CN107358241A - Image processing method, device, storage medium and electronic equipment - Google Patents
Image processing method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN107358241A CN107358241A CN201710526347.3A CN201710526347A CN107358241A CN 107358241 A CN107358241 A CN 107358241A CN 201710526347 A CN201710526347 A CN 201710526347A CN 107358241 A CN107358241 A CN 107358241A
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- destination object
- local area
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method, device, storage medium and electronic equipment.The image processing method, by obtaining target image, and the destination object in recognition target image, then the local area image on destination object is determined, and obtains the characteristics of image of local area image, pre-set image feature corresponding to destination object is then obtained from default characteristic set, again by characteristics of image compared with pre-set image feature corresponding to destination object, comparative result is obtained, is finally handled according to comparative result localized region image, with the target image after being handled.Characteristics of image of the program based on image and the comparative result of pre-set image feature, are pointedly handled image, improve the accuracy and validity of image procossing.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of image processing method, device, storage medium and electricity
Sub- equipment.
Background technology
With the development of internet and the development of mobile communications network, at the same also along with electronic equipment disposal ability and
The fast development of storage capacity, the application program of magnanimity have obtained rapid propagation and use.It is especially related to image procossing
Using its image processing function is stronger and stronger.At present, many camera application programs provide conveniently photo beautification work(
Can, it is only necessary to which shirtsleeve operation can be realized as the instant optimization of photo effect.
The content of the invention
The embodiment of the present invention provides a kind of image processing method, device, storage medium and electronic equipment, can lift image
The accuracy and validity of processing.
In a first aspect, the embodiment of the present invention provides a kind of image processing method, including：
Target image is obtained, and identifies the destination object in the target image；
The local area image on the destination object is determined, and obtains the characteristics of image of the local area image；
Pre-set image feature corresponding to the destination object is obtained from default characteristic set；
By described image feature compared with pre-set image feature corresponding to the destination object, comparative result is obtained；
The local area image is handled according to the comparative result, with the target image after being handled.
Second aspect, the embodiments of the invention provide a kind of image processing apparatus, including：
Identification module, for obtaining target image, and identify the destination object in the target image；
Determining module, for determining the local area image on the destination object, and obtain the local area image
Characteristics of image；
Acquisition module, for obtaining pre-set image feature corresponding to the destination object from default characteristic set；
Comparison module, for by described image feature compared with pre-set image feature corresponding to the destination object,
Obtain comparative result；
Processing module, for being handled according to the comparative result the local area image, after obtaining processing
Target image.
The third aspect, the embodiment of the present invention additionally provide a kind of storage medium, a plurality of finger are stored with the storage medium
Order, the instruction are suitable to be loaded by processor to perform above-mentioned image processing method.
Fourth aspect, the embodiment of the present invention additionally provide a kind of electronic equipment, including processor, memory, the processing
Device is electrically connected with the memory, and the memory is used for store instruction and data；Processor is used to perform above-mentioned image
Processing method.
The embodiment of the invention discloses a kind of image processing method, device, storage medium and electronic equipment.The image procossing
Method, by obtaining target image, and the destination object in recognition target image, then determine the regional area on destination object
Image, and the characteristics of image of local area image is obtained, then obtain corresponding to destination object and preset from default characteristic set
Characteristics of image, then by characteristics of image compared with pre-set image feature corresponding to destination object, obtain comparative result, last root
Handled according to comparative result localized region image, with the target image after being handled.Image of the program based on image
The comparative result of feature and pre-set image feature, is pointedly handled image, improve the accuracy of image procossing with
Validity.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, make required in being described below to embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those skilled in the art, on the premise of not paying creative work, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of scene framework schematic diagram of image processing system provided in an embodiment of the present invention.
Fig. 2 is a kind of schematic flow sheet of image processing method provided in an embodiment of the present invention.
Fig. 3 is a kind of application scenario diagram of image processing method provided in an embodiment of the present invention.
Fig. 4 is another application scenario diagram of image processing method provided in an embodiment of the present invention.
Fig. 5 is another schematic flow sheet of image processing apparatus provided in an embodiment of the present invention.
Fig. 6 is a kind of structural representation of image processing apparatus provided in an embodiment of the present invention.
Fig. 7 is another structural representation of image processing apparatus provided in an embodiment of the present invention.
Fig. 8 is a kind of structural representation of electronic equipment provided in an embodiment of the present invention.
Fig. 9 is another 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, the every other implementation that those skilled in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
The embodiment of the present invention provides a kind of image processing method, device, storage medium and electronic equipment.It will enter respectively below
Row describes in detail.
Please with reference first to Fig. 1, Fig. 1 is that a kind of scene framework of image processing system provided in an embodiment of the present invention is illustrated
Figure, including electronic equipment and server, electronic equipment and server are established by internet and communicated to connect.
When user is handled image by the image processing function in electronic equipment, the recordable processing of electronic equipment
During inputoutput data, then, to server send record data, wherein, electronic equipment can use WEB modes to
Server sends data, can also send data to server by the client-side program installed in electronic equipment.Server is received
Collect the data that multiple electronic equipments are sent, handled based on machine deep learning receiving data, generation meets popular examine
The reference data of image procossing attractive in appearance, the reference data that can obtain image procossing by electronic equipment so as to user are entered to image
Row processing.
It can be, but not limited between electronic equipment and server using any of following host-host protocol：HTTP
(Hypertexttransferprotocol, HTTP), FTP (FileTransferProtocol, file transmission
Agreement), P2P (PeertoPeer, peer-to-peer network), P2SP (PeertoServer＆Peer, putting to server and point) etc..
Electronic equipment can be mobile terminal, such as mobile phone, tablet personal computer, or traditional PC
(PersonalComputer, PC) etc., the embodiment of the present invention is to this without limiting.
In one embodiment, there is provided a kind of image processing method, as shown in Fig. 2 flow can be as follows：
S101, obtain target image, and the destination object in recognition target image.
Wherein, target image can be character image or scene image.Destination object can be people, Ke Yishi
Thing.For example recognition of face can be carried out to target image, can be by the human body where the face recognized when recognizing face
As the destination object in target image.Again for example, when recognize one it is colored when, can be using the flower recognized as target pair
As.
S102, local area image on destination object is determined, and obtain the characteristics of image of local area image.
Specifically, it is available and its deep learning or general image procossing mechanism etc., and combining target object is in itself,
Obtain out the local area image that notable difference be present with other regions.
In certain embodiments, destination object is who object, then step " characteristics of image for obtaining local area image "
It can include：
Who object is divided into by multiple positions according to organization of human body；
Obtain priority corresponding to each position；
Target site is chosen from multiple positions from high to low according to priority, and using the image of target site as local
Area image.
In practical application, to who object division mode can have it is a variety of.Such as if being directed to Whole Body image, can
It is divided into：Head, neck, four limbs, trunk etc..Again for example, if being directed to facial image, can be divided into：Volume, eye, nose, ear, lip, eyebrow
Etc..Specific dividing mode can divide according to the position that user's request or specific image occur.
In certain embodiments, characteristics of image includes：Color characteristic, textural characteristics, shape facility, spatial relationship are special
Sign.Color characteristic is a kind of global characteristics, describes the surface nature of image or the scenery corresponding to image-region.Textural characteristics
And a kind of global characteristics, also illustrate the surface nature of scenery corresponding to image or image-region.Shape facility is a kind of office
Portion's feature, there are two class method for expressing, one kind is contour feature, mainly for the external boundary of object；Another kind of is provincial characteristics, its
It is related to whole shape area.Spatial relation characteristics, refer to the mutual space bit between the multiple targets split in image
Put or relative direction relation, these relations can also be divided into connection/syntople, overlapping/overlapping relation and comprising/containment relationships
Deng.
Image characteristics extraction is using computer extraction image information, determines whether the point of each image belongs to an image
Feature.The result of feature extraction is that the point on image is divided into different subsets, and these subsets tend to belong to isolated point, continuous
Curve or continuous region.It is characterized in the starting point of many computer image analysis algorithms.Most important one of feature extraction
Characteristic is " repeatability ", i.e. the feature that the different images of Same Scene are extracted should be identical.
Feature extraction is a primary computing in image processing, and it checks each pixel to determine whether the pixel represents
One feature.If it is a part for a bigger algorithm, then the regional area of general check image of this algorithm
Image.As a premise computing of feature extraction, input picture is typically smoothed by Gaussian Blur core in metric space.
One or more features of image are calculated thereafter through local derivative computing.
In specific implementation process, using Fourier transform, window fourier transform method, most Wavelet Transform, a young waiter in a wineshop or an inn
Multiplication, edge direction histogram method, texture feature extraction based on Tamura textural characteristics etc., extract the figure of local area image
As feature.
S103, pre-set image feature corresponding to destination object is obtained from default characteristic set.
In certain embodiments, for the ease of different target object pre-set image feature acquisition, step is " from default spy
Collection obtains pre-set image feature corresponding to destination object in closing " it can include：
Determine the classification belonging to who object；
Pre-set image feature corresponding to the category is obtained from default characteristic set, using the pre-set image feature as target
Pre-set image feature corresponding to object.
In the embodiment of the present invention, it need to pre-establish including characteristics of image, classification and the feature of mapping relations between the two
Set.
In certain embodiments, affiliated classification may include：Male, women etc..Same type of who object, there is phase
The characteristics of image of same type, such as, male has Adam's apple, women not to have Adam's apple；Male's eyebrows, women eyebrow are thin.It is different types of
Destination object has different types of characteristics of image, and the demand of the image landscaping effect to that need to reach also differs.
Certainly, can also there are other mode classifications, for example by age be divided into：Old age, middle age, youth, teenager, childhood etc.
Deng.Specific implementation is not limited this depending on user's request.
In certain embodiments, pre-set image feature can be uploaded by server based on the deep learning of machine to electronic equipment
Processing parameter in various images before and after the processing, operating process is analyzed and study processing, identifies that all kinds of images institutes are right
The treatment effect that popular should be more inclined to, and obtained based on treatment effect extraction characteristics of image.
In order to lift image processing speed, pre-set image characteristic value can be downloaded to the memory space preserved in the electronic device
It is interior.
In certain embodiments, server can collect the image processing operations that different user is directed to a certain image, therefrom
Obtain the common images feature of same category image.For example when repairing figure software progress image procossing in using electronic equipment, lead to
Electronic equipment is crossed by the image adjustment parameter in original image, processing procedure and the image after processing, is uploaded onto the server, with
Allow server using learning algorithm to uploading various view data, operation data is analyzed and study is handled.Server
By the processing procedure voluntarily analyzed and learnt, the popular processing effect being more inclined to corresponding to different classes of image is identified
Fruit, and based on treatment effect extraction characteristics of image, classification and the mapping relations of characteristics of image are established, to obtain characteristic set.
In specific implementation process, when passing view data, operation data to server on an electronic device, it can will be similar to that
The operation that " key U.S. face " " automatic U.S. figure " etc. automatically processes image filters out, and then true idea of being more close to the users
Data.
S104, by characteristics of image compared with pre-set image feature corresponding to destination object, obtain comparative result.
In certain embodiments, step " by characteristics of image compared with pre-set image feature corresponding to destination object, obtains
To comparative result " it may include below scheme：
The pre-set image feature is analyzed, obtains the First Eigenvalue；
The characteristics of image is analyzed, obtains Second Eigenvalue；
By the First Eigenvalue compared with Second Eigenvalue, feature difference is calculated, using feature difference as comparative result.
Wherein, characteristic value is the quantized data value to each characteristics of image, can be based on associated picture algorithm to characteristics of image
Parsed, and be calculated by binary conversion treatment.
S105, handled according to comparative result localized region image, with the target image after being handled.
In certain embodiments, comparative result as described above is the feature difference of the First Eigenvalue and Second Eigenvalue, then
Step " being handled according to comparative result local area image " includes：
The image adjustment parameter according to corresponding to obtaining feature difference；
The characteristics of image of local area image is adjusted according to image adjustment parameter.
In certain embodiments, step " characteristics of image that local area image is adjusted according to image adjustment parameter " may include
Below scheme：
Color characteristic figure layer, textural characteristics figure layer, shape facility figure layer and space is extracted from local area image to close
It is feature figure layer, obtains feature figure layer set；
Target signature figure layer is chosen according to adjusting parameter from feature figure layer set to be adjusted；
Unchecked feature figure layer in target signature figure layer after adjustment and characteristic set is synthesized.
Each figure layer is made up of many pixels, and figure layer forms whole figure further through the mode being superimposed up and down
Picture.For example so that local area image is " eyes " as an example, color characteristic figure layer (such as Asians and westerner are extracted from eyes
The difference of eye color), textural characteristics figure layer (texture such as spot, filament, coronal, striped, crypts in iris), shape facility
Figure layer (such as slim eye, circle eye shape) and spatial relation characteristics the figure layer position of sclera (such as pupil relative to).Then, root
The feature figure layer that being chosen according to specific adjusting parameter from these feature figure layers needs to adjust is adjusted, and e.g., is led due to staying up late
Cause eyes to spread all over the trace of blood, then eyes textural characteristics figure layer can be adjusted, the trace of blood is removed.
Such as by taking skin as an example, including characteristics of image：Pale degree (color characteristic) and degree of roughness (textural characteristics),
If the quantized data value of two characteristics of image of the skin in target image is respectively：3rd, 5, and the characteristics of image of pre-set skin
Quantized data value is respectively：5th, 5, then obtaining feature difference is：2、0.Then, corresponding image is obtained according to this feature difference to adjust
Whole parameter, and pre-set image Processing Algorithm is based on, skin image is handled according to the image adjustment parameter.
When multiple local area images be present, with reference to figure 3, by taking face as an example, image (Fig. 3 left figures) bag of before processing
Include：Eyebrow A1, eyes B1, lip C1 and shape of face D1.If between eyebrow A1 characteristics of image and the pre-set image feature of eyebrow
In the absence of feature difference, existing characteristics difference a between eyes B1 characteristics of image and the pre-set image feature of eyes, lip C1 with
Existing characteristics difference b between the pre-set image feature of lip, is not present feature between shape of face D1 and the pre-set image feature of shape of face
Difference.Then feature based difference a obtains corresponding image adjustment parameter, and root respective image Processing Algorithm, according to the figure of acquisition
As adjusting parameter is handled image；Feature based difference b obtains corresponding image adjustment parameter, and according to respective image at
Adjustment method, it is adjusted according to the characteristics of image of the automatic localized region image of the image adjustment parameter of acquisition.Finally, at output
Image (Fig. 3 right figures) after reason, has carried out that big eye (referring to B2) lip type changes, lip color is deepened (refer to C2) and handled, and eyebrow A2
It is then unchanged with shape of face D2.
That is, when opening a pictures, can which position of automatic identification need to be handled, and pointedly to the portion
Position carries out image procossing, and keeps the other specification of image constant.
Such as with reference to figure 4, with reference to shown in Fig. 3, on the basis of same beautification standard, it is known that eyebrow A2 and eyebrow it is pre-
If feature difference is not present between characteristics of image, feature difference, lip are not present between eyes B2 and the pre-set image feature of eyes
Feature difference is not present between portion C2 and the pre-set image feature of lip, exists between shape of face D2 and the pre-set image feature of shape of face
Feature difference d, the then corresponding image adjustment parameter of feature based difference d acquisitions, and according to image processing algorithm, according to acquisition
Image adjustment parameter is handled image.Finally, the image (Fig. 4 right figures) after output processing, has carried out shape of face change (reference
D3) handle, and eyebrow A3, eyes B3 and shape of face lip C3 are then unchanged.
In certain embodiments, can be by the feature difference of acquisition directly as image adjustment parameter, at respective image
Adjustment method is handled according to the characteristics of image of this feature difference localized region image.
And for scene image, then can the algorithm based on character pair carry out image procossing according to feature difference, strictly according to the facts
Existing different filter processing.
From the foregoing, it will be observed that the embodiments of the invention provide a kind of image processing method, target image is obtained, and identify target figure
Destination object as in, the local area image on destination object is then determined, and obtains the characteristics of image of local area image,
Then pre-set image feature corresponding to destination object is obtained from default characteristic set, then characteristics of image is corresponding with destination object
Pre-set image feature be compared, obtain comparative result, finally handled according to comparative result localized region image, with
Target image after being handled.Characteristics of image of the program based on image and the comparative result of pre-set image feature, to image
Pointedly handled, improve the accuracy and validity of image procossing.
In one embodiment, another image processing method is also provided, as shown in figure 5, flow can be as follows：
S201, obtain target image, and the destination object in recognition target image.
Wherein, target image can be character image or scene image.Destination object can be people, Ke Yishi
Thing.For example recognition of face can be carried out to target image, can be by the human body where the face recognized when recognizing face
As the destination object in target image.
S202, local area image on destination object is determined, and obtain the characteristics of image of local area image.
Specifically, it is available and its deep learning or general image procossing mechanism etc., and combining target object is in itself,
Obtain out the local area image that notable difference be present with other regions.
In certain embodiments, so that destination object is who object as an example, then step " obtains the image of local area image
Feature " can include：
Who object is divided into by multiple positions according to organization of human body；
Obtain priority corresponding to each position；
Target site is chosen from multiple positions from high to low according to priority, and using the image of target site as local
Area image.
In practical application, to who object division mode can have it is a variety of.Such as if being directed to Whole Body image, can
It is divided into：Head, neck, four limbs, trunk etc..Again for example, if being directed to facial image, can be divided into：Volume, eye, nose, ear, lip, eyebrow
Etc..Specific dividing mode can divide according to the position that user's request or specific image occur.
In specific implementation process, using Fourier transform, window fourier transform method, most Wavelet Transform, a young waiter in a wineshop or an inn
Multiplication, edge direction histogram method etc. extract the characteristics of image of local area image.
S203, the affiliated classification for determining destination object, destination object is obtained from default characteristic set according to the category
Corresponding pre-set image feature.
In certain embodiments, affiliated classification may include：Male, women etc..Same type of who object, there is phase
The characteristics of image of same type, such as, male has Adam's apple, women not to have Adam's apple；Male's eyebrows, women eyebrow are thin.It is different types of
Destination object has different types of characteristics of image, and the demand of the image landscaping effect to that need to reach also differs.
Certainly, can also there are other mode classifications, for example by age be divided into：Old age, middle age, youth, teenager, childhood etc.
Deng.Specific implementation is not limited this depending on user's request.
In the embodiment of the present invention, it need to pre-establish including characteristics of image, classification and the feature of mapping relations between the two
Set.
In certain embodiments, server can collect the image processing operations that different user is directed to a certain image, therefrom
Obtain the common images feature of same category image.For example when repairing figure software progress image procossing in using electronic equipment, lead to
Electronic equipment is crossed by the image adjustment parameter in original image, processing procedure and the image after processing, is uploaded onto the server, with
Allow server using learning algorithm to uploading various view data, operation data is analyzed and study is handled.Server
By the processing procedure voluntarily analyzed and learnt, the popular processing effect being more inclined to corresponding to different classes of image is identified
Fruit, and based on treatment effect extraction characteristics of image, classification and the mapping relations of characteristics of image are established, to obtain characteristic set.
In order to lift image processing speed, pre-set image characteristic value can be downloaded to the memory space preserved in the electronic device
It is interior.
S205, the pre-set image feature is analyzed, obtain the First Eigenvalue, analyzed the characteristics of image, obtain Second Eigenvalue.
Wherein, characteristic value is the quantized data value to each feature.Specifically, each characteristics of image may include that more height are special
Sign, each subcharacter have corresponding characteristic value.Such as by taking features of skin colors as an example, including subcharacter：Pale degree, coarse journey
Degree, tone etc..
S206, by the First Eigenvalue compared with Second Eigenvalue, calculate feature difference.
Wherein, characteristic value is the quantized data value to each characteristics of image, can be based on associated picture algorithm to characteristics of image
Parsed, and be calculated by binary conversion treatment.
Such as by taking skin as an example, including characteristics of image：Pale degree (color characteristic) and degree of roughness (textural characteristics),
If the quantized data value of two characteristics of image of the skin in target image is respectively：3rd, 5, and the characteristics of image of pre-set skin
Quantized data value is respectively：5th, 5, then obtaining feature difference is：2、0.
S207, the image adjustment parameter according to corresponding to obtaining feature difference.
With the characteristics of image of above-mentioned skin and the feature difference of the pre-set image feature of skin：2nd, exemplified by 0, the color is obtained
Image adjustment parameter corresponding to feature difference.In practical application, a reduction formula can be designed, the feature difference of acquisition is treated such as this
Reduction formula is to obtain corresponding image adjustment parameter.
In addition, can also divide difference section, each difference section corresponds to different image adjustment parameters.By by acquisition
Feature difference is matched with the difference section set, determines image adjustment parameter corresponding to feature difference acquisition.
In certain embodiments, can be by the feature difference of acquisition directly as image adjustment parameter.
S208, according to the image adjustment parameter of acquisition adjust local area image characteristics of image, and export processing after
Image.
In certain embodiments, it is special that color characteristic figure layer, textural characteristics figure layer, shape can be extracted from local area image
Figure layer and spatial relation characteristics figure layer are levied, feature figure layer set is obtained, then, according to adjusting parameter from feature figure layer set
Target signature figure layer is chosen to be adjusted, then by unchecked feature figure layer in the target signature figure layer after adjustment and characteristic set
Synthesized, obtain final image.
When it is implemented, corresponding image processing algorithm is determined according to characteristics of image, according to the image adjustment parameter of acquisition
The characteristics of image of localized region image is adjusted, and exports the image after processing.
When multiple images feature be present, by taking face as an example, including：Features of skin colors, shape of face feature, eye feature, if skin
Feature difference is not present between color and the default colour of skin, existing characteristics difference between shape of face and default shape of face, eyes and default eyes
Between be not present feature difference, then the feature difference being based only between shape of face and default shape of face, obtain corresponding Image Adjusting ginseng
Number, and according to respective image Processing Algorithm, carried out according to the characteristics of image of the image adjustment parameter localized region image of acquisition
Adjustment, and export the image after processing.
From the foregoing, it will be observed that image processing method provided in an embodiment of the present invention, by obtaining target image, and identifies target figure
The destination object of picture, the local area image in destination object is then determined, then obtains the characteristics of image of local area image,
Pre-set image feature corresponding to destination object is obtained again, characteristics of image and pre-set image feature are analyzed respectively, obtains
One characteristic value and Second Eigenvalue, and calculate feature difference between the two, then, the image according to corresponding to obtaining feature difference
Adjusting parameter, handled according to the image adjustment parameter localized region image, and export the image after processing.Program base
Difference between the characteristics of image of image and pre-set image feature, is directed to the local area image of existing characteristics difference
The processing of property, improve the accuracy and validity of image procossing.
In still another embodiment of the process, a kind of image processing apparatus is also provided, the image processing apparatus can with software or
The form of hardware is integrated in the electronic device, and the electronic equipment can specifically include mobile phone, tablet personal computer, notebook computer etc. and set
It is standby.As shown in fig. 6, the image processing apparatus 300 can include identification module 301, determining module 302, acquisition module 303, ratio
Compared with module 304 and processing module 305, wherein：
Identification module 301, for obtaining target image, and the destination object in recognition target image.
Wherein, target image can be character image or scene image.Destination object can be people, Ke Yishi
Thing.For example recognition of face can be carried out to target image, can be by the human body where the face recognized when recognizing face
As the destination object in target image.Again for example, when recognize one it is colored when, can be using the flower recognized as destination object
Determining module 302, for determining the local area image on destination object, and obtain the image of local area image
Feature.
Specifically, it is available and its deep learning or general image procossing mechanism etc., and combining target object is in itself,
Obtain out the local area image that notable difference be present with other regions.
One image can have one or more characteristics of image.Such as by taking face as an example, characteristics of image can be include it is all
Such as shape of face, the colour of skin, nasal height, the one or more features of eyes size.In specific implementation process, using Fourier transform,
Window fourier transform method, Wavelet Transform, least square method, edge direction histogram method etc., extract local area image
Characteristics of image.
Acquisition module 303, for obtaining pre-set image feature corresponding to destination object from default characteristic set.
Comparison module 304, for characteristics of image compared with pre-set image feature corresponding to destination object, to be compared
Relatively result.
In certain embodiments, pre-set image feature can be uploaded by server based on the deep learning of machine to electronic equipment
Processing parameter in various images before and after the processing, operating process is analyzed and study processing, identifies that all kinds of images institutes are right
The treatment effect that popular should be more inclined to, and obtained based on treatment effect extraction characteristics of image.
Processing module 305, for being handled according to comparative result localized region image, with the target after being handled
Image.
With reference to figure 7, in certain embodiments, comparison module 304 includes：
Submodule 3041 is analyzed, for analyzing pre-set image feature, the First Eigenvalue is obtained, analyzes characteristics of image, obtain
Second Eigenvalue；
Comparison sub-module 3042, for compared with Second Eigenvalue, the First Eigenvalue to be calculated into feature difference, by spy
Difference is levied as comparative result.
Wherein, characteristic value is the quantized data value to each characteristics of image, can be based on associated picture algorithm to characteristics of image
Parsed, and be calculated by binary conversion treatment.
With continued reference to Fig. 7, in certain embodiments, processing module 305 includes：
Parameter acquiring submodule 3051, for image adjustment parameter corresponding to being obtained according to feature difference；
Submodule 3052 is handled, for adjusting the characteristics of image of local area image according to image adjustment parameter.
In practical application, a reduction formula can be designed, the feature difference of acquisition is treated as corresponding to obtain such as the reduction formula
Image adjustment parameter.
In addition, can also divide difference section, each difference section corresponds to different image adjustment parameters.By by acquisition
Feature difference is matched with the difference section set, determines image adjustment parameter corresponding to feature difference acquisition.
In certain embodiments, processing submodule 3052 is used for：
Color characteristic figure layer, textural characteristics figure layer, shape facility figure layer and space is extracted from local area image to close
It is feature figure layer, obtains feature figure layer set；
Target signature figure layer is chosen according to adjusting parameter from feature figure layer set to be adjusted；
Unchecked feature figure layer in target signature figure layer after adjustment and characteristic set is synthesized.
In certain embodiments, destination object is who object, and acquisition module 303 is used for：
Determination sub-module 3031, for determining the affiliated classification of who object；
Feature acquisition submodule 3032, for obtaining pre-set image feature corresponding to the category from default characteristic set,
Using pre-set image feature as pre-set image feature corresponding to destination object.
Wherein, affiliated type may include：Male, women etc..Same type of who object, there is the figure of same type
As feature, such as, male has Adam's apple, women not to have Adam's apple；Male's eyebrows, women eyebrow are thin.Different types of destination object tool
There is different types of characteristics of image, and the demand of the image landscaping effect to that need to reach also differs.
In certain embodiments, destination object is who object；As shown in fig. 7, determining module 302 includes：
Submodule 3021 is divided, for who object to be divided into multiple positions according to organization of human body；
Rank acquisition submodule 3022, for obtaining priority corresponding to each position；
Submodule 3023 is chosen, for choosing target site from multiple positions from high to low according to priority, and by mesh
The image at position is marked as local area image.
From the foregoing, it will be observed that image processing apparatus provided in an embodiment of the present invention, by obtaining target image, and identifies target figure
The destination object of picture, the local area image on destination object is then determined, and obtain the characteristics of image of local area image, so
Pre-set image feature corresponding to destination object is obtained from default characteristic set afterwards, then characteristics of image is corresponding with destination object
Pre-set image feature is compared, and obtains comparative result, is finally handled according to comparative result localized region image, with
Target image after to processing.Characteristics of image of the program based on image and the comparative result of pre-set image feature, enter to image
Row is targetedly handled, and improves the accuracy and validity of image procossing.
A kind of electronic equipment is also provided in still another embodiment of the process, and the electronic equipment can be smart mobile phone, flat board
Apparatus such as computer.As shown in figure 8, electronic equipment 400 includes processor 401, memory 402.Wherein, processor 401 and storage
Device 402 is electrically connected with.
Processor 401 is the control centre of electronic equipment 400, utilizes various interfaces and the whole electronic equipment of connection
Various pieces, by the application program of operation or load store in memory 402, and call and be stored in memory 402
Data, the various functions and processing data of electronic equipment are performed, so as to carry out integral monitoring to electronic equipment.
In the present embodiment, processor 401 in electronic equipment 400 can according to the steps, by one or one with
On application program process corresponding to instruction be loaded into memory 402, and be stored in memory by processor 401 to run
Application program in 402, so as to realize various functions：
Obtain target image, and the destination object in recognition target image；
The local area image on destination object is determined, and obtains the characteristics of image of local area image；
Pre-set image feature corresponding to destination object is obtained from default characteristic set；
By characteristics of image compared with pre-set image feature corresponding to destination object, comparative result is obtained；
Handled according to comparative result localized region image, with the target image after being handled.
In certain embodiments, processor 401 performs following steps：
Pre-set image feature is analyzed, obtains the First Eigenvalue；
Characteristics of image is analyzed, obtains Second Eigenvalue；
By the First Eigenvalue compared with Second Eigenvalue, feature difference is calculated, using feature difference as comparative result.
In certain embodiments, processor 401 also performs following steps：The Image Adjusting according to corresponding to obtaining feature difference
Parameter；The characteristics of image of local area image is adjusted according to image adjustment parameter.
In certain embodiments, processor 401 also performs following steps：
Color characteristic figure layer, textural characteristics figure layer, shape facility figure layer and space is extracted from local area image to close
It is feature figure layer, obtains feature figure layer set；
Target signature figure layer is chosen according to adjusting parameter from feature figure layer set to be adjusted；
Unchecked feature figure layer in target signature figure layer after adjustment and characteristic set is synthesized.
In certain embodiments, processor 401 also performs following steps：Determine the classification belonging to destination object；From default
Pre-set image feature corresponding to the category is obtained in characteristic set, using pre-set image feature as default figure corresponding to destination object
As feature.
In certain embodiments, destination object is who object；Processor 401 also performs following steps：According to human body knot
Who object is divided into multiple positions by structure；Obtain priority corresponding to each position；According to priority from high to low from multiple
Target site is chosen in position, and using the image of target site as local area image.
Memory 402 can be used for storage application program and data.Including in the application program that memory 402 stores can be
The instruction performed in processor.Application program can form various functions module.Processor 401 is stored in memory by operation
402 application program, so as to perform various function application and data processing.
In certain embodiments, as shown in figure 9, electronic equipment 400 also includes：Display screen 403, control circuit 404, radio frequency
Circuit 405, input block 406, voicefrequency circuit 407, sensor 408 and power supply 409.Wherein, processor 401 respectively with display
Screen 403, control circuit 404, radio circuit 405, input block 406, voicefrequency circuit 407, sensor 408 and the electricity of power supply 409
Property connection.
Display screen 403 can be used for display by user input information or be supplied to user information and electronic equipment it is each
Kind graphical user interface, these graphical user interface can be made up of image, text, icon, video and its any combination.Its
In, the display screen 403 can be as the screen in the embodiment of the present invention, for display information.
Control circuit 404 is electrically connected with display screen 403, for the display information of control display screen 403.
Radio circuit 405 is used for transceiving radio frequency signal, to be built by radio communication and the network equipment or other electronic equipments
Vertical wireless telecommunications, the receiving and transmitting signal between the network equipment or other electronic equipments.
Input block 406 can be used for numeral, character information or the user's characteristic information (such as fingerprint) for receiving input, and
Keyboard, mouse, action bars, optics or the trace ball signal relevant with user's setting and function control is produced to input.Wherein,
Input block 406 can include fingerprint recognition module.
Voicefrequency circuit 407 can provide the COBBAIF between user and electronic equipment by loudspeaker, microphone.
Sensor 408 is used to gather external environmental information.Sensor 408 can include ambient light sensor, acceleration
Sensor, optical sensor, motion sensor and other sensors.
The all parts that power supply 409 is used for electron equipment 400 are powered.In certain embodiments, power supply 409 can pass through
Power-supply management system and processor 401 are logically contiguous, so as to realize management charging, electric discharge, Yi Jigong by power-supply management system
The functions such as consumption management.
Although not shown in Fig. 9, electronic equipment 400 can also include camera, bluetooth module etc., will not be repeated here.
From the foregoing, it will be observed that electronic equipment provided in an embodiment of the present invention, by obtaining target image, and recognition target image
Destination object, the local area image on destination object is then determined, and obtain the characteristics of image of local area image, Ran Houcong
Pre-set image feature corresponding to destination object is obtained in default characteristic set, then characteristics of image is corresponding with destination object default
Characteristics of image is compared, and obtains comparative result, is finally handled according to comparative result localized region image, to obtain everywhere
Target image after reason.Characteristics of image of the program based on image and the comparative result of pre-set image feature, enter the hand-manipulating of needle to image
Processing to property, improve the accuracy and validity of image procossing.
A kind of storage medium is also provided in further embodiment of this invention, a plurality of instruction is stored with the storage medium, this refers to
The step of order is suitable to be loaded to perform any of the above-described image processing method by processor.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
To instruct the hardware of correlation to complete by program, the program can be stored in a computer-readable recording medium, storage
Medium can include：Read-only storage (ROM, ReadOnlyMemory), random access memory (RAM,
RandomAccessMemory), disk or CD etc..
Term " one " and " described " and similar word have been used during idea of the invention is described (especially
In the appended claims), it should be construed to not only cover odd number by these terms but also cover plural number.In addition, unless herein
In be otherwise noted, otherwise herein narration number range when merely by quick method belong to the every of relevant range to refer to
Individual independent value, and each independent value is incorporated into this specification, just as these values have individually carried out statement one herein
Sample.In addition, unless otherwise stated herein or context has clearly opposite prompting, otherwise institute specifically described herein is methodical
Step can be performed by any appropriate order.The change of the present invention is not limited to the step of description order.Unless in addition
Advocate, be otherwise all only using any and all example presented herein or exemplary language (for example, " such as ")
Idea of the invention is better described, and not the scope of idea of the invention is any limitation as.Spirit and model are not being departed from
In the case of enclosing, those skilled in the art becomes readily apparent that a variety of modifications and adaptation.
A kind of image processing method, device, storage medium and the electronic equipment provided above the embodiment of the present invention enters
Go and be discussed in detail, program used herein specific case is set forth to the principle and embodiment of the present invention, the above
The explanation of embodiment is only intended to help the method and its core concept for understanding the present invention；Meanwhile for those skilled in the art
Member, according to the thought of the present invention, the there will be changes in embodiment and range of applications, in summary, this
Description should not be construed as limiting the invention.
Claims (11)
- A kind of 1. image processing method, it is characterised in that including：Target image is obtained, and identifies the destination object in the target image；The local area image on the destination object is determined, and obtains the characteristics of image of the local area image；Pre-set image feature corresponding to the destination object is obtained from default characteristic set；By described image feature compared with pre-set image feature corresponding to the destination object, comparative result is obtained；The local area image is handled according to the comparative result, with the target image after being handled.
- 2. image processing method as claimed in claim 1, it is characterised in that by described image feature and the destination object pair The step of pre-set image feature answered is compared, obtains comparative result includes：The pre-set image feature is analyzed, obtains the First Eigenvalue；Described image feature is analyzed, obtains Second Eigenvalue；By the First Eigenvalue compared with the Second Eigenvalue, calculate feature difference, using the feature difference as Comparative result.
- 3. image processing method as claimed in claim 2, it is characterised in that according to the comparative result to the regional area The step of image is handled includes：The image adjustment parameter according to corresponding to obtaining the feature difference；The characteristics of image of the local area image is adjusted according to described image adjusting parameter.
- 4. image processing method as claimed in claim 3, it is characterised in that the office is adjusted according to described image adjusting parameter The step of characteristics of image of portion's area image, includes：Color characteristic figure layer, textural characteristics figure layer, shape facility figure layer and space is extracted from the local area image to close It is feature figure layer, obtains feature figure layer set；Target signature figure layer is chosen according to the adjusting parameter from the feature figure layer set to be adjusted；Unchecked feature figure layer in target signature figure layer after adjustment and the characteristic set is synthesized.
- 5. image processing method as claimed in claim 1, it is characterised in that the destination object is who object；From default The step of pre-set image feature corresponding to the destination object is obtained in characteristic set includes：Determine the classification belonging to the who object；Pre-set image feature corresponding to the classification is obtained from default characteristic set, using the pre-set image feature as described in Pre-set image feature corresponding to destination object.
- 6. image processing method as claimed in claim 1, it is characterised in that the destination object is who object；Determine institute The step of stating the local area image on destination object includes：The who object is divided into by multiple positions according to organization of human body；Obtain priority corresponding to each position；Choose target site from the multiple position from high to low according to priority, and using the image of the target site as Local area image.
- A kind of 7. image processing apparatus, it is characterised in that including：Identification module, for obtaining target image, and identify the destination object in the target image；Determining module, for determining the local area image on the destination object, and obtain the figure of the local area image As feature；Acquisition module, for obtaining pre-set image feature corresponding to the destination object from default characteristic set；Comparison module, for described image feature compared with pre-set image feature corresponding to the destination object, to be obtained Comparative result；Processing module, for being handled according to the comparative result the local area image, with the mesh after being handled Logo image.
- 8. image processing apparatus as claimed in claim 7, it is characterised in that the comparison module includes：Submodule is analyzed, for analyzing the pre-set image feature, obtains the First Eigenvalue, and analysis described image feature, Obtain Second Eigenvalue；Comparison sub-module, for compared with the Second Eigenvalue, the First Eigenvalue to be calculated into feature difference, by institute Feature difference is stated as comparative result.
- 9. image processing apparatus as claimed in claim 8, it is characterised in that the processing module includes：Parameter acquiring submodule, for the image adjustment parameter according to corresponding to feature difference acquisition；Submodule is handled, for adjusting the characteristics of image of the local area image according to described image adjusting parameter.
- A kind of 10. storage medium, it is characterised in that be stored with a plurality of instruction in the storage medium, the instruction be suitable to by Reason device is loaded to perform the image processing method as any one of claim 1-6.
- 11. a kind of electronic equipment, it is characterised in that including processor and memory, the processor and the memory are electrical Connection, the memory are used for store instruction and data；The processor is used to perform as any one of claim 1-6 Image processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710526347.3A CN107358241B (en) | 2017-06-30 | 2017-06-30 | Image processing method, image processing device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710526347.3A CN107358241B (en) | 2017-06-30 | 2017-06-30 | Image processing method, image processing device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107358241A true CN107358241A (en) | 2017-11-17 |
| CN107358241B CN107358241B (en) | 2021-01-26 |
Family
ID=60273675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710526347.3A Expired - Fee Related CN107358241B (en) | 2017-06-30 | 2017-06-30 | Image processing method, image processing device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358241B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108076288A (en) * | 2017-12-14 | 2018-05-25 | 光锐恒宇（北京）科技有限公司 | Image processing method, device and computer readable storage medium |
| CN108093177A (en) * | 2017-12-28 | 2018-05-29 | 广东欧珀移动通信有限公司 | Image acquiring method, device, storage medium and electronic equipment |
| CN108174099A (en) * | 2017-12-29 | 2018-06-15 | 光锐恒宇（北京）科技有限公司 | Method for displaying image, device and computer readable storage medium |
| CN108198144A (en) * | 2017-12-28 | 2018-06-22 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN108446653A (en) * | 2018-03-27 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling face-image |
| CN108776819A (en) * | 2018-06-05 | 2018-11-09 | Oppo广东移动通信有限公司 | A kind of target identification method, mobile terminal and computer readable storage medium |
| CN109035159A (en) * | 2018-06-27 | 2018-12-18 | 努比亚技术有限公司 | A kind of image optimization processing method, mobile terminal and computer readable storage medium |
| CN109120906A (en) * | 2018-10-30 | 2019-01-01 | 信利光电股份有限公司 | A kind of intelligent monitor system |
| CN109598722A (en) * | 2018-12-10 | 2019-04-09 | 杭州帝视科技有限公司 | Image analysis method based on recurrent neural network |
| CN109726255A (en) * | 2018-12-18 | 2019-05-07 | 斑马网络技术有限公司 | Automatic update method, device, system and the storage medium of POI |
| WO2019120025A1 (en) * | 2017-12-22 | 2019-06-27 | Oppo广东移动通信有限公司 | Photograph adjustment method and apparatus, storage medium and electronic device |
| CN110738626A (en) * | 2019-10-24 | 2020-01-31 | 广东三维家信息科技有限公司 | Rendering graph optimization method and device and electronic equipment |
| CN111246113A (en) * | 2020-03-05 | 2020-06-05 | 上海瑾盛通信科技有限公司 | Image processing method, device, equipment and storage medium |
| CN112083863A (en) * | 2020-09-17 | 2020-12-15 | 维沃移动通信有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN112419470A (en) * | 2020-12-15 | 2021-02-26 | 北京映客芝士网络科技有限公司 | Color rendering method, device, equipment and medium for target area |
| CN113449755A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Data processing method, model training method, device, equipment and storage medium |
| CN114332730A (en) * | 2021-12-31 | 2022-04-12 | 广州繁星互娱信息科技有限公司 | Target image acquisition method, storage medium and electronic equipment |
| CN114693554A (en) * | 2022-03-28 | 2022-07-01 | 唐山学院 | Big data image processing method and system |
| WO2023045979A1 (en) * | 2021-09-27 | 2023-03-30 | 上海商汤智能科技有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| CN118015645A (en) * | 2023-12-27 | 2024-05-10 | 中铁建工集团有限公司 | Hierarchical data acquisition method, device, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080153757A1 (en) * | 2006-12-26 | 2008-06-26 | Ad Lunam Labs, Inc. | Skin Rejuvenation Cream |
| CN104346136A (en) * | 2013-07-24 | 2015-02-11 | 腾讯科技（深圳）有限公司 | Method and device for picture processing |
| CN104503749A (en) * | 2014-12-12 | 2015-04-08 | 广东欧珀移动通信有限公司 | Photo processing method and electronic equipment |
| CN105096241A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Face image beautifying device and method |
| CN105279186A (en) * | 2014-07-17 | 2016-01-27 | 腾讯科技（深圳）有限公司 | Image processing method and system |
| CN105812853A (en) * | 2016-03-16 | 2016-07-27 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN106886752A (en) * | 2017-01-06 | 2017-06-23 | 深圳市金立通信设备有限公司 | The method and terminal of a kind of image procossing |
-
2017
- 2017-06-30 CN CN201710526347.3A patent/CN107358241B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080153757A1 (en) * | 2006-12-26 | 2008-06-26 | Ad Lunam Labs, Inc. | Skin Rejuvenation Cream |
| CN104346136A (en) * | 2013-07-24 | 2015-02-11 | 腾讯科技（深圳）有限公司 | Method and device for picture processing |
| CN105279186A (en) * | 2014-07-17 | 2016-01-27 | 腾讯科技（深圳）有限公司 | Image processing method and system |
| CN104503749A (en) * | 2014-12-12 | 2015-04-08 | 广东欧珀移动通信有限公司 | Photo processing method and electronic equipment |
| CN105096241A (en) * | 2015-07-28 | 2015-11-25 | 努比亚技术有限公司 | Face image beautifying device and method |
| CN105812853A (en) * | 2016-03-16 | 2016-07-27 | 联想(北京)有限公司 | Image processing method and electronic device |
| CN106886752A (en) * | 2017-01-06 | 2017-06-23 | 深圳市金立通信设备有限公司 | The method and terminal of a kind of image procossing |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108076288A (en) * | 2017-12-14 | 2018-05-25 | 光锐恒宇（北京）科技有限公司 | Image processing method, device and computer readable storage medium |
| WO2019120025A1 (en) * | 2017-12-22 | 2019-06-27 | Oppo广东移动通信有限公司 | Photograph adjustment method and apparatus, storage medium and electronic device |
| CN109961403A (en) * | 2017-12-22 | 2019-07-02 | 广东欧珀移动通信有限公司 | Method of adjustment, device, storage medium and the electronic equipment of photo |
| CN108093177A (en) * | 2017-12-28 | 2018-05-29 | 广东欧珀移动通信有限公司 | Image acquiring method, device, storage medium and electronic equipment |
| CN108198144A (en) * | 2017-12-28 | 2018-06-22 | 广东欧珀移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN108093177B (en) * | 2017-12-28 | 2021-01-26 | Oppo广东移动通信有限公司 | Image acquisition method and device, storage medium and electronic equipment |
| CN108174099A (en) * | 2017-12-29 | 2018-06-15 | 光锐恒宇（北京）科技有限公司 | Method for displaying image, device and computer readable storage medium |
| CN108446653A (en) * | 2018-03-27 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for handling face-image |
| CN108776819A (en) * | 2018-06-05 | 2018-11-09 | Oppo广东移动通信有限公司 | A kind of target identification method, mobile terminal and computer readable storage medium |
| CN109035159A (en) * | 2018-06-27 | 2018-12-18 | 努比亚技术有限公司 | A kind of image optimization processing method, mobile terminal and computer readable storage medium |
| CN109120906A (en) * | 2018-10-30 | 2019-01-01 | 信利光电股份有限公司 | A kind of intelligent monitor system |
| CN109598722A (en) * | 2018-12-10 | 2019-04-09 | 杭州帝视科技有限公司 | Image analysis method based on recurrent neural network |
| CN109598722B (en) * | 2018-12-10 | 2020-12-08 | 杭州帝视科技有限公司 | Image analysis method based on recurrent neural network |
| CN109726255A (en) * | 2018-12-18 | 2019-05-07 | 斑马网络技术有限公司 | Automatic update method, device, system and the storage medium of POI |
| CN110738626A (en) * | 2019-10-24 | 2020-01-31 | 广东三维家信息科技有限公司 | Rendering graph optimization method and device and electronic equipment |
| CN111246113A (en) * | 2020-03-05 | 2020-06-05 | 上海瑾盛通信科技有限公司 | Image processing method, device, equipment and storage medium |
| CN113449755A (en) * | 2020-03-26 | 2021-09-28 | 阿里巴巴集团控股有限公司 | Data processing method, model training method, device, equipment and storage medium |
| CN112083863A (en) * | 2020-09-17 | 2020-12-15 | 维沃移动通信有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN112419470A (en) * | 2020-12-15 | 2021-02-26 | 北京映客芝士网络科技有限公司 | Color rendering method, device, equipment and medium for target area |
| WO2023045979A1 (en) * | 2021-09-27 | 2023-03-30 | 上海商汤智能科技有限公司 | Image processing method and apparatus, electronic device, and storage medium |
| CN114332730A (en) * | 2021-12-31 | 2022-04-12 | 广州繁星互娱信息科技有限公司 | Target image acquisition method, storage medium and electronic equipment |
| CN114693554A (en) * | 2022-03-28 | 2022-07-01 | 唐山学院 | Big data image processing method and system |
| CN118015645A (en) * | 2023-12-27 | 2024-05-10 | 中铁建工集团有限公司 | Hierarchical data acquisition method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107358241B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358241A (en) | Image processing method, device, storage medium and electronic equipment | |
| US11443462B2 (en) | Method and apparatus for generating cartoon face image, and computer storage medium | |
| CN107256555B (en) | Image processing method, device and storage medium | |
| CN109961453B (en) | Image processing method, device and equipment | |
| CN108259758B (en) | Image processing method, image processing apparatus, storage medium, and electronic device | |
| CN107578380A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN109977739A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN108198130B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| CN108229369A (en) | Image capturing method, device, storage medium and electronic equipment | |
| US20220180485A1 (en) | Image Processing Method and Electronic Device | |
| CN113129312A (en) | Image processing method, device and equipment | |
| KR20150079804A (en) | Image processing method and apparatus, and terminal device | |
| CN108875594B (en) | Face image processing method, device and storage medium | |
| EP3623973B1 (en) | Unlocking control method and related product | |
| CN108921941A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109413326A (en) | Camera control method and Related product | |
| CN108234882A (en) | A kind of image weakening method and mobile terminal | |
| CN109271930A (en) | Micro- expression recognition method, device and storage medium | |
| CN113452969B (en) | Image processing method and device | |
| CN109272466A (en) | A kind of tooth beautification method and device | |
| CN110765924A (en) | Living body detection method and device and computer-readable storage medium | |
| CN109167914A (en) | A kind of image processing method and mobile terminal | |
| CN108491780A (en) | Image landscaping treatment method, apparatus, storage medium and terminal device | |
| CN114187166A (en) | Image processing method, intelligent terminal and storage medium | |
| CN110502959A (en) | Sexual discriminating method, apparatus, storage medium and electronic equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210126 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |