of the facial image as light locating for corresponding facial image
High field scape.
For example, still by taking gray scale value range is 0-255 as an example, it is assumed that by the grey level histogram of facial image according to 0-
255 gray value is at equal intervals or unequal interval is divided into 1,2,3,4,5,6,7,8,9,10 grades, if the facial image
The gray scale of 90% pixel is in 4 this grade in grey level histogram, then the light intensity scene of the facial image is 4.
It is understood that can also be by the maximum preceding several gray scale of accounting in the grey level histogram of the facial image
The average value of grade is not construed as limiting this as light intensity scene, the disclosure locating for corresponding facial image.
It in the exemplary embodiment, can also be according in the human face region in the facial image or the facial image
Each pixel gray value average value locating for tonal gradation, the light intensity scene as the facial image.At other
It, can also be also by the ash of each pixel in the human face region in the facial image or the facial image in embodiment
Light intensity scene of the average value of angle value directly as the facial image.
It is understood that the division of different light intensity scenes can be by the way of any appropriate in the embodiment of the present disclosure
It obtains, however it is not limited to the illustration of above-described embodiment.
In step S220, it is special that face of the target object under different light intensity scenes is obtained according to the facial image
Reference breath.
In step S230, facial feature information of the target object under different light intensity scenes is stored.
In the exemplary embodiment, when user carries out face unlock using electronic equipment, the user can be collected and existed
Facial image under different light intensity scenes can extract user face under different light intensity scenes after image procossing
Characteristic information.For example, face overall profile line information of the user under different light intensity scenes, each organ (example of face
Such as nose, mouth, eyebrow, ear, eyes, hair) shape information, skin of face colouring information, each organ face of face
Color information etc..In some embodiments, the facial feature information under same light intensity scene can be integrated treatment multiple be identical
Facial image under light intensity scene and under different faces shooting angle obtains, but the disclosure is not construed as limiting this.It is with nose
Example, can acquire nose image of the target object under different tonal gradations, different shooting angles, then store in the database
A certain light intensity scene under nose shape information can be multiple noses under comprehensive same light level, different shooting angles
The characteristic information for the nose that image zooming-out comes out, so as to cover various application scenarios.
It should be noted why being in the database not only to store under different light intensity scenes in the embodiment of the present disclosure
The corresponding nose characteristic information of clearest image, but the nose characteristic information under different light intensity scenes is all stored to data
In library, allowing for machine recognition is not as eye recognition so simple, intuitive, machine can not judge the face figure to be processed
On the nose of picture it is unintelligible, lack some part or the reason of noise is nose itself caused or image quality asks
Topic, can if judgement is imaging reason compared with can going at this time with the nose characteristic information under same light high field scape in database
It is corrected with taking the clearly nose characteristic information stored in database under normal light high field scape.
Here the facial feature information with the target object that will acquire under different light intensity scenes is stored to database
For be illustrated, but the disclosure actually to information storage mode be not construed as limiting.
In the embodiment of the present disclosure, the target object can be stored in a tabular form in the database in different light intensity scenes
Under facial feature information.For example, can be by face overall profile line information, the face of the target object under same light high field scape
The shape information of each organ in portion, skin of face colouring information are together with each organ colouring information associated storage of face.Again
For example, it is also possible to by face overall profile line information of the target object under different light intensity scenes, each organ of face
Shape information, each organ colouring information of skin of face colouring information or face are respectively associated and are stored together.
In other embodiments, the facial feature information can also include the target object in different light intensity scenes
Under, face's original image information under different faces' shooting angle.For example, when collecting a people of the user in face unlock when
When face image, locating light intensity scene and face's shooting angle when can know its shooting by image processing techniques.In this way, can
To store face original image of the target object under different light intensity scenes, under different faces shooting angle in the database
Information.Specifically, face's original image information can be the entirety of the facial image, can also be according to face monolithic wheel
The topography that wide, each organ of face obtains after being split to the facial image.
The image processing method that disclosure embodiment provides, can be by acquisition target object under different light intensity scenes
Facial image, obtain facial feature information of the target object under different light intensity scenes, and stored in advance, in this way,
When facial image to be processed is to shoot to obtain under improper light intensity scene, the pre-stored target can be read directly
Target face characteristic information in normal light high field scape of the object in the facial feature information under different light intensity scenes, will be non-
Facial image to be processed under normal light high field scape is converted to the facial image under proper exposure environment, so as to improve wait locate
The image quality of facial image is managed, and improves the image procossing speed of the facial image to be processed.Further, it is also possible to pass through people
Face acquires facial image of the target object under different light intensity scenes when unlocking, and can bring following benefit: on the one hand, leading to
It is often that the owner of electronic equipment carries out face unlock using the electronic equipment, it is possible to not have to through the means such as recognition of face
It is the target object that the facial image currently acquired, which can be directly determined,；On the other hand, due to face unlock itself with
Machine can collect the face figure under different light intensity scenes in the case where not needing user and specially cooperating anywhere or anytime
Picture.
Fig. 3 diagrammatically illustrates the flow chart of one embodiment of step S120 and step S130 in Fig. 1.The disclosure is real
It applies in example, the facial feature information may include face mask information of the target object under different light intensity scenes, institute
Stating target face characteristic information may include target face profile information.Wherein, the face mask information may include face
The shape information of overall profile line information, each organ of face (such as nose, mouth, eyebrow, ear, eyes, hair etc.)
In any one or it is a variety of.
As shown in figure 3, the step S120 in above-mentioned embodiment illustrated in fig. 1 may further include following steps.
In step S121, if the position to be modified of the face mask of the facial image to be processed is in shape to be modified
State obtains the target for being in the normal light high field scape then from the face mask information under the different light intensity scenes
Face mask information.
In the embodiment of the present disclosure, non-half-light scene, non-overexposure scene and non-backlight scene can be referred to as normal light intensity
Scene, wherein the judgment method of half-light scene, overexposure scene and backlight scene is referred to above-described embodiment.From the target pair
As in the face mask information under different light intensity scenes, extracting the face mask information under normal light high field scape as institute
State target face profile information.Wherein, the target face profile information can be target face profile characteristic information (such as
Characteristic parameter of the nose of target object under normal light high field scape), it is also possible to the original image information of target face profile
(such as the original unlock facial image of the nose of target object under normal light high field scape).
Specifically how to judge whether the position to be modified of the face mask of the facial image to be processed is in shape to be modified
State can refer to the embodiment of following Fig. 4.
With continued reference to Fig. 3, the step S130 in above-mentioned embodiment illustrated in fig. 1 may further include following steps.
In step S131, the face mask of the facial image to be processed is corrected according to the target face profile information
Position to be modified.
It, can be according to acquisition after confirming that the position to be modified is in the positive status to be repaired in the embodiment of the present disclosure
Target face profile information correct the position to be modified, so that it is become complete, clear.The embodiment of the present disclosure is to specifically repairing
Normal operation method is not construed as limiting.
For example, passing through the characteristic information of the right eyebrow under the normal light high field scape stored in database, closed by image
It, can be with the right eyebrow of the facial image to be processed shot under the improper light intensity scene of amendment of equal proportion not at algorithm
Clearly profile.
For another example under the normal light high field scape that stores in database and identical the right of face shooting angle can also be passed through
The corresponding original face of eyebrow unlocks image, replaces the right eyebrow to be modified in the facial image to be processed.
Fig. 4 diagrammatically illustrates the flow chart of the image processing method of another embodiment according to the disclosure.The image
The executing subject of processing method can be the equipment with calculation processing function, such as server and/or mobile terminal.
As shown in figure 4, with above-described embodiment the difference is that, disclosure embodiment provide image processing method
It can also include the following steps.
In step S410, according to the target face profile information, face's wheel of the facial image to be processed is determined
Wide position to be modified.
In the embodiment of the present disclosure, image procossing can be carried out to the facial image to be processed, obtain its face shooting angle
Degree.Such as image analysis finds that the image distribution of the facial image to be processed has symmetry, the facial image to be processed
Shape be ellipse, and including the ear of the left and right of the target object two, then can be determined that it for front shooting.Example again
Such as, if image analysis finds that the facial image to be processed lacks a left eye of the target object, and its comprehensive hair wheel
Exterior feature can be determined that it for right side shooting.The image processing techniques for obtaining the face shooting angle of the facial image to be processed can be with
Referring to the relevant technologies, the disclosure is not construed as limiting this.
In the embodiment of the present disclosure, when determining the target face profile information, and the facial image to be processed is known
After face shooting angle, by image fitting algorithm, the position to be modified of the facial image to be processed can be determined.Wherein,
The position to be modified can be one or more.
For example, passing through the characteristic information of the eyebrow under the normal light high field scape stored in database, and in conjunction with described wait locate
After the face shooting angle for managing facial image, it is assumed here that shot for the right side, then know to lack in the facial image to be processed
The left side eyebrow of the target object is normal, and further according to the right of the image processing techniques target object
There are unintelligible or imperfect places for eyebrow, and the spy of the right eyebrow under the normal light high field scape by storing in database
Reference breath is it is found that the imperfect place can be then determined described caused by the eyebrow missing of described target object the right itself
The position to be modified of target object is the right eyebrow of the target object.
For another example still by taking the right eyebrow as an example, if being found by image procossing, in the face figure to be processed
As in there are imperfect place or missing place, by compared with the right eyebrow under normal light high field scape it is found that if should
Imperfect place or missing place are caused by the right eyebrow of the target object inherently lacks this part, then described at this time
The right eyebrow of target object is still judged as non-position to be modified；If the imperfect place or missing place are not the mesh
Caused by the right eyebrow itself for marking object, then it can be determined that the right eyebrow is the position to be modified.
Whether other human faces, overall profile lines are that the judgment method at position to be modified is referred to the example above and says
Bright, how the disclosure is to specifically judging that the method at position to be modified is not construed as limiting.
In the step s 420, judge whether the light intensity of the facial image to be processed less than the first Intensity threshold or is greater than
Second Intensity threshold；If the light intensity of the facial image to be processed is less than first Intensity threshold or is greater than second light
Strong threshold value, then enter step S430；Conversely, then jumping to step S440.
Behind the above-mentioned determination position to be modified, need to further determine that the position to be modified is since face is shot
Caused by angle, or as shooting when improper light intensity scene caused by.
In the embodiment of the present disclosure, the light intensity of the facial image to be processed is referred to its gray value, grey level histogram, bright
Angle value, contrast etc. determine.
In the embodiment of the present disclosure, if having preassigned the light intensity lower limit of the normal light high field scape of the facial image to be processed
And the upper limit, then first Intensity threshold is less than the light intensity lower limit, and second Intensity threshold is greater than the light intensity upper limit, i.e.,
It here is not directly to adjust the light intensity of the facial image to be processed to normal light high field scape.Wherein, first light intensity
Threshold value and the value of second Intensity threshold can also be carried out according to practical application scene from main modulation, and the disclosure does not make this
It limits.
In step S430, the brightness of the facial image to be processed is adjusted.
If in view of the facial image to be processed shoot when light intensity be less than first Intensity threshold, illustrate described in
Facial image to be processed is acquired under very dark light intensity scene, at this time can be by the brightness of the facial image to be processed slightly
It is micro- to improve, to increase the brightness of the facial image to be processed；If the light intensity when facial image to be processed is shot is big
In second Intensity threshold, then illustrates that the facial image to be processed is acquired under very bright light intensity scene, at this time may be used
With by the brightness of the facial image to be processed down slightly, to reduce the brightness of the facial image to be processed.
In step S440, from the face mask information under the different light intensity scenes, obtain and the people to be processed
Face image is under same light high field scape and corresponding with the position to be modified unlocks face mask information.
For example, light intensity scene locating when the facial image to be processed shooting can be determined first, wherein described wait locate
The determination method for managing the light intensity scene of facial image is referred in above-described embodiment about the light intensity scene for unlocking facial image
Method of determination.Wherein, if the facial image to be processed pass through above-mentioned steps S430 adjustment, will it is adjusted described in
Facial image is handled as facial image to be processed described in step S440.
Then, it from the facial feature information stored in database, chooses and is in identical with the facial image to be processed
The face mask information at the position to be modified under light intensity scene is as the unlock face mask information.
For another example the light intensity scene and face shooting angle when the facial image to be processed shooting can be determined first,
Then it chooses and is under same light high field scape with the facial image to be processed and face shooting angle phase from the database
The facial image acquired when the original face unlock at the same position to be modified is as the unlock face mask information.
In step S450, if the unlock face mask information and the position to be modified mismatch, it is determined that described
The position to be modified of the face mask of facial image to be processed is in the positive status to be repaired.
In the embodiment of the present disclosure, if the position to be modified be as shooting when improper light intensity scene caused by profile
Unintelligible or localized loss then can be determined that it is in the positive status to be repaired.
It, can face shooting angle in conjunction with the facial image to be processed and the unlock face in the embodiment of the present disclosure
Profile information is similar between the unlock face mask information and the position to be modified of the facial image to be processed to judge
Degree can be recognized if similarity between the two is less than preset threshold (can carry out flexible setting according to concrete application scene)
It is mismatched for the unlock face mask information and the position to be modified, that is, determines that the position to be modified is in shape to be modified
State.
In step S460, if the unlock face mask information is matched with the position to be modified, it is determined that it is described to
The position to be modified for handling the face mask of facial image is not at the positive status to be repaired.
It, can if the position to be modified is partially lacked at as caused by face shooting angle in the embodiment of the present disclosure
To determine that it is not in the positive status to be repaired.
It, can face shooting angle in conjunction with the facial image to be processed and the unlock face in the embodiment of the present disclosure
Profile information is similar between the unlock face mask information and the position to be modified of the facial image to be processed to judge
Degree, if similarity between the two is more than or equal to the preset threshold, it may be considered that the unlock face mask information and institute
Position matching to be modified is stated, that is, determines that the position to be modified is not at the positive status to be repaired.
Or by taking above-mentioned the right eyebrow is the position to be modified as an example.
For example, if choosing from the facial feature information stored in database and being in phase with the facial image to be processed
The characteristic information of the right eyebrow under high field of sharing the same light scape can then be believed according to the feature of the right eyebrow under the same light high field scape
Breath, judge the right eyebrow localized loss be as caused by face shooting angle, or due to shooting when improper light intensity
Caused by scene.
For another example if selection is in the facial image to be processed from the facial feature information stored in database
Under same light high field scape and the original unlock facial image of the identical the right eyebrow of face shooting angle, then it can be sentenced by comparing
The localized loss of disconnected the right eyebrow is that the improper light intensity scene as caused by face shooting angle, or when due to shooting is led
It causes.
The image processing method that disclosure embodiment provides, on the one hand, do not shared the same light by storing in the database in advance
Face's organ contours information, facial skin colouring information and/or face's organ colouring information of target object under high field scape etc.,
The lower facial image to be processed of imaging definition shot under improper light intensity scene such as half-light scene can be corrected, thus
The image quality under improper light intensity scene can be improved；On the other hand, a variety of light intensity fields have been comprehensively considered in makeover process
The information acquired under scape can be imaged the problems such as unnatural to avoid revised facial image, improve user experience.
Fig. 5 diagrammatically illustrates the flow chart of the image processing method of the further embodiment according to the disclosure.The image
The executing subject of processing method can be the equipment with calculation processing function, such as server and/or mobile terminal.The disclosure
In embodiment, the facial feature information may include facial skin color letter of the target object under different light intensity scenes
Breath.Further, the facial skin colouring information may include skin of face colouring information, each organ of face (such as nose
Son, mouth, eyebrow, ear, eyes, hair etc.) in colouring information etc. any one or it is a variety of.
As shown in figure 5, with above-described embodiment the difference is that, disclosure embodiment provide image processing method
It can also include the following steps.
In step S510, if there are noises for the facial skin color of the facial image to be processed, from the difference
It is determining to be in the mesh under same light high field scape with the facial image to be processed in facial skin colouring information under light intensity scene
Mark facial skin colouring information.
In the embodiment of the present disclosure, identify that the facial skin color of the facial image to be processed whether there is noise, it can be with
It is realized by image recognition technology in the related technology, noise here for example can be a certain unnatural face on facial image
Color lump, such as the green point of face.The facial image to be processed facial skin color there are when noise, can be from described
It is extracted in database and is in face's skin under same light high field scape and with the noise corresponding site with the facial image to be processed
Skin colouring information is as the target face skin color information.
In step S520, the facial skin of the facial image to be processed is corrected according to the purported skin colouring information
Color.
In the embodiment of the present disclosure, according to the target face skin being in the facial image to be processed under same light high field scape
Skin colouring information corrects the facial skin color of the corresponding site of the facial image to be processed, rather than according to the data
Facial skin colouring information in library under normal light high field scape is corrected, it is ensured that revised facial skin color with it is described
The general image of facial image to be processed is consistent, to realize that nature is imaged.
Fig. 6 diagrammatically illustrates the flow chart of the image processing method of the further embodiment according to the disclosure.The image
The executing subject of processing method can be the equipment with calculation processing function, such as server and/or mobile terminal.
As shown in fig. 6, with above-mentioned illustrated embodiment the difference is that, disclosure embodiment provide image procossing
Method can also include the following steps.
In step S610, landscaping treatment is carried out to the revised facial image to be processed and is shown.
In the embodiment of the present disclosure, the landscaping treatment can be using " image U.S. face " function in the related technology, specifically originally
It is open that this is not construed as limiting.
In step S620, in response to the selection operation of input, from the facial image to be processed after landscaping treatment
Determine target facial image.
In the embodiment of the present disclosure, the facial image to be processed after landscaping treatment is shown to the display device of electronic equipment
On, for selection by the user, after selecting a wherein width or a few width images when the user clicks, selected image can be saved
As final target facial image.
The Installation practice of the disclosure introduced below can be used for executing the above-mentioned image processing method of the disclosure.
Fig. 7 diagrammatically illustrates the block diagram of the image processing apparatus of one embodiment according to the disclosure.The image procossing
Device can be set in the equipment with calculation processing function, such as server and/or mobile terminal.
As shown in fig. 7, the image processing apparatus 700 that disclosure embodiment provides may include that facial image obtains module
710, face feature obtains module 720 and facial image correction module 730.
Wherein, facial image obtains module 710 and is configurable to obtain the facial image to be processed of target object.Face is special
If sign acquisition module 720 is configurable to the facial image to be processed and is in improper light intensity scene, according to the target
Object obtains target face of the target object under normal light high field scape in the facial feature information under different light intensity scenes
Characteristic information.Facial image correction module 730 is configurable to be corrected according to the target face characteristic information described to be processed
Facial image.
In the exemplary embodiment, image processing apparatus 700 can also include: image capture module, be configurable to adopt
Collect facial image of the target object under different light intensity scenes；Characteristic extracting module is configurable to according to the face
Image obtains facial feature information of the target object under different light intensity scenes；Characteristic storage module is configurable to deposit
Store up facial feature information of the target object under different light intensity scenes.
In the exemplary embodiment, described device can be applied to electronic equipment, and the electronic equipment can have preposition
Camera, and the electronic equipment can have face unlocking function.Wherein, described image acquisition module may include: image
Acquisition unit is configurable to adopt when the electronic equipment opens the face unlocking function by the front camera
Collect facial image of the target object under different light intensity scenes.
In the exemplary embodiment, the facial feature information may include the target object under different light intensity scenes
Face mask information.Wherein, it may include: face feature acquiring unit that face feature, which obtains module 720, if being configurable to
The position to be modified of the face mask of the facial image to be processed is in positive status to be repaired, then under the different light intensity scenes
Face mask information in, obtain be in the normal light high field scape the target face profile information.Facial image amendment
Module 730 may include: facial image amending unit, be configurable to be corrected according to the target face profile information it is described to
Handle the position to be modified of the face mask of facial image.
In the exemplary embodiment, image processing apparatus 700 can also include: amendment position determining module, can configure
To determine the position to be modified of the face mask of the facial image to be processed according to the target face profile information；Unlock
Profile information obtains module, is configurable to from the face mask information under the different light intensity scenes, obtain with it is described to
Processing facial image is under same light high field scape and corresponding with the position to be modified unlocks face mask information；State is sentenced
Disconnected module, if being configurable to the unlock face mask information and the position mismatch to be modified, it is determined that described wait locate
The position to be modified for managing the face mask of facial image is in the positive status to be repaired；If the unlock face mask information and institute
State position matching to be modified, it is determined that the position to be modified of the face mask of the facial image to be processed is not at described to be repaired
Positive status.
In the exemplary embodiment, image processing apparatus 700 can also include brightness adjusting section, be configurable to obtaining
It takes before being in the unlock face mask information under same light high field scape with the facial image to be processed, if the people to be processed
The light intensity of face image is less than the first Intensity threshold or is greater than the second Intensity threshold, then adjusts the bright of the facial image to be processed
Degree.
In the exemplary embodiment, image processing apparatus 700 can also include: image beautification display module, can configure
To carry out landscaping treatment to the revised facial image to be processed and showing；Target facial image determining module, Ke Yipei
It is set to the selection operation in response to input, target facial image is determined from the facial image to be processed after landscaping treatment.
Each functional module and above-mentioned image processing method due to the image processing apparatus of the example embodiment of the disclosure
Example embodiment the step of it is corresponding, therefore for those undisclosed details in the apparatus embodiments, please refer in the disclosure
The embodiment for the image processing method stated.
Below with reference to Fig. 8, it illustrates the computer systems 800 for the electronic equipment for being suitable for being used to realize the embodiment of the present disclosure
Structural schematic diagram.The computer system 800 of electronic equipment shown in Fig. 8 is only an example, should not be to the embodiment of the present disclosure
Function and use scope bring any restrictions.
As shown in figure 8, computer system 800 includes central processing unit (CPU) 801, it can be read-only according to being stored in
Program in memory (ROM) 802 or be loaded into the program in random access storage device (RAM) 803 from storage section 807 and
Execute various movements appropriate and processing.In RAM 803, it is also stored with various programs and data needed for system operatio.CPU
801, ROM 802 and RAM 803 is connected with each other by bus 804.Input/output (I/O) interface 805 is also connected to bus
804。
I/O interface 805 is connected to lower component: the importation 806 including keyboard, mouse etc.；It is penetrated including such as cathode
The output par, c 807 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage section 808 including hard disk etc.；
And the communications portion 809 of the network interface card including LAN card, modem etc..Communications portion 809 via such as because
The network of spy's net executes communication process.Driver 810 is also connected to I/O interface 805 as needed.Detachable media 811, such as
Disk, CD, magneto-optic disk, semiconductor memory etc. are mounted on as needed on driver 810, in order to read from thereon
Computer program be mounted into storage section 807 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communications portion 809, and/or from detachable media
811 are mounted.When the computer program is executed by central processing unit (CPU) 801, executes and limited in the system of the application
Above-mentioned function.
It should be noted that computer-readable medium shown in the disclosure can be computer-readable signal media or meter
Calculation machine readable storage medium storing program for executing either the two any combination.Computer readable storage medium for example can be --- but not
Be limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor system, device or device, or any above combination.Meter
The more specific example of calculation machine readable storage medium storing program for executing can include but is not limited to: have the electrical connection, just of one or more conducting wires
Taking formula computer disk, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type may be programmed read-only storage
Device (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic memory device,
Or above-mentioned any appropriate combination.In the disclosure, computer readable storage medium can be it is any include or storage journey
The tangible medium of sequence, the program can be commanded execution system, device or device use or in connection.And at this
In open, computer-readable signal media may include in a base band or as the data-signal that carrier wave a part is propagated,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.Include on computer-readable medium
Program code can transmit with any suitable medium, including but not limited to: wireless, electric wire, optical cable, RF etc. are above-mentioned
Any appropriate combination.
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of above-mentioned module, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram or flow chart and the box in block diagram or flow chart, can use and execute rule
The dedicated hardware based systems of fixed functions or operations is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Being described in module and/or unit involved in the embodiment of the present disclosure can be realized by way of software,
It can be realized by way of hardware, described module and/or unit also can be set in the processor.Wherein, these
Module and/or the title of unit do not constitute the restriction to the module and/or unit itself under certain conditions.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment；It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programs
When standby execution, so that the electronic equipment realizes such as above-mentioned image processing method as described in the examples.
For example, the electronic equipment may be implemented as shown in Figure 1: step S110, obtain target object wait locate
Manage facial image；Step S120, if the facial image to be processed is in improper light intensity scene, according to the target object
Target face feature of the target object under normal light high field scape is obtained in the facial feature information under different light intensity scenes
Information；Step S130 corrects the facial image to be processed according to the target face characteristic information.
For another example, each step as shown in Figures 2 to 6 may be implemented in the electronic equipment.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, touch control terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (11)
1. a kind of image processing method characterized by comprising
Obtain the facial image to be processed of target object；
If the facial image to be processed is in improper light intensity scene, according to the target object under different light intensity scenes
Facial feature information obtain target face characteristic information of the target object under normal light high field scape；And
The facial image to be processed is corrected according to the target face characteristic information.
2. the method according to claim 1, wherein further include:
Acquire facial image of the target object under different light intensity scenes；
Facial feature information of the target object under different light intensity scenes is obtained according to the facial image；
Store facial feature information of the target object under different light intensity scenes.
3. according to the method described in claim 2, it is characterized in that, the method is applied to electronic equipment, the electronic equipment
With front camera, and the electronic equipment has face unlocking function；Wherein, the target object is acquired in different light intensity
Facial image under scene, comprising:
When the electronic equipment opens the face unlocking function, the target object is acquired by the front camera and is existed
Facial image under different light intensity scenes.
4. according to the method described in claim 2, it is characterized in that, the facial feature information includes the target object not
Face mask information under high field of sharing the same light scape, the target face characteristic information include target face profile information；Wherein, according to
The target object obtains the target object under normal light high field scape in the facial feature information under different light intensity scenes
Target face characteristic information, comprising:
If the position to be modified of the face mask of the facial image to be processed is in positive status to be repaired, from the different light intensity
In face mask information under scene, the target face profile information for being in the normal light high field scape is obtained；
The facial image to be processed is corrected according to the target face characteristic information, comprising:
The position to be modified of the face mask of the facial image to be processed is corrected according to the target face profile information.
5. according to the method described in claim 4, it is characterized by further comprising:
According to the target face profile information, the position to be modified of the face mask of the facial image to be processed is determined；
From the face mask information under the different light intensity scenes, obtains and be in identical light intensity with the facial image to be processed
Under scene and corresponding with the position to be modified unlock face mask information；
If the unlock face mask information and the position to be modified mismatch, it is determined that the face of the facial image to be processed
The position to be modified of contouring is in the positive status to be repaired；
If the unlock face mask information is matched with the position to be modified, it is determined that the face of the facial image to be processed
The position to be modified of profile is not at the positive status to be repaired.
6. according to the method described in claim 5, it is characterized in that, being in same light with the facial image to be processed obtaining
Before unlock face mask information under high field scape, further includes:
If the light intensity of the facial image to be processed is less than the first Intensity threshold or is greater than the second Intensity threshold, described in adjustment
The brightness of facial image to be processed.
7. according to the method described in claim 2, it is characterized in that, the facial feature information includes the target object not
Facial skin colouring information under high field of sharing the same light scape；Wherein, the method also includes:
If there are noises for the facial skin color of the facial image to be processed, face's skin under the different light intensity scenes
It is determining to be in the letter of the target face skin color under same light high field scape with the facial image to be processed in skin colouring information
Breath；
The facial skin color of the facial image to be processed is corrected according to the purported skin colouring information.
8. the method according to claim 1, wherein further include:
Landscaping treatment is carried out to the revised facial image to be processed and is shown；
In response to the selection operation of input, target facial image is determined from the facial image to be processed after landscaping treatment.
9. a kind of image processing apparatus characterized by comprising
Facial image obtains module, is configured to obtain the facial image to be processed of target object；
Face feature obtains module, if being configured to the facial image to be processed is in improper light intensity scene, according to
Target object obtains target of the target object under normal light high field scape in the facial feature information under different light intensity scenes
Facial feature information；And
Facial image correction module is configured to correct the facial image to be processed according to the target face characteristic information.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
Such as image processing method described in any item of the claim 1 to 8 is realized when row.
11. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
When device executes, so that one or more of processors realize such as image processing method described in any item of the claim 1 to 8
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140134.6A CN109919866B (en) | 2019-02-26 | 2019-02-26 | Image processing method, device, medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910140134.6A CN109919866B (en) | 2019-02-26 | 2019-02-26 | Image processing method, device, medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109919866A true CN109919866A (en) | 2019-06-21 |
| CN109919866B CN109919866B (en) | 2023-12-01 |
Family
ID=66962312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910140134.6A Active CN109919866B (en) | 2019-02-26 | 2019-02-26 | Image processing method, device, medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109919866B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111243105A (en) * | 2020-01-15 | 2020-06-05 | Oppo广东移动通信有限公司 | Augmented reality processing method and device, storage medium and electronic equipment |
| CN112069977A (en) * | 2020-09-02 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN112348738A (en) * | 2020-11-04 | 2021-02-09 | Oppo广东移动通信有限公司 | Image optimization method, image optimization device, storage medium, and electronic apparatus |
| CN112749607A (en) * | 2020-06-01 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Image identification method and device based on artificial intelligence |
| CN113971822A (en) * | 2020-07-22 | 2022-01-25 | 武汉Tcl集团工业研究院有限公司 | Face detection method, intelligent terminal and storage medium |
| EP3958169A4 (en) * | 2019-12-06 | 2022-07-27 | ZTE Corporation | Facial image processing method and apparatus, computer device, and medium |
| WO2022222702A1 (en) * | 2021-04-23 | 2022-10-27 | 华为技术有限公司 | Screen unlocking method and electronic device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018054054A1 (en) * | 2016-09-23 | 2018-03-29 | 中兴通讯股份有限公司 | Face recognition method, apparatus, mobile terminal and computer storage medium |
| CN108495038A (en) * | 2018-03-30 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
-
2019
- 2019-02-26 CN CN201910140134.6A patent/CN109919866B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018054054A1 (en) * | 2016-09-23 | 2018-03-29 | 中兴通讯股份有限公司 | Face recognition method, apparatus, mobile terminal and computer storage medium |
| CN108495038A (en) * | 2018-03-30 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 邱佳梁等: "结合肤色分割与平滑的人脸图像快速美化", 《中国图象图形学报》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3958169A4 (en) * | 2019-12-06 | 2022-07-27 | ZTE Corporation | Facial image processing method and apparatus, computer device, and medium |
| US20220245962A1 (en) * | 2019-12-06 | 2022-08-04 | Zte Corporation | Facial image processing method and apparatus, computer device, and medium |
| CN111243105A (en) * | 2020-01-15 | 2020-06-05 | Oppo广东移动通信有限公司 | Augmented reality processing method and device, storage medium and electronic equipment |
| CN111243105B (en) * | 2020-01-15 | 2023-07-28 | Oppo广东移动通信有限公司 | Augmented reality processing method and device, storage medium and electronic equipment |
| CN112749607A (en) * | 2020-06-01 | 2021-05-04 | 腾讯科技（深圳）有限公司 | Image identification method and device based on artificial intelligence |
| CN112749607B (en) * | 2020-06-01 | 2023-09-12 | 腾讯科技（深圳）有限公司 | Image recognition method and device based on artificial intelligence |
| CN113971822A (en) * | 2020-07-22 | 2022-01-25 | 武汉Tcl集团工业研究院有限公司 | Face detection method, intelligent terminal and storage medium |
| CN112069977A (en) * | 2020-09-02 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Image processing method, image processing device, electronic equipment and computer readable medium |
| CN112348738A (en) * | 2020-11-04 | 2021-02-09 | Oppo广东移动通信有限公司 | Image optimization method, image optimization device, storage medium, and electronic apparatus |
| CN112348738B (en) * | 2020-11-04 | 2024-03-26 | Oppo广东移动通信有限公司 | Image optimization method, image optimization device, storage medium and electronic equipment |
| WO2022222702A1 (en) * | 2021-04-23 | 2022-10-27 | 华为技术有限公司 | Screen unlocking method and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109919866B (en) | 2023-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919866A (en) | Image processing method, device, medium and electronic equipment | |
| CN105187810B (en) | A kind of auto white balance method and electronic medium device based on face color character | |
| CN108509892B (en) | Method and apparatus for generating near-infrared image | |
| CN108388878A (en) | The method and apparatus of face for identification | |
| CN110175555A (en) | Facial image clustering method and device | |
| CN108491809A (en) | The method and apparatus for generating model for generating near-infrared image | |
| US20220230323A1 (en) | Automatically Segmenting and Adjusting Images | |
| CN104834908A (en) | Image exposure method for mobile terminal based on eye pattern recognition and exposure system | |
| Pei et al. | Effective image haze removal using dark channel prior and post-processing | |
| CN108491823A (en) | Method and apparatus for generating eye recognition model | |
| CN109785228B (en) | Image processing method, image processing apparatus, storage medium, and server | |
| CN110069974A (en) | Bloom image processing method, device and electronic equipment | |
| US20230059499A1 (en) | Image processing system, image processing method, and non-transitory computer readable medium | |
| CN113610723B (en) | Image processing method and related device | |
| CN110516598A (en) | Method and apparatus for generating image | |
| CN109819176A (en) | A kind of image pickup method, system, device, electronic equipment and storage medium | |
| CN109472738A (en) | Image irradiation correcting method and device, electronic equipment and storage medium | |
| CN110248141A (en) | Video image brightness adjusting method, device, equipment and readable storage medium | |
| CN111127367A (en) | Method, device and system for processing face image | |
| CN111275648B (en) | Face image processing method, device, equipment and computer readable storage medium | |
| CN109348207A (en) | Color temperature adjusting method, image processing method and device, medium and electronic equipment | |
| CN113240760B (en) | Image processing method, device, computer equipment and storage medium | |
| CN110047126A (en) | Render method, apparatus, electronic equipment and the computer readable storage medium of image | |
| CN109523564A (en) | Method and apparatus for handling image | |
| CN109308690A (en) | A kind of brightness of image equalization methods and terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |