CN107578380A - Image processing method and device, electronic equipment and storage medium - Google Patents
Image processing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN107578380A CN107578380A CN201710665959.0A CN201710665959A CN107578380A CN 107578380 A CN107578380 A CN 107578380A CN 201710665959 A CN201710665959 A CN 201710665959A CN 107578380 A CN107578380 A CN 107578380A
- Authority
- CN
- China
- Prior art keywords
- region
- target face
- pixel
- area
- characteristic portion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The embodiment of the invention provides an image processing method, an image processing device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a face image to be processed; determining a characteristic region where a target face characteristic part in the face image is located; and performing image processing on the characteristic region where the target face characteristic part is located by adopting a preset beautifying algorithm corresponding to the target face characteristic part. The embodiment of the invention can reduce the waste of computing resources in the process of processing the face image; meanwhile, the embodiment of the invention also improves the operation efficiency, enables the operation to be smoother and improves the user experience.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method, device, electronic equipment and
Storage medium.
Background technology
In actual life, the class client band of taking pictures of installation in most electronic equipment (such as smart mobile phone, tablet personal computer)
There is U.S. face function.
U.S. face function refers to:After getting facial image (image for including human face region), using U.S. face algorithm, to face
Image carries out landscaping treatment, so that the human face region in treated facial image has the effect of U.S. face.
Under normal circumstances, above-mentioned class client of taking pictures has a variety of U.S. face functions, such as big eye function, thin face function or whitening
Function etc..After user selects certain U.S. face function, above-mentioned class client of taking pictures can run U.S. face algorithm corresponding to the U.S. face function
Facial image is handled, so as to reach corresponding U.S. face effect.For example, run big eye algorithm to facial image at
Reason, can make the eyes of the human face region in the facial image after processing seem bigger.
U.S. face effect can be reached by carrying out image procossing using aforesaid way, but above-mentioned class client of taking pictures is using beautiful
When face algorithm is handled facial image, all areas in facial image can be handled, be generally comprised due to image
Data volume is larger, therefore, using aforesaid way carry out image procossing when, it is necessary to amount of computational resources it is larger.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of image processing method, device, electronic equipment and storage medium, with
The waste of computing resource during reduction face image processing.
To reach above-mentioned purpose, the embodiments of the invention provide a kind of image processing method, methods described includes:
Obtain pending facial image;
Determine the characteristic area where target face characteristic portion in the facial image;
Using U.S. face algorithm is preset corresponding to the target face characteristic portion, to where the target face characteristic portion
Characteristic area carry out image procossing.
It is described to determine target face features in the facial image in specific implementation provided in an embodiment of the present invention
The step of characteristic area at position place, including:
The characteristic point for characterizing target face characteristic portion is extracted from the facial image;
The characteristic point area defined that will be extracted, the characteristic area being defined as where the target face characteristic portion
Domain.
In specific implementation provided in an embodiment of the present invention, the target face characteristic portion be with lower portion extremely
Few one kind:
Eyes, eyebrow, face, nose, ear, chin, face.
It is described when the target face characteristic portion is eyes in specific implementation provided in an embodiment of the present invention
Using the default U.S. face algorithm of the target face characteristic portion, the characteristic area where the target face characteristic portion is entered
The step of row image procossing, including:
Black eye ball region is searched in eyes region;
Based on the black eye ball region, black eye ball's dead center and the black eye radius of a ball are determined;
It is determined that adjustment radius is the numerical value more than the black eye radius of a ball;
Using the pixel value of pixel in black eye ball region, the pixel value of pixel in first area is adjusted, wherein,
The first area is:Region in second area in addition to the black eye ball region, the second area are:Where eyes
Border circular areas in region using the black eye ball's dead center as origin, using the adjustment radius as radius.
It is described when the target face characteristic portion is chin in specific implementation provided in an embodiment of the present invention
Using the default U.S. face algorithm of the target face characteristic portion, the characteristic area where the target face characteristic portion is entered
The step of row image procossing, including:
Using the pixel value of first kind pixel, the pixel value of the second class pixel in adjustment chin region, wherein,
The second class pixel includes:In the edge pixel point of chin region, chin region with the edge pixel point
The distance between be less than the pixel of the first preset value, the first kind pixel is:In 3rd region with the edge pixel
The distance between point is less than the pixel of the second preset value, and the 3rd region is:Chin location is removed in the facial image
Region beyond domain.
In the specific implementation that inventive embodiments provide, when the target face characteristic portion is face, the use
The default U.S. face algorithm of the target face characteristic portion, figure is carried out to the characteristic area where the target face characteristic portion
As the step of processing, including:
Using default mill skin algorithm and/or whitening algorithm, the characteristic area where the target face characteristic portion is entered
Row image procossing.
The embodiment of the present invention additionally provides a kind of image processing apparatus, and described device includes:
Acquisition module, for obtaining pending facial image;
Determining module, for determining the characteristic area in the facial image where target face characteristic portion;
Processing module, U.S. face algorithm is preset corresponding to the target face characteristic portion for using, to the target person
Characteristic area where face characteristic portion carries out image procossing.
In specific implementation provided in an embodiment of the present invention, the determining module, including:
Extraction unit, for extracting the characteristic point for characterizing target face characteristic portion from the facial image;
First determining unit, for the characteristic point area defined that will be extracted, it is defined as the target face characteristic
Characteristic area where position.
In specific implementation provided in an embodiment of the present invention, the target face characteristic portion be with lower portion extremely
Few one kind:
Eyes, eyebrow, face, nose, ear, chin, face.
It is described when the target face characteristic portion is eyes in specific implementation provided in an embodiment of the present invention
Processing module, including:
Searching unit, for searching black eye ball region in eyes region;
Second determining unit, for based on the black eye ball region, determining black eye ball's dead center and the black eye radius of a ball;
3rd determining unit, for determining that adjustment radius is the numerical value more than the black eye radius of a ball;
Adjustment unit, for the pixel value using pixel in black eye ball region, adjust pixel in first area
Pixel value, wherein, the first area is:Region in second area in addition to the black eye ball region, described second
Region is:Border circular areas in eyes region using the black eye ball's dead center as origin, using the adjustment radius as radius.
In specific implementation provided in an embodiment of the present invention, when the target face characteristic portion is chin,
The processing module, specifically for the pixel value using first kind pixel, adjust second in chin region
The pixel value of class pixel, wherein, the second class pixel includes:The edge pixel point of chin region, chin place
It is less than the pixel of the first preset value in region with the distance between the edge pixel point, the first kind pixel is:The
It is less than the pixel of the second preset value in three regions with the distance between the edge pixel point, the 3rd region is:It is described
Region in facial image in addition to chin region.
In specific implementation provided in an embodiment of the present invention, when the target face characteristic portion is face, the place
Module is managed, specifically for grinding skin algorithm and/or whitening algorithm using default, to the feature where the target face characteristic portion
Region carries out image procossing.
The embodiment of the present invention additionally provides a kind of electronic equipment, including processor, communication interface, memory and communication are always
Line, wherein, processor, communication interface, memory completes mutual communication by communication bus;
Memory, for depositing computer program;
Processor, during for performing the program deposited on memory, realize described method and step.
The embodiment of the present invention additionally provides a kind of computer-readable recording medium, the computer-readable recording medium internal memory
Computer program is contained, described method and step is realized when the computer program is executed by processor.
A kind of image processing method, device, electronic equipment and storage medium provided in an embodiment of the present invention, obtain pending
Facial image;Determine the characteristic area where target face characteristic portion in the facial image;Using the target face
U.S. face algorithm is preset corresponding to characteristic portion, image procossing is carried out to the characteristic area where the target face characteristic portion.
In the embodiment of the present invention, phase only is carried out to the characteristic area where the target face characteristic portion in facial image
The image procossing of Ying Meiyan algorithms, without needing to handle all areas in facial image as in the prior art, because
This, the embodiment of the present invention can reduce the waste of computing resource during face image processing.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the flow chart of image processing method provided in an embodiment of the present invention;
Fig. 2 is the structural representation of image processing apparatus provided in an embodiment of the present invention;
Fig. 3 is the structural representation of electronic equipment provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
To reach above-mentioned purpose, the embodiments of the invention provide a kind of image processing method.This method can be applied to electronics
Equipment (such as smart mobile phone, tablet personal computer, intelligent robot), the electronic equipment can be provided with the class of taking pictures with U.S. face function
Client;
Fig. 1 is the flow chart of image processing method provided in an embodiment of the present invention, and methods described comprises the following steps S110
~step S130:
S110, obtain pending facial image.
The application scenarios of the present embodiment can be:User shoots oneself or its using the class client of taking pictures in electronic equipment
The face of his user, and landscaping treatment, certainly, application scenarios are carried out to captured image using the U.S. face function of client
It can be that electronic equipment selects a locally stored facial image, and landscaping treatment etc. is carried out to selected facial image
Deng the application is only illustrated as example, and concrete application scene is not limited to that.
Specifically, above-mentioned pending facial image can be that electronic equipment obtains to captured face progress IMAQ
, it can also be from the image that is locally stored and carry out what image selection obtained etc..
It should be noted that face is not only included in pending facial image, it is also possible to comprising on human body remove face it
Other outer positions (such as neck, chest) or the background (such as wall, trees) of human body.
S120, determine the characteristic area where target face characteristic portion in the facial image.
Specifically, after pending facial image being got in electronic equipment, face recognition algorithms can be used to face
Image is identified, and identifies the characteristic area where target face characteristic portion corresponding to the U.S. face function of this in facial image.
In the present embodiment, target face characteristic portion can be at least one of following position:Eyes, eyebrow, face,
Nose, ear, chin, face.
For example, when target face characteristic portion is eyes, eyes location in electronic equipment identification facial image
Domain;When target face characteristic portion is chin, chin region in electronic equipment identification facial image;When target face is special
When sign position is eyes and chin, eyes region and chin region in electronic equipment identification facial image.
S130, using U.S. face algorithm is preset corresponding to the target face characteristic portion, to the target face features
Characteristic area where position carries out image procossing.
U.S. face algorithm can be understood as:The algorithm of landscaping treatment is carried out to the appearance of people.Specifically, U.S. face algorithm can be
For beautifying the algorithms (for example, big eye algorithm) of eyes, the algorithm (for example, thin face algorithm) for beautifying chin, for beautifying
Algorithm (for example, whitening algorithm) of face etc..
Based on foregoing description, if target face characteristic portion is eyes, it can be big eye algorithm to preset U.S. face algorithm,
Then enter to exercise the big processing of eyes change to eyes region using big eye algorithm;If target face characteristic portion is chin,
It can be thin face algorithm then to preset U.S. face algorithm, then enters to exercise the place that chin reduces to chin region using thin face algorithm
Reason;If target face characteristic portion is face, it can be whitening algorithm to preset U.S. face algorithm, then using whitening algorithm to face institute
Enter to exercise the processing that face bleaches in region.
, can be by the picture in this feature region when the characteristic area where to target face characteristic portion carries out image procossing
The pixel value of vegetarian refreshments is adjusted, by each pixel in this feature region before each pixel pixel value replacement adjustment after adjustment
Pixel value.After the completion of image procossing, the facial image after processing is shown, the face figure after beautification can be seen in user
Picture.
It should be noted that target face characteristic portion can be a few individual positions (such as eyes and eyebrow), it is determined that
Characteristic area in facial image where target face characteristic portion is the region at these positions, using for each portion
The default U.S. face algorithm of position carries out image procossing to the region at each position respectively.
In an embodiment provided by the invention, user first clicks on U.S. face function (such as big eye function), and electronic equipment is cut
Shoot function is shifted to, user shoots the face of oneself or other users, and electronic equipment obtains captured pending face figure
Picture, then identify that target face characteristic portion is (such as in facial image using face recognition algorithms:Eyes) where characteristic area
Domain, using target face characteristic portion default U.S. face algorithm (such as:Big eye algorithm), to the spy where target face characteristic portion
Levy region (such as:Eyes region) carry out image procossing.
In another embodiment provided by the invention, user selects a certain face figure prestored in electronic equipment
Picture, electronic equipment obtain the facial image, then identify target face characteristic in the facial image using face recognition algorithms
Position is (such as:Eyes) where characteristic area, using target face characteristic portion default U.S. face algorithm (such as:Big eye algorithm),
To the characteristic area where target face characteristic portion (such as:Eyes region) carry out image procossing.
Image processing method provided in an embodiment of the present invention, obtain pending facial image;Determine the facial image
Characteristic area where middle target face characteristic portion;Using the default U.S. face algorithm of the target face characteristic portion, to institute
Characteristic area where stating target face characteristic portion carries out image procossing.
In the embodiment of the present invention, phase only is carried out to the characteristic area where the target face characteristic portion in facial image
The image procossing of Ying Meiyan algorithms, without needing to handle all areas in facial image as in the prior art, because
This, the embodiment of the present invention can reduce the waste of computing resource during face image processing;Meanwhile the embodiment of the present invention also carries
High operation efficiency, makes operation more smooth, improves Consumer's Experience.
It is described to determine target face in the facial image in a kind of specific implementation provided in an embodiment of the present invention
The step of characteristic area where characteristic portion, comprise the following steps A1~step A2:
A1, extract from the facial image characteristic point for characterizing target face characteristic portion.
Specifically, facial image can be identified using face recognition algorithms, with identification in face recognition algorithms
The function of the characteristic point of different face characteristic portions, can recognize that the characteristic point for characterizing target face characteristic portion.Example
Such as, if target face characteristic portion is eyes, the characteristic point of eyes can be left eye angle point, right eye angle point, superior orbit summit
With inferior orbit summit.
, can also be by the way of model training, to a large amount of target face characteristics collected in other implementations
The sign point data at position is trained, and obtains training pattern, is used to characterize mesh in facial image to identify using the training pattern
Mark the characteristic point at face characteristic position.
A2, the characteristic point area defined that will be extracted, the feature being defined as where the target face characteristic portion
Region.
Specifically, after the characteristic point of target face characteristic portion is obtained, characteristic point area defined is defined as
Characteristic area where target face characteristic portion.
It should be noted that characteristic point area defined may be irregular region, in order to further reduce calculating
Amount, in the range of error permission, the boundary rectangle frame in selected characteristic region, using default U.S. face algorithm accordingly to the rectangle
Inframe region carries out image procossing.For example, big eye algorithm can be calculated two pieces of rectangular areas of covering right and left eyes;Thin face is calculated
Method can be calculated the rectangular area for covering chin;Whitening algorithm can be counted to the rectangular area for covering whole face
Calculate.
It is eyes in the target face characteristic portion in a kind of specific implementation provided in an embodiment of the present invention
When, the default U.S. face algorithm using the target face characteristic portion, to the spy where the target face characteristic portion
The step of region carries out image procossing is levied, comprises the following steps B1~step B4:
B1, black eye ball region is searched in eyes region;
Specifically, black eye ball region can be searched from eyes region using face recognition algorithms;Or by
In the color of the pixel of black eye ball region be black, therefore where can finding black eye ball according to the pixel value of pixel
Region.
B2, based on the black eye ball region, determine black eye ball's dead center and the black eye radius of a ball;
Specifically, black eye ball region can be considered as to the border circular areas of rule, the circle is determined using geometric algorithm
The center in domain and the radius of the border circular areas.
B3, determine that adjustment radius is the numerical value more than the black eye radius of a ball;
In the present embodiment, adjustment radius is some numerical value more than the black eye radius of a ball, the numerical value and the black eye radius of a ball
Size of the difference can freely be set.For example, if the black eye radius of a ball is the length of 50 pixels, it is true radius will can be adjusted
It is set to the length of 60 pixels or the length of 70 pixels.
B4, the pixel value using pixel in black eye ball region, the pixel value of pixel in first area is adjusted, its
In, the first area is:Region in second area in addition to the black eye ball region, the second area are:Eyes
Border circular areas in region using the black eye ball's dead center as origin, using the adjustment radius as radius.
Specifically, after radius is adjusted, determined from eyes region using black eye ball's dead center as origin, with tune
Whole radius is the border circular areas (i.e. second area) of radius, and the second area can be slightly larger than black eye ball region;Then, it is determined that
Region (i.e. first area) in second area in addition to the black eye ball region, the region can be considered annular region;Finally,
Using the pixel value of pixel in black eye ball region, the pixel value of pixel in first area is adjusted.
In the present embodiment, the pixel value of pixel in first area directly can be adjusted to pixel in black eye ball region
The pixel value of point;Change of the pixel value of pixel in black eye ball region from regional center to edges of regions can also be calculated
Rate, the pixel value of pixel in first area is calculated according to the rate of change and is adjusted.It should be noted that in order to ensure U.S.
After change facial image authenticity, it is necessary to limit adjustment radius size, second area is located in eyes region.
In the present embodiment, using the pixel value of pixel in black eye ball region, pixel in first area is adjusted
Pixel value, make the pixel in first area similar to pixel in black eye ball region, make the people after the processing of user's sensation
Eyes in face image become big, so as to reach the effect of big eye.
It is chin in the target face characteristic portion in a kind of specific implementation provided in an embodiment of the present invention
When, the default U.S. face algorithm using the target face characteristic portion, to the spy where the target face characteristic portion
The step of region carries out image procossing is levied, including:
Using the pixel value of first kind pixel, the pixel value of the second class pixel in adjustment chin region, wherein,
The second class pixel includes:In the edge pixel point of chin region, chin region with the edge pixel point
The distance between be less than the pixel of the first preset value, the first kind pixel is:In 3rd region with the edge pixel
The distance between point is less than the pixel of the second preset value, and the 3rd region is:Chin location is removed in the facial image
Region beyond domain.
In the present embodiment, first kind pixel represents the pixel in a certain thickness range of chin edge in the 3rd region
Point, the thickness range can be characterized by the size of the second preset value.The big I fixed setting of second preset value, also can basis
The diverse location of chin sets different numerical value.For example, the second preset value corresponding at immediately below chin can be set to 10 pictures
The length of vegetarian refreshments, the second preset value corresponding at chin both sides can be set to the length of 20 pixels.
It should be noted that user is the region where neck when taking pictures, immediately below chin, the both sides of chin
May be the background (such as wall, trees) of human body, then the 3rd region can be neck region or background area.
In the present embodiment, the second class pixel is represented in chin region in a certain thickness range of chin edge
Pixel, the thickness range can be characterized by the size of the first preset value.The big I fixed setting of first preset value, also may be used
Different numerical value is set according to the diverse location of chin.For example, the first preset value corresponding at immediately below chin can be set to 30
The length of individual pixel, the first preset value corresponding at chin both sides can be set to the length of 40 pixels.
Specifically, the pixel value of the second class pixel in chin region can be directly adjusted to first kind pixel
Pixel value;Also the pixel value ecto-entad that first kind pixel can be calculated (points to chin edge from the outside at chin edge
Direction) rate of change, according to the rate of change calculate first kind pixel pixel value and be adjusted.
In the present embodiment, using the pixel value of first kind pixel, the second class pixel in chin region is adjusted
Pixel value, the pixel of chin edge can be made similar to first kind pixel, made in the facial image after the processing of user's sensation
Chin it is thin, so as to reach the effect of thin face.
In a kind of specific implementation provided in an embodiment of the present invention, when the target face characteristic portion is face,
The default U.S. face algorithm using the target face characteristic portion, to the characteristic area where the target face characteristic portion
Domain is carried out the step of image procossing, including:
Using default mill skin algorithm and/or whitening algorithm, the characteristic area where the target face characteristic portion is entered
Row image procossing.
Mill skin algorithm refers to:Point miscellaneous to the color spot on skin, black mole etc. is purged, and makes the algorithm that skin is more smooth.
Whitening algorithm refers to:By the way that the color of skin is bleached, brightness become strong, make the algorithm that skin is more pale.
In the present embodiment, figure is carried out to the characteristic area where the target face characteristic portion using default mill skin algorithm
As the process of processing can be:Pixel in characteristic area where target face characteristic portion is divided into multiple subcharacters
Region, the pixel value of each pixel in each subcharacter region is averaged.The process makes each subcharacter region
Pixel is similar, makes the face in the facial image after the processing of user's sensation more smooth, so as to reach landscaping effect.
Using default whitening algorithm, to the mistake of the characteristic area progress image procossing where the target face characteristic portion
Journey can be:By the pixel value of the pixel in the characteristic area where target face characteristic portion, to the pixel value side of white
To being finely adjusted;The brightness of pixel in characteristic area where target face characteristic portion can also be lightened.The process
The face in the facial image after the processing of user's sensation is set to bleach, so as to reach the effect of whitening.
In the embodiment of the present invention, the process of recognition of face can be carried out in advance, then perform image provided by the invention again
Processing method, so as to avoid expense caused by operation recognition of face.
Corresponding with above method embodiment, the embodiment of the present invention additionally provides a kind of image processing apparatus.Fig. 2 is this
The structural representation for the image processing apparatus that inventive embodiments provide, described device include:
Acquisition module 210, for obtaining pending facial image;
Determining module 220, for determining the characteristic area in the facial image where target face characteristic portion;
Processing module 230, U.S. face algorithm is preset corresponding to the target face characteristic portion for using, to the target
Characteristic area where face characteristic position carries out image procossing.
Image processing apparatus provided in an embodiment of the present invention, only to where the target face characteristic portion in facial image
Characteristic area carry out the image procossing of corresponding U.S. face algorithm, without being needed as in the prior art to all in facial image
Region is handled, and therefore, the embodiment of the present invention can reduce the waste of computing resource during face image processing;Meanwhile
The embodiment of the present invention also improves operation efficiency, makes operation more smooth, improves Consumer's Experience.
In specific implementation provided in an embodiment of the present invention, the determining module, including:
Extraction unit, for extracting the characteristic point for characterizing target face characteristic portion from the facial image;
First determining unit, for the characteristic point area defined that will be extracted, it is defined as the target face characteristic
Characteristic area where position.
In specific implementation provided in an embodiment of the present invention, the target face characteristic portion is with lower portion
It is at least one:
Eyes, eyebrow, face, nose, ear, chin, face.
In specific implementation provided in an embodiment of the present invention, when the target face characteristic portion is eyes, institute
Processing module is stated, including:
Searching unit, for searching black eye ball region in eyes region;
Second determining unit, for based on the black eye ball region, determining black eye ball's dead center and the black eye radius of a ball;
3rd determining unit, for determining that adjustment radius is the numerical value more than the black eye radius of a ball;
Adjustment unit, for the pixel value using pixel in black eye ball region, adjust pixel in first area
Pixel value, wherein, the first area is:Region in second area in addition to the black eye ball region, described second
Region is:Border circular areas in eyes region using the black eye ball's dead center as origin, using the adjustment radius as radius.
In specific implementation provided in an embodiment of the present invention, when the target face characteristic portion is chin,
The processing module, specifically for the pixel value using first kind pixel, adjust second in chin region
The pixel value of class pixel, wherein, the second class pixel includes:The edge pixel point of chin region, chin place
It is less than the pixel of the first preset value in region with the distance between the edge pixel point, the first kind pixel is:The
It is less than the pixel of the second preset value in three regions with the distance between the edge pixel point, the 3rd region is:It is described
Region in facial image in addition to chin region.
It is described when the target face characteristic portion is face in specific implementation provided in an embodiment of the present invention
Processing module, specifically for grinding skin algorithm and/or whitening algorithm using default, to the spy where the target face characteristic portion
Levy region and carry out image procossing.
Corresponding with above method embodiment, the embodiment of the present invention additionally provides a kind of electronic equipment.Fig. 3 is the present invention
The structural representation for the electronic equipment that embodiment provides, the electronic equipment include processor 310, communication interface 320, memory
330 and communication bus 340, wherein, processor 310, communication interface 320, memory 330 completed mutually by communication bus 340
Between communication,
Memory 330, for depositing computer program;
Processor 310, during for performing the program deposited on memory 330, realize that the present invention implements the image provided
Processing method.
Specifically, above-mentioned image processing method includes:
Obtain pending facial image;
Determine the characteristic area where target face characteristic portion in the facial image;
Using U.S. face algorithm is preset corresponding to the target face characteristic portion, to where the target face characteristic portion
Characteristic area carry out image procossing.
Electronic equipment provided in an embodiment of the present invention, only to the spy where the target face characteristic portion in facial image
The image procossing that region carries out corresponding U.S. face algorithm is levied, without being needed as in the prior art to all areas in facial image
Handled, therefore, the embodiment of the present invention can reduce the waste of computing resource during face image processing;Meanwhile this hair
Bright embodiment also improves operation efficiency, makes operation more smooth, improves Consumer's Experience.
The image procossing mode that other implementations of above-mentioned image processing method provide with preceding method embodiment part
It is identical, repeat no more here.
The communication bus that above-mentioned electronic equipment is mentioned can be Peripheral Component Interconnect standard (Peripheral Component
Interconnect, PCI) bus or EISA (Extended Industry Standard
Architecture, EISA) bus etc..The communication bus can be divided into address bus, data/address bus, controlling bus etc..For just
Only represented in expression, figure with a thick line, it is not intended that an only bus or a type of bus.
The communication that communication interface is used between above-mentioned electronic equipment and other equipment.
Memory can include random access memory (Random Access Memory, RAM), can also include non-easy
The property lost memory (Non-Volatile Memory, NVM), for example, at least a magnetic disk storage.Optionally, memory may be used also
To be at least one storage device for being located remotely from aforementioned processor.
Above-mentioned processor can be general processor, including central processing unit (Central Processing Unit,
CPU), network processing unit (Network Processor, NP) etc.;It can also be digital signal processor (Digital Signal
Processing, DSP), it is application specific integrated circuit (Application Specific Integrated Circuit, ASIC), existing
It is field programmable gate array (Field-Programmable Gate Array, FPGA) or other PLDs, discrete
Door or transistor logic, discrete hardware components.
Corresponding with above method embodiment, the embodiment of the present invention additionally provides a kind of computer-readable recording medium,
The computer-readable recording medium internal memory contains computer program, and the computer program realizes this hair when being executed by processor
The bright image processing method for implementing to provide.
Specifically, above-mentioned image processing method includes:
Obtain pending facial image;
Determine the characteristic area where target face characteristic portion in the facial image;
Using U.S. face algorithm is preset corresponding to the target face characteristic portion, to where the target face characteristic portion
Characteristic area carry out image procossing.
The application program stored in storage medium provided in an embodiment of the present invention operationally, only in facial image
Characteristic area where target face characteristic portion carries out the image procossing of corresponding U.S. face algorithm, without as in the prior art
Need to handle all areas in facial image, therefore, the embodiment of the present invention can be reduced during face image processing
The waste of computing resource;Meanwhile the embodiment of the present invention also improves operation efficiency, make operation more smooth, improve user's body
Test.
The image procossing mode that other implementations of above-mentioned image processing method provide with preceding method embodiment part
It is identical, repeat no more here.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.
Each embodiment in this specification is described by the way of related, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.Especially for device,
For electronic equipment and storage medium embodiment, because it is substantially similar to embodiment of the method, so fairly simple, the phase of description
Part is closed referring to the part of embodiment of the method to illustrate.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent substitution and improvements made within the spirit and principles in the present invention etc., are all contained in protection scope of the present invention
It is interior.
Claims (10)
1. a kind of image processing method, it is characterised in that methods described includes:
Obtain pending facial image;
Determine the characteristic area where target face characteristic portion in the facial image;
Using U.S. face algorithm is preset corresponding to the target face characteristic portion, to the spy where the target face characteristic portion
Levy region and carry out image procossing.
2. according to the method for claim 1, it is characterised in that described to determine target face features in the facial image
The step of characteristic area at position place, including:
The characteristic point for characterizing target face characteristic portion is extracted from the facial image;
The characteristic point area defined that will be extracted, the characteristic area being defined as where the target face characteristic portion.
3. method according to claim 1 or 2, it is characterised in that the target face characteristic portion is with lower portion
At least one:
Eyes, eyebrow, face, nose, ear, chin, face.
4. according to the method for claim 3, it is characterised in that described when the target face characteristic portion is eyes
Using the default U.S. face algorithm of the target face characteristic portion, the characteristic area where the target face characteristic portion is entered
The step of row image procossing, including:
Black eye ball region is searched in eyes region;
Based on the black eye ball region, black eye ball's dead center and the black eye radius of a ball are determined;
It is determined that adjustment radius is the numerical value more than the black eye radius of a ball;
Using the pixel value of pixel in black eye ball region, the pixel value of pixel in first area is adjusted, wherein, it is described
First area is:Region in second area in addition to the black eye ball region, the second area are:Eyes region
In using the black eye ball's dead center as origin, using it is described adjustment radius as radius border circular areas.
5. according to the method for claim 3, it is characterised in that described when the target face characteristic portion is chin
Using the default U.S. face algorithm of the target face characteristic portion, the characteristic area where the target face characteristic portion is entered
The step of row image procossing, including:
Using the pixel value of first kind pixel, the pixel value of the second class pixel in adjustment chin region, wherein, it is described
Second class pixel includes:In the edge pixel point of chin region, chin region between the edge pixel point
Distance be less than the pixel of the first preset value, the first kind pixel is:In 3rd region with the edge pixel point it
Between distance be less than the second preset value pixel, the 3rd region is:In the facial image except chin region with
Outer region.
6. according to the method for claim 3, it is characterised in that described to adopt when the target face characteristic portion is face
With the default U.S. face algorithm of the target face characteristic portion, the characteristic area where the target face characteristic portion is carried out
The step of image procossing, including:
Using default mill skin algorithm and/or whitening algorithm, figure is carried out to the characteristic area where the target face characteristic portion
As processing.
7. a kind of image processing apparatus, it is characterised in that described device includes:
Acquisition module, for obtaining pending facial image;
Determining module, for determining the characteristic area in the facial image where target face characteristic portion;
Processing module, U.S. face algorithm is preset corresponding to the target face characteristic portion for using, it is special to the target face
Characteristic area where levying position carries out image procossing.
8. device according to claim 7, it is characterised in that the determining module, including:
Extraction unit, for extracting the characteristic point for characterizing target face characteristic portion from the facial image;
First determining unit, for the characteristic point area defined that will be extracted, it is defined as the target face characteristic portion
The characteristic area at place.
9. the device according to claim 7 or 8, it is characterised in that the target face characteristic portion is with lower portion
At least one:
Eyes, eyebrow, face, nose, ear, chin, face.
10. device according to claim 9, it is characterised in that described when the target face characteristic portion is eyes
Processing module, including:
Searching unit, for searching black eye ball region in eyes region;
Second determining unit, for based on the black eye ball region, determining black eye ball's dead center and the black eye radius of a ball;
3rd determining unit, for determining that adjustment radius is the numerical value more than the black eye radius of a ball;
Adjustment unit, for using the pixel value of pixel in black eye ball region, adjust the picture of pixel in first area
Element value, wherein, the first area is:Region in second area in addition to the black eye ball region, the second area
For:Border circular areas in eyes region using the black eye ball's dead center as origin, using the adjustment radius as radius.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710665959.0A CN107578380A (en) | 2017-08-07 | 2017-08-07 | Image processing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710665959.0A CN107578380A (en) | 2017-08-07 | 2017-08-07 | Image processing method and device, electronic equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107578380A true CN107578380A (en) | 2018-01-12 |
Family
ID=61035636
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710665959.0A Pending CN107578380A (en) | 2017-08-07 | 2017-08-07 | Image processing method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107578380A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108346130A (en) * | 2018-03-20 | 2018-07-31 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108364254A (en) * | 2018-03-20 | 2018-08-03 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108389155A (en) * | 2018-03-20 | 2018-08-10 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108399599A (en) * | 2018-03-20 | 2018-08-14 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108447023A (en) * | 2018-03-20 | 2018-08-24 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108491780A (en) * | 2018-03-16 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image landscaping treatment method, apparatus, storage medium and terminal device |
CN108564531A (en) * | 2018-05-08 | 2018-09-21 | 麒麟合盛网络技术股份有限公司 | A kind of image processing method and device |
CN108632535A (en) * | 2018-07-26 | 2018-10-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN109087239A (en) * | 2018-07-25 | 2018-12-25 | 腾讯科技(深圳)有限公司 | A kind of face image processing process, device and storage medium |
CN109086761A (en) * | 2018-06-28 | 2018-12-25 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium, electronic equipment |
CN109242765A (en) * | 2018-08-31 | 2019-01-18 | 腾讯科技(深圳)有限公司 | A kind of face image processing process, device and storage medium |
CN109255763A (en) * | 2018-08-28 | 2019-01-22 | 百度在线网络技术(北京)有限公司 | Image processing method, device, equipment and storage medium |
CN109376618A (en) * | 2018-09-30 | 2019-02-22 | 北京旷视科技有限公司 | Image processing method, device and electronic equipment |
CN109584153A (en) * | 2018-12-06 | 2019-04-05 | 北京旷视科技有限公司 | Modify the methods, devices and systems of eye |
CN109815821A (en) * | 2018-12-27 | 2019-05-28 | 北京旷视科技有限公司 | A kind of portrait tooth method of modifying, device, system and storage medium |
CN110555806A (en) * | 2018-05-31 | 2019-12-10 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110555794A (en) * | 2018-05-31 | 2019-12-10 | 北京市商汤科技开发有限公司 | image processing method and device, electronic equipment and storage medium |
WO2020057667A1 (en) * | 2018-09-21 | 2020-03-26 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, and computer storage medium |
WO2021120626A1 (en) * | 2019-12-16 | 2021-06-24 | 上海传英信息技术有限公司 | Image processing method, terminal, and computer storage medium |
CN113572955A (en) * | 2021-06-25 | 2021-10-29 | 维沃移动通信(杭州)有限公司 | Image processing method and device and electronic equipment |
CN113781295A (en) * | 2021-09-14 | 2021-12-10 | 网易(杭州)网络有限公司 | Image processing method, device, equipment and storage medium |
US11410268B2 (en) | 2018-05-31 | 2022-08-09 | Beijing Sensetime Technology Development Co., Ltd | Image processing methods and apparatuses, electronic devices, and storage media |
CN115348709A (en) * | 2022-10-18 | 2022-11-15 | 良业科技集团股份有限公司 | Smart cloud service lighting display method and system suitable for text travel |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104992402A (en) * | 2015-07-02 | 2015-10-21 | 广东欧珀移动通信有限公司 | Facial beautification processing method and device |
CN105184249A (en) * | 2015-08-28 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Method and device for processing face image |
CN105654420A (en) * | 2015-12-21 | 2016-06-08 | 小米科技有限责任公司 | Face image processing method and device |
CN105787878A (en) * | 2016-02-25 | 2016-07-20 | 杭州格像科技有限公司 | Beauty processing method and device |
CN106909892A (en) * | 2017-01-24 | 2017-06-30 | 珠海市魅族科技有限公司 | A kind of image processing method and system |
-
2017
- 2017-08-07 CN CN201710665959.0A patent/CN107578380A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104992402A (en) * | 2015-07-02 | 2015-10-21 | 广东欧珀移动通信有限公司 | Facial beautification processing method and device |
CN105184249A (en) * | 2015-08-28 | 2015-12-23 | 百度在线网络技术(北京)有限公司 | Method and device for processing face image |
CN105654420A (en) * | 2015-12-21 | 2016-06-08 | 小米科技有限责任公司 | Face image processing method and device |
CN105787878A (en) * | 2016-02-25 | 2016-07-20 | 杭州格像科技有限公司 | Beauty processing method and device |
CN106909892A (en) * | 2017-01-24 | 2017-06-30 | 珠海市魅族科技有限公司 | A kind of image processing method and system |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491780A (en) * | 2018-03-16 | 2018-09-04 | 广东欧珀移动通信有限公司 | Image landscaping treatment method, apparatus, storage medium and terminal device |
CN108491780B (en) * | 2018-03-16 | 2021-05-04 | Oppo广东移动通信有限公司 | Image beautification processing method and device, storage medium and terminal equipment |
CN108346130A (en) * | 2018-03-20 | 2018-07-31 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108364254A (en) * | 2018-03-20 | 2018-08-03 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108389155A (en) * | 2018-03-20 | 2018-08-10 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108399599A (en) * | 2018-03-20 | 2018-08-14 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108447023A (en) * | 2018-03-20 | 2018-08-24 | 北京奇虎科技有限公司 | Image processing method, device and electronic equipment |
CN108447023B (en) * | 2018-03-20 | 2021-08-24 | 北京奇虎科技有限公司 | Image processing method and device and electronic equipment |
CN108364254B (en) * | 2018-03-20 | 2021-07-23 | 北京奇虎科技有限公司 | Image processing method and device and electronic equipment |
CN108346130B (en) * | 2018-03-20 | 2021-07-23 | 北京奇虎科技有限公司 | Image processing method and device and electronic equipment |
CN108389155B (en) * | 2018-03-20 | 2021-10-01 | 北京奇虎科技有限公司 | Image processing method and device and electronic equipment |
CN108399599B (en) * | 2018-03-20 | 2021-11-26 | 北京奇虎科技有限公司 | Image processing method and device and electronic equipment |
CN108564531A (en) * | 2018-05-08 | 2018-09-21 | 麒麟合盛网络技术股份有限公司 | A kind of image processing method and device |
US11410268B2 (en) | 2018-05-31 | 2022-08-09 | Beijing Sensetime Technology Development Co., Ltd | Image processing methods and apparatuses, electronic devices, and storage media |
CN110555806A (en) * | 2018-05-31 | 2019-12-10 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
CN110555794A (en) * | 2018-05-31 | 2019-12-10 | 北京市商汤科技开发有限公司 | image processing method and device, electronic equipment and storage medium |
US11216904B2 (en) | 2018-05-31 | 2022-01-04 | Beijing Sensetime Technology Development Co., Ltd. | Image processing method and apparatus, electronic device, and storage medium |
CN109086761B (en) * | 2018-06-28 | 2020-12-01 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium and electronic equipment |
CN109086761A (en) * | 2018-06-28 | 2018-12-25 | Oppo广东移动通信有限公司 | Image processing method and device, storage medium, electronic equipment |
CN109087239B (en) * | 2018-07-25 | 2023-03-21 | 腾讯科技(深圳)有限公司 | Face image processing method and device and storage medium |
CN109087239A (en) * | 2018-07-25 | 2018-12-25 | 腾讯科技(深圳)有限公司 | A kind of face image processing process, device and storage medium |
CN108632535A (en) * | 2018-07-26 | 2018-10-09 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
CN109255763A (en) * | 2018-08-28 | 2019-01-22 | 百度在线网络技术(北京)有限公司 | Image processing method, device, equipment and storage medium |
CN109242765B (en) * | 2018-08-31 | 2023-03-10 | 腾讯科技(深圳)有限公司 | Face image processing method and device and storage medium |
CN109242765A (en) * | 2018-08-31 | 2019-01-18 | 腾讯科技(深圳)有限公司 | A kind of face image processing process, device and storage medium |
CN110942422A (en) * | 2018-09-21 | 2020-03-31 | 北京市商汤科技开发有限公司 | Image processing method and device and computer storage medium |
JP2021515313A (en) * | 2018-09-21 | 2021-06-17 | ベイジン センスタイム テクノロジー デベロップメント カンパニー, リミテッド | Image processing methods, devices and computer storage media |
WO2020057667A1 (en) * | 2018-09-21 | 2020-03-26 | 北京市商汤科技开发有限公司 | Image processing method and apparatus, and computer storage medium |
JP7090169B2 (en) | 2018-09-21 | 2022-06-23 | ベイジン センスタイム テクノロジー デベロップメント カンパニー, リミテッド | Image processing methods, equipment and computer storage media |
CN109376618A (en) * | 2018-09-30 | 2019-02-22 | 北京旷视科技有限公司 | Image processing method, device and electronic equipment |
CN109584153A (en) * | 2018-12-06 | 2019-04-05 | 北京旷视科技有限公司 | Modify the methods, devices and systems of eye |
CN109815821A (en) * | 2018-12-27 | 2019-05-28 | 北京旷视科技有限公司 | A kind of portrait tooth method of modifying, device, system and storage medium |
WO2021120626A1 (en) * | 2019-12-16 | 2021-06-24 | 上海传英信息技术有限公司 | Image processing method, terminal, and computer storage medium |
CN113572955A (en) * | 2021-06-25 | 2021-10-29 | 维沃移动通信(杭州)有限公司 | Image processing method and device and electronic equipment |
CN113781295A (en) * | 2021-09-14 | 2021-12-10 | 网易(杭州)网络有限公司 | Image processing method, device, equipment and storage medium |
CN113781295B (en) * | 2021-09-14 | 2024-02-27 | 网易(杭州)网络有限公司 | Image processing method, device, equipment and storage medium |
CN115348709A (en) * | 2022-10-18 | 2022-11-15 | 良业科技集团股份有限公司 | Smart cloud service lighting display method and system suitable for text travel |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107578380A (en) | Image processing method and device, electronic equipment and storage medium | |
CN105787454B (en) | Method and system for biometric verification | |
CN105243371B (en) | A kind of detection method, system and the camera terminal of face U.S. face degree | |
CN107358241A (en) | Image processing method, device, storage medium and electronic equipment | |
WO2022161009A1 (en) | Image processing method and apparatus, and storage medium and terminal | |
CN104574285B (en) | One kind dispels the black-eyed method of image automatically | |
CN104992402A (en) | Facial beautification processing method and device | |
CN107527046B (en) | Unlocking control method and related product | |
CN107169458B (en) | Data processing method, device and storage medium | |
CN103268475A (en) | Skin beautifying method based on face and skin color detection | |
CN109952594A (en) | Image processing method, device, terminal and storage medium | |
CN107395960A (en) | Photographic method and device, computer installation and computer-readable recording medium | |
CN104346136A (en) | Method and device for picture processing | |
CN107578371A (en) | Image processing method and device, electronic equipment and medium | |
CN106971164A (en) | Shape of face matching process and device | |
CN112036209A (en) | Portrait photo processing method and terminal | |
CN111179156B (en) | Video beautifying method based on face detection | |
WO2017173578A1 (en) | Image enhancement method and device | |
CN107992816B (en) | Photographing search method and device, electronic equipment and computer readable storage medium | |
CN114187166A (en) | Image processing method, intelligent terminal and storage medium | |
CN105931204A (en) | Image restoring method and system | |
CN108564537A (en) | Method, apparatus, electronic equipment and the medium of image procossing | |
CN110310318B (en) | Special effect processing method and device, storage medium and terminal | |
CN114972014A (en) | Image processing method and device and electronic equipment | |
CN109886186A (en) | A kind of face identification method and device |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180112 |