CN106846244A - A kind of image processing method, equipment and terminal - Google Patents
A kind of image processing method, equipment and terminal Download PDFInfo
- Publication number
- CN106846244A CN106846244A CN201710005059.3A CN201710005059A CN106846244A CN 106846244 A CN106846244 A CN 106846244A CN 201710005059 A CN201710005059 A CN 201710005059A CN 106846244 A CN106846244 A CN 106846244A
- Authority
- CN
- China
- Prior art keywords
- data
- image
- characteristic
- image data
- destination
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 claims description 9
- 238000000034 method Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 7
- 238000009826 distribution Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 6
- 210000001508 eye Anatomy 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000000153 supplemental effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention discloses a kind of image processing method, equipment and terminal, described image data processing method includes:The image feature data of selected destination image data is obtained, image of the generation comprising described image characteristic obtains instruction;Described image is obtained into instruction to send to server, so that the server obtains at least one view data being associated with described image characteristic;At least one view data that the server sends is received, treatment is analyzed at least one view data using described image characteristic, to reduce the corresponding raw image data of the destination image data.Using the present invention, at least one view data being associated with target image can be obtained from network, and the corresponding raw image data of destination image data can be restored from least one associated view data, improve the authenticity of the image information that destination image data is carried in itself.
Description
Technical field
The present invention relates to Internet technical field, more particularly to a kind of image processing method, equipment and terminal.
Background technology
Constantly developed and perfect with Internet technology, the terminal device such as mobile phone and computer has become people's life
In an indispensable part, people can check various in social friends circle or news web page on these terminal devices
Picture, and obtain the image information entrained by photo in itself by photo, for example:Picture can be known by personage's picture
The current looks of middle personage, the architectural style of the building is will be seen that by a building picture.However, people often exist
Before issue picture, picture is modified using various figure softwares of repairing in order to reach oneself desired effect, so that friend
Picture in circle or webpage loses certain authenticity, and then causes the image information that people obtain from picture to there is also one
The fixed distortion factor.
The content of the invention
In view of this, the embodiment of the present invention provides a kind of image processing method, equipment and terminal, can be from network
At least one view data that acquisition is associated with target image, it is possible to reduced from least one associated view data
Go out the corresponding raw image data of destination image data, improve the authenticity of the image information that destination image data is carried in itself.
In order to solve the above-mentioned technical problem, a kind of image processing method, methods described be the embodiment of the invention provides
Including:
The image feature data of selected destination image data is obtained, image of the generation comprising described image characteristic is obtained
Instruction;
Described image is obtained into instruction to send to server, so that the server is obtained and described image characteristic phase
At least one view data of association;
Receive at least one view data that the server sends, using described image characteristic to it is described extremely
A few view data is analyzed treatment, to reduce the corresponding raw image data of the destination image data.
Correspondingly, the embodiment of the present invention additionally provides a kind of image-data processing apparatus, and the equipment includes:
Instruction generation unit, the image feature data for obtaining selected destination image data, generation includes described image
The image of characteristic obtains instruction;
Instruction sending unit, sends to server for described image to be obtained into instruction so that the server obtain with
At least one associated view data of described image characteristic;
Data convert unit, for receiving at least one view data that the server sends, using the figure
It is corresponding original to reduce the destination image data as characteristic is analyzed treatment at least one view data
View data.
The embodiment of the present invention additionally provides a kind of terminal, and the terminal includes the described image data that above-described embodiment is provided
Processing equipment.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information.
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
The accompanying drawing for having technology to be needed to use in describing is briefly described, it should be apparent that, drawings in the following description are only this hair
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can be with root
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of image processing method provided in an embodiment of the present invention;
Fig. 2 is the schematic flow sheet of another image processing method provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of image-data processing apparatus provided in an embodiment of the present invention;
Fig. 4 is the structural representation of data convert unit provided in an embodiment of the present invention;
Fig. 5 is the structural representation of another image-data processing apparatus provided in an embodiment of the present invention.
Specific 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 is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, it is every other that those of ordinary skill in the art are obtained on the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Image processing method provided in an embodiment of the present invention can apply to the reduction of distorted picture (for example:To repairing
The reduction of the excessive character image or landscape image of figure) application scenarios in, for example:Image-data processing apparatus obtain selected mesh
The image feature data of logo image data, image of the generation comprising image feature data obtains instruction, and image acquisition is instructed
Send to server, so that server obtains at least one view data being associated with image feature data, the reception server
At least one view data for sending, treatment is analyzed using image feature data at least one view data, to reduce
The corresponding raw image data of destination image data.Obtained by image feature data is associated at least with destination image data
One view data, and by therefrom restoring the corresponding original image of destination image data at least one analysis of image data
Data, improve the authenticity of the image information that destination image data is carried in itself.
The present embodiments relate to image-data processing apparatus can include panel computer, personal computer (PC), intelligence
The terminal devices such as energy mobile phone, palm PC and mobile internet device (MID).
Below in conjunction with accompanying drawing 1 and accompanying drawing 2, image processing method provided in an embodiment of the present invention is situated between in detail
Continue.
Fig. 1 is a kind of schematic flow sheet of image processing method provided in an embodiment of the present invention.As shown in figure 1, this
Method described in inventive embodiments may comprise steps of S101- steps S103.
S101, obtains the image feature data of selected destination image data, figure of the generation comprising described image characteristic
Instructed as obtaining.
Specifically, described image data processing equipment can be obtained described in user selects when circle of friends or webpage is browsed
The image feature data of destination image data, wherein, the destination image data can be a portrait photographs, a building
Photo, picture with scenes etc..
It is understood that described image characteristic can be the number for representing the destination image data principal character
According to face characteristic, color characteristic data, textural characteristics data, character shape data and spatial relation characteristics can be included
One or more in data.Generally, the face characteristic is mainly the size of face, distribution etc., is to discriminate between face
Principal character data;The color characteristic data is the characteristic based on pixel, because color is to image or image-region
The change such as direction, size it is insensitive, so color characteristic data can not well catch the local feature of objects in images, be
Used as supplemental characteristic data;The textural characteristics data are a kind of global characteristics data, and it describes image or image district
The surface nature of object corresponding to domain, when retrieval has the texture image of the aspect bigger differences such as thickness, density, it is possible to use
Textural characteristics data;The character shape data can be the contour feature data or region shape characteristic of image;It is described
Spatial relation characteristics data can describe the mutual locus or relative in image between multiple targets for splitting
The characteristic of direction relationses.
Further, described image data processing equipment can generate the image comprising described image characteristic and obtain and refer to
Order.It is understood that described image can include described image characteristic in obtaining instruction, so that server is received
Described image can obtain the image being associated with the destination image data after obtaining instruction according to described image characteristic
Data.
S102, obtains described image instruction and sends to server.
Specifically, described image data processing equipment can be sent to server the instruction of described image data acquisition.Institute
State after server receives the instruction of described image data acquisition, can obtain special comprising described image in instruction according to described image
Data are levied to be searched for from network side at least one view data of the acquisition with described image characteristic by big data.Can manage
Solution, has certain relevance, for example between at least one view data and the destination image data:It is described extremely
The data type of corresponding at least one characteristic of a few view data can be with the number of described image characteristic
It is consistent according to type.
S103, receives at least one view data that the server sends, using described image characteristic pair
At least one view data is analyzed treatment, to reduce the corresponding raw image data of the destination image data.
Specifically, described image data processing equipment can receive at least one picture number that the server sends
According to, it is possible to treatment is analyzed at least one view data using described image characteristic, to reduce the mesh
The corresponding raw image data of logo image data.
Optionally, described image data processing equipment can receive at least one picture number that the server sends
According to, and characteristic is carried out to each view data at least one view data according to described image characteristic
Extract, obtain at least one characteristic.It is understood that due to the destination image data and at least one image
There is relevance between data, then also there is relevance between at least one characteristic and described image characteristic,
For example:The data type of at least one characteristic can it is consistent with the data type of described image characteristic (for example:
If described image characteristic includes:The size of face, distribution, the texture of image, the then number of at least one characteristic
Also include according to type:The size of face, distribution, the texture of image).Further, at least one characteristic with it is described
Image feature data can have certain proportionate relationship, for example:Eyes size at least one characteristic can be with
It is 0.5 times of eyes size in described image characteristic.
Further, described image data processing equipment can be to each characteristic at least one characteristic
Similarity comparison is carried out between, it is possible to obtain similar between each characteristic at least one characteristic
Degree.Contrasted with default similarity threshold by by the similarity between each characteristic, obtain the similarity and be more than
Or equal to the fisrt feature data of the default similarity threshold.It is understood that comparing by with the similarity threshold
The fisrt feature data closest to initial characteristic data can be effectively obtained from least one characteristic, for example:
If set similarity threshold is 98%, each characteristic of similarity more than or equal to 98% can between any two
It is the fisrt feature data.It is understood that comprising at least at least one characteristic in the fisrt feature data
According at least one of characteristic.
Further, described image data processing equipment is asked for for reducing the target according to the fisrt feature data
The initial characteristic data of view data, it is possible to the destination image data is restored according to the initial characteristic data corresponding
Raw image data.It is understood that data content in the raw image data not necessarily destination image data
Most real reflection, and it is closest to the reflection of real data content.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information.
Fig. 2 is referred to, to the embodiment of the invention provides the schematic flow sheet of another image processing method.As schemed
Shown in 2, the described image data processing method in the present embodiment can include with step S201- steps S205.
S201, obtains the image feature data of selected destination image data, figure of the generation comprising described image characteristic
Instructed as obtaining.
Specifically, described image data processing equipment can be obtained described in user selects when circle of friends or webpage is browsed
Destination image data, for example:The destination image data can be a portrait photographs, building photo, a landscape
Photo etc..
It is understood that described image characteristic can be the number for representing the destination image data principal character
According to face characteristic, color characteristic data, textural characteristics data, character shape data and spatial relation characteristics can be included
One or more in data.Generally, the face characteristic is mainly the size of face, distribution etc., is to discriminate between face
Principal character data;The color characteristic data is the characteristic based on pixel, because color is to image or image-region
The change such as direction, size it is insensitive, so color characteristic data can not well catch the local feature of objects in images, be
Used as supplemental characteristic data;The textural characteristics data are a kind of global characteristics data, and it describes image or image district
The surface nature of object corresponding to domain, when retrieval has the texture image of the aspect bigger differences such as thickness, density, it is possible to use
Textural characteristics data;The character shape data can be the contour feature data or region shape characteristic of image;It is described
Spatial relation characteristics data can describe the mutual locus or relative in image between multiple targets for splitting
The characteristic of direction relationses.
Further, described image data processing equipment can generate the image comprising described image characteristic and obtain and refer to
Order.It is understood that described image can include described image characteristic in obtaining instruction, so that server is received
Described image can obtain the image being associated with the destination image data after obtaining instruction according to described image characteristic
Data.
S202, obtains described image instruction and sends to server.
Specifically, described image data processing equipment can be sent to server the instruction of described image data acquisition.Institute
State after server receives the instruction of described image data acquisition, can obtain special comprising described image in instruction according to described image
Data are levied to be searched for from network side at least one view data of the acquisition with described image characteristic by big data.Can manage
Solution, has certain relevance, for example between at least one view data and the destination image data:It is described extremely
The data type of corresponding at least one characteristic of a few view data can be with the number of described image characteristic
It is consistent according to type.
S203, receives at least one view data that the server sends, and according to described image characteristic
The extraction of characteristic is carried out to each view data at least one view data, at least one characteristic is obtained
According to.
Specifically, described image processing equipment can receive at least one view data that the server sends,
And carrying for characteristic is carried out to each view data at least one view data according to described image characteristic
Take, obtain at least one characteristic.It is understood that due to the destination image data and at least one picture number
There is relevance between, then also there is relevance, example between at least one characteristic and described image characteristic
Such as:The data type of at least one characteristic can it is consistent with the data type of described image characteristic (for example:If
Described image characteristic includes:The size of face, distribution, the texture of image, then data of at least one characteristic
Type also includes:The size of face, distribution, the texture of image).Further, at least one characteristic and the figure
As characteristic can have certain proportionate relationship, for example:Eyes size at least one characteristic can be
0.5 times of eyes size in described image characteristic.
S204, obtains the similarity between each characteristic at least one characteristic, and obtain described
Fisrt feature data of the similarity in default similarity threshold.
Specifically, described image data processing equipment can be to each characteristic at least one characteristic
Between carry out similarity comparison, it is possible to obtain similar between each characteristic at least one characteristic
Degree.Contrasted with default similarity threshold by by the similarity between each characteristic, obtain the similarity and be more than
Or equal to the fisrt feature data of the default similarity threshold.It is understood that comparing by with the similarity threshold
The fisrt feature data closest to initial characteristic data can be effectively obtained from least one characteristic, for example:
If set similarity threshold is 98%, each characteristic of similarity more than or equal to 98% can between any two
It is the fisrt feature data.It is understood that comprising at least at least one characteristic in the fisrt feature data
According at least one of characteristic.
It is understood that described image data processing equipment is by obtaining each at least one characteristic
Similarity between characteristic, and compare by with the default similarity threshold, can effectively filter described at least one
The characteristic larger with other characteristic similarity gaps in individual characteristic, is reduced by least one characteristic
The error of the initial characteristic data is asked for, such that it is able to increase the corresponding original image of the destination image data for restoring
The authenticity of data.
The fisrt feature data are carried out computing of averaging by S205 using mean algorithm, are obtained for reducing the mesh
The initial characteristic data of logo image data, and the corresponding original of the destination image data is restored according to the initial characteristic data
Beginning view data.
Specifically, described image data processing equipment can be using mean algorithm (for example:Exponential smoothing is average
(Exponential Moving Average, EMV), simple rolling average (Simple Moving Average, SMA) etc.)
Computing of averaging is carried out to the fisrt feature data, the initial characteristic data for reducing the destination image data is obtained.
It is understood that the initial characteristic data can be the feature that can most represent the data content in the destination image data
Data, the corresponding raw image data of the destination image data can be restored according to the initial characteristic data.Can manage
Solution, the most real reflection of data content in the raw image data not necessarily destination image data, but most
Close to the reflection of real data content.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information;By obtaining fisrt feature data of the similarity in default similarity threshold, reduce by least one
Characteristic asks for the error of initial characteristic data, and then increased the target image number restored by least one view data
According to the authenticity of corresponding raw image data.
Below in conjunction with accompanying drawing 3- accompanying drawings 4, image-data processing apparatus provided in an embodiment of the present invention are situated between in detail
Continue.It should be noted that the equipment shown in accompanying drawing 3- accompanying drawings 4, the method for performing Fig. 1 of the present invention and embodiment illustrated in fig. 2,
For convenience of description, the part related to the embodiment of the present invention is illustrate only, particular technique details is not disclosed, and refer to this hair
Embodiment shown in bright Fig. 1 and Fig. 2.
Fig. 3 is referred to, to the embodiment of the invention provides a kind of structural representation of image-data processing apparatus.Such as Fig. 3
Shown, the described image data processing equipment 1 of the embodiment of the present invention can include:Instruction generation unit 11, instruction sending unit
12 and data reduction unit 13.
Instruction generation unit 11, the image feature data for obtaining selected destination image data, generation includes the figure
As the image of characteristic obtains instruction.
In implementing, the instruction generation unit 11 can obtain the institute that user selects when circle of friends or webpage is browsed
The image feature data of destination image data is stated, wherein, the destination image data can be a portrait photographs, a building
Thing photo, picture with scenes etc..Further, the instruction generation unit 11 can carry out spy to the destination image data
The extraction for levying data obtains the image feature data of the destination image data.The extraction of the characteristic can extract institute
The characteristic that described image content can be represented in destination image data is stated, for example:The size of face, building are special in image
Distinctive shape of some decorative patterns, object etc..
It is understood that described image characteristic can be the number for representing the destination image data principal character
According to face characteristic, color characteristic data, textural characteristics data, character shape data and spatial relation characteristics can be included
One or more in data.Generally, the face characteristic is mainly the size of face, distribution etc., is to discriminate between face
Principal character data;The color characteristic data is the characteristic based on pixel, because color is to image or image-region
The change such as direction, size it is insensitive, so color characteristic data can not well catch the local feature of objects in images, be
Used as supplemental characteristic data;The textural characteristics data are a kind of global characteristics data, and it describes image or image district
The surface nature of object corresponding to domain, when retrieval has the texture image of the aspect bigger differences such as thickness, density, it is possible to use
Textural characteristics data;The character shape data can be the contour feature data or region shape characteristic of image;It is described
Spatial relation characteristics data can describe the mutual locus or relative in image between multiple targets for splitting
The characteristic of direction relationses.
Further, the instruction generation unit 11 can generate the image comprising described image characteristic and obtain and refer to
Order.It is understood that described image can include described image characteristic in obtaining instruction, so that server is received
Described image can obtain the image being associated with the destination image data after obtaining instruction according to described image characteristic
Data.
Instruction sending unit 12, sends to server for described image to be obtained into instruction.
In implementing, the instruction sending unit 12 can be sent to server the instruction of described image data acquisition.
After the server receives the instruction of described image data acquisition, described image is included during instruction can be obtained according to described image
Characteristic is searched for from network side by big data and obtains at least one view data with described image characteristic.Can be with
Understand there is certain relevance, for example between at least one view data and the destination image data:It is described
The data type of corresponding at least one characteristic of at least one view data can be with described image characteristic
Data type is consistent.
Data convert unit 13, for receiving at least one view data that the server sends, using described
Image feature data is analyzed treatment at least one view data, to reduce the corresponding original of the destination image data
Beginning view data.
In implementing, the data convert unit 13 can receive at least one image that the server sends
Data, it is possible to which treatment is analyzed at least one view data using described image characteristic, it is described to reduce
The corresponding raw image data of destination image data.
Please also refer to Fig. 4, to the embodiment of the invention provides the structural representation of data convert unit 13.Such as Fig. 4 institutes
Show, the data convert unit 13 can include:
Characteristic obtains subelement 131, for receiving at least one view data that the server sends, and
The extraction of characteristic is carried out to each view data at least one view data according to described image characteristic,
Obtain at least one characteristic.
In implementing, the characteristic obtain that subelement 131 can receive that the server sends it is described at least
One view data, and each view data at least one view data is carried out according to described image characteristic
The extraction of characteristic, obtains at least one characteristic.It is understood that due to the destination image data with it is described extremely
There is relevance between a few view data, then also have between at least one characteristic and described image characteristic
Relevant property, for example:The data type of at least one characteristic can be with the data type of described image characteristic
Unanimously (for example:If described image characteristic includes:The size of face, distribution, the texture of image, then described at least one is special
The data type for levying data also includes:The size of face, distribution, the texture of image).Further, at least one feature
Data can have certain proportionate relationship with described image characteristic, for example:Eye at least one characteristic
Eyeball size can be 0.5 times of eyes size in described image characteristic.
First data acquisition subelement 132, for obtain each characteristic at least one characteristic it
Between similarity, and obtain fisrt feature data of the similarity in default similarity threshold.
In implementing, the first data acquisition subelement 132 can at least one characteristic in it is every
Similarity comparison is carried out between individual characteristic, it is possible to obtain each characteristic at least one characteristic it
Between similarity.Contrasted with default similarity threshold by by the similarity between each characteristic, obtained the phase
Fisrt feature data like degree more than or equal to the default similarity threshold.It is understood that by with the similarity
Threshold value relatively can effectively obtain the fisrt feature number closest to initial characteristic data from least one characteristic
According to for example:If set similarity threshold is 98%, similarity is more than or equal to 98% each characteristic between any two
According to can be the fisrt feature data.It is understood that comprising at least described at least one in the fisrt feature data
At least one of individual characteristic characteristic.
It is understood that during the first data acquisition subelement 132 is by obtaining at least one characteristic
Each characteristic between similarity, and compare by with the default similarity threshold, can effectively filter described
The characteristic larger with other characteristic similarity gaps at least one characteristic, is reduced special by described at least one
The error that data ask for the initial characteristic data is levied, such that it is able to increase the corresponding original of the destination image data for restoring
The authenticity of beginning view data.
Data convert subelement 133, for being asked for for reducing the target image number according to the fisrt feature data
According to initial characteristic data, and the corresponding original image number of the destination image data is restored according to the initial characteristic data
According to.
In implementing, the data convert subelement 133 can be asked for for reducing according to the fisrt feature data
The initial characteristic data of the destination image data, and the destination image data pair is restored according to the initial characteristic data
The raw image data answered.
Further, the data convert subelement 133 can be using mean algorithm (for example:EMV, SMA etc.) to described
Fisrt feature data carry out computing of averaging, and obtain the initial characteristic data for reducing the destination image data.Can manage
Solution, the initial characteristic data can be the characteristic that can most represent the data content in the destination image data,
The corresponding raw image data of the destination image data can be restored according to the initial characteristic data.May be appreciated
It is, the most real reflection of data content in the raw image data not necessarily destination image data, and is closest to
The reflection of real data content.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information;By obtaining fisrt feature data of the similarity in default similarity threshold, reduce by least one
Characteristic asks for the error of initial characteristic data, and then increased the target image number restored by least one view data
According to the authenticity of corresponding raw image data.
Fig. 5 is referred to, to the embodiment of the invention provides the structural representation of another image-data processing apparatus.As schemed
Shown in 5, described image data processing equipment 1000 can include:At least one processor 1001, such as CPU, at least one net
Network interface 1004, user interface 1003, memory 1005, at least one communication bus 1002.Wherein, communication bus 1002 is used for
Realize the connection communication between these components.Wherein, user interface 1003 can include display screen (Display), keyboard
(Keyboard), optional user interface 1003 can also include wireline interface, the wave point of standard.Network interface 1004 is optional
Can include standard wireline interface, wave point (such as WI-FI interfaces).Memory 1005 can be high-speed RAM memory,
Can also be non-labile memory (non-volatile memory), for example, at least one magnetic disk storage.Memory
1005 optionally can also be at least one storage device for being located remotely from aforementioned processor 1001.As shown in figure 5, as a kind of
Operating system, network communication module, Subscriber Interface Module SIM and figure can be included in the memory 1005 of computer-readable storage medium
As data processor.
In the image-data processing apparatus 1000 shown in Fig. 5, user interface 1003 is mainly used in providing the user input
Interface, obtain user input data;And processor 1001 can be used for calling the network connection stored in memory 1005
Application program, and specifically perform following operation:
The image feature data of selected destination image data is obtained, image of the generation comprising described image characteristic is obtained
Instruction;
Described image is obtained into instruction to send to server, so that the server is obtained and described image characteristic phase
At least one view data of association;
Receive at least one view data that the server sends, using described image characteristic to it is described extremely
A few view data is analyzed treatment, to reduce the corresponding raw image data of the destination image data.
In one embodiment, the processor 1001 is performing at least one figure that the reception server sends
As data, treatment is analyzed at least one view data using described image characteristic, to reduce the target
It is specific to perform following operation during the corresponding raw image data of view data:
At least one view data that the server sends is received, and according to described image characteristic to described
Each view data at least one view data carries out the extraction of characteristic, obtains at least one characteristic;
The similarity between each characteristic at least one characteristic is obtained, and obtains the similarity
Fisrt feature data in default similarity threshold;
The initial characteristic data for reducing the destination image data is asked for according to the fisrt feature data, and according to
The initial characteristic data restores the corresponding raw image data of the destination image data.
In one embodiment, the processor 1001 is asked for for reducing in execution according to the fisrt feature data
The initial characteristic data of destination image data is stated, and the destination image data correspondence is restored according to the initial characteristic data
Raw image data when, it is specific to perform following operation:
Computing of averaging is carried out to the fisrt feature data using mean algorithm, is obtained for reducing the target image
The initial characteristic data of data, and the corresponding original image of the destination image data is restored according to the initial characteristic data
Data.
In one embodiment, described image characteristic includes:Face characteristic, color characteristic data, texture are special
Levy one or more in data, character shape data and spatial relation characteristics data.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information;By obtaining fisrt feature data of the similarity in default similarity threshold, reduce by least one
Characteristic asks for the error of initial characteristic data, and then increased the target image number restored by least one view data
According to the authenticity of corresponding raw image data.
The embodiment of the present invention additionally provides a kind of terminal, and the terminal can include the figure of embodiment as Figure 3-Figure 4
As data processing equipment, following steps are specifically performed:
The image feature data of selected destination image data is obtained, image of the generation comprising described image characteristic is obtained
Instruction;
Described image is obtained into instruction to send to server, so that the server is obtained and described image characteristic phase
At least one view data of association;
Receive at least one view data that the server sends, using described image characteristic to it is described extremely
A few view data is analyzed treatment, to reduce the corresponding raw image data of the destination image data.
In one embodiment, at least one view data that the reception server sends is being performed, using institute
State image feature data and treatment is analyzed at least one view data, it is corresponding to reduce the destination image data
During raw image data, following steps are specifically performed:
At least one view data that the server sends is received, and according to described image characteristic to described
Each view data at least one view data carries out the extraction of characteristic, obtains at least one characteristic;
The similarity between each characteristic at least one characteristic is obtained, and obtains the similarity
Fisrt feature data in default similarity threshold;
The initial characteristic data for reducing the destination image data is asked for according to the fisrt feature data, and according to
The initial characteristic data restores the corresponding raw image data of the destination image data.
In one embodiment, asked for for reducing the destination image data according to the fisrt feature data in execution
Initial characteristic data, and the corresponding raw image data of the destination image data is restored according to the initial characteristic data
When, it is specific to perform following operation:
Computing of averaging is carried out to the fisrt feature data using mean algorithm, is obtained for reducing the target image
The initial characteristic data of data, and the corresponding original image of the destination image data is restored according to the initial characteristic data
Data.
In one embodiment, described image characteristic includes:Face characteristic, color characteristic data, texture are special
Levy one or more in data, character shape data and spatial relation characteristics data.
In embodiments of the present invention, by obtaining the image feature data of selected destination image data, generation includes image
The image of characteristic obtains instruction, and image is obtained into instruction transmission to server, so that server is obtained and characteristics of image
At least one associated view data of data, at least one view data that the reception server sends, using characteristics of image number
Treatment is analyzed according to at least one view data, to reduce the corresponding raw image data of destination image data.By figure
As characteristic obtains at least one view data being associated with destination image data, and by least one view data
Analysis therefrom restores the corresponding raw image data of destination image data, improves the image that destination image data is carried in itself
The authenticity of information;By obtaining fisrt feature data of the similarity in default similarity threshold, reduce by least one
Characteristic asks for the error of initial characteristic data, and then increased the target image number restored by least one view data
According to the authenticity of corresponding raw image data.
It should be noted that for above each method embodiment, a series of actions is stated that in order to be briefly described
Combination, but those skilled in the art should know, sequence of movement of the present invention not by described by is limited, and some steps can be with
Serially or simultaneously carried out using other.Secondly, those skilled in the art should know, embodiment described in this description belongs to
In preferred embodiment, necessary to involved operation and the unit not necessarily present invention.And in the above-described embodiments, to each
The description of individual embodiment all emphasizes particularly on different fields, and does not have the part described in detail in certain embodiment, may refer to the correlation of other embodiment
Description.
In addition, each functional unit in each embodiment of the invention can be integrated in a unit for treatment, it is also possible to
It is that unit is individually physically present, or two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.The integrated unit is such as
Fruit is to realize in the form of SFU software functional unit and as independent production marketing or when using, can store can in a computer
In reading storage medium.Based on such understanding, technical scheme substantially contributes to prior art in other words
Part or all or part of the technical scheme can be embodied in the form of software product, the computer software product
Storage is in a storage medium, including some instructions are used to so that a computer equipment (can be personal computer, server
Or the network equipment etc.) perform all or part of step of each embodiment methods described of the invention.Wherein described storage is situated between
Matter includes:USB flash disk, read-only storage (Read-Only Memory, ROM), random access memory (Random Access
Memory, RAM), mobile hard disk, magnetic disc or CD etc. are various can be with the medium of store program codes.
Above disclosed is only present pre-ferred embodiments, can not limit the right model of the present invention with this certainly
Enclose, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (9)
1. a kind of image processing method, it is characterised in that including:
The image feature data of selected destination image data is obtained, image of the generation comprising described image characteristic is obtained and referred to
Order;
Described image is obtained into instruction to send to server, so as to the server is obtained be associated with described image characteristic
At least one view data;
At least one view data that the server sends is received, using described image characteristic to described at least one
Individual view data is analyzed treatment, to reduce the corresponding raw image data of the destination image data.
2. the method for claim 1, it is characterised in that at least one figure that the reception server sends
As data, treatment is analyzed at least one view data using described image characteristic, to reduce the target
The corresponding raw image data of view data, including:
Receive at least one view data that the server sends, and according to described image characteristic to it is described at least
Each view data in one view data carries out the extraction of characteristic, obtains at least one characteristic;
The similarity between each characteristic at least one characteristic is obtained, and obtains the similarity pre-
If the fisrt feature data in similarity threshold;
The initial characteristic data for reducing the destination image data is asked for according to the fisrt feature data, and according to described
Initial characteristic data restores the corresponding raw image data of the destination image data.
3. method as claimed in claim 2, it is characterised in that described to be asked for for reducing according to the fisrt feature data
The initial characteristic data of destination image data is stated, and the destination image data correspondence is restored according to the initial characteristic data
Raw image data, including:
Computing of averaging is carried out to the fisrt feature data using mean algorithm, is obtained for reducing the destination image data
Initial characteristic data, and the corresponding original image number of the destination image data is restored according to the initial characteristic data
According to.
4. the method for claim 1, it is characterised in that described image characteristic includes:Face characteristic, color
One or more in characteristic, textural characteristics data, character shape data and spatial relation characteristics data.
5. a kind of image-data processing apparatus, it is characterised in that including:
Instruction generation unit, the image feature data for obtaining selected destination image data, generation includes described image feature
The image of data obtains instruction;
Instruction sending unit, sends to server for described image to be obtained into instruction so that the server obtain with it is described
At least one associated view data of image feature data;
Data convert unit, it is special using described image for receiving at least one view data that the server sends
Levy data and treatment is analyzed at least one view data, to reduce the corresponding original image of the destination image data
Data.
6. equipment as claimed in claim 5, it is characterised in that the data convert unit includes:
Characteristic obtains subelement, for receiving at least one view data that the server sends, and according to institute
Stating image feature data carries out the extraction of characteristic to each view data at least one view data, obtain to
A few characteristic;
First data acquisition subelement, it is similar between each characteristic at least one characteristic for obtaining
Degree, and obtain fisrt feature data of the similarity in default similarity threshold;
Data convert subelement, for being asked for for reducing the original of the destination image data according to the fisrt feature data
Characteristic, and the corresponding raw image data of the destination image data is restored according to the initial characteristic data.
7. equipment as claimed in claim 6, it is characterised in that the data convert subelement specifically for,
Computing of averaging is carried out to the fisrt feature data using mean algorithm, is obtained for reducing the destination image data
Initial characteristic data, and the corresponding original image number of the destination image data is restored according to the initial characteristic data
According to.
8. equipment as claimed in claim 5, it is characterised in that described image characteristic includes:Face characteristic, color
One or more in characteristic, textural characteristics data, character shape data and spatial relation characteristics data.
9. a kind of terminal, it is characterised in that the terminal includes that the image real time transfer as described in claim any one of 5-8 sets
It is standby.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710005059.3A CN106846244A (en) | 2017-01-04 | 2017-01-04 | A kind of image processing method, equipment and terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710005059.3A CN106846244A (en) | 2017-01-04 | 2017-01-04 | A kind of image processing method, equipment and terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106846244A true CN106846244A (en) | 2017-06-13 |
Family
ID=59118482
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710005059.3A Pending CN106846244A (en) | 2017-01-04 | 2017-01-04 | A kind of image processing method, equipment and terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106846244A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663053A (en) * | 2012-03-30 | 2012-09-12 | 上海博康智能信息技术有限公司 | Distributed server system based on image content search |
CN103268338A (en) * | 2013-05-16 | 2013-08-28 | 北京京东尚科信息技术有限公司 | Method and server device for providing images and terminal device |
CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
CN105447846A (en) * | 2014-08-25 | 2016-03-30 | 联想(北京)有限公司 | Image-processing method and electronic device |
CN105741171A (en) * | 2016-01-28 | 2016-07-06 | 李天� | Character feature image processing method for credit reference systems and credit reference system |
CN105898302A (en) * | 2016-04-28 | 2016-08-24 | 上海斐讯数据通信技术有限公司 | Image transmission method and system based on compressed sensing |
-
2017
- 2017-01-04 CN CN201710005059.3A patent/CN106846244A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102663053A (en) * | 2012-03-30 | 2012-09-12 | 上海博康智能信息技术有限公司 | Distributed server system based on image content search |
CN103268338A (en) * | 2013-05-16 | 2013-08-28 | 北京京东尚科信息技术有限公司 | Method and server device for providing images and terminal device |
CN103927387A (en) * | 2014-04-30 | 2014-07-16 | 成都理想境界科技有限公司 | Image retrieval system, method and device |
CN105447846A (en) * | 2014-08-25 | 2016-03-30 | 联想(北京)有限公司 | Image-processing method and electronic device |
CN105741171A (en) * | 2016-01-28 | 2016-07-06 | 李天� | Character feature image processing method for credit reference systems and credit reference system |
CN105898302A (en) * | 2016-04-28 | 2016-08-24 | 上海斐讯数据通信技术有限公司 | Image transmission method and system based on compressed sensing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3370188B1 (en) | Facial verification method, device, and computer storage medium | |
CN106682632B (en) | Method and device for processing face image | |
CN111325271B (en) | Image classification method and device | |
CN112527115B (en) | User image generation method, related device and computer program product | |
CN106067024A (en) | Feature point extraction device and method and the image matching system utilizing it | |
US20130042509A1 (en) | Method and system for producing greeting cards | |
CN105956051A (en) | Information finding method, device and system | |
CN104333730A (en) | Video communication method and video communication device | |
CN111062426A (en) | Method, device, electronic equipment and medium for establishing training set | |
CN113781356A (en) | Training method of image denoising model, image denoising method, device and equipment | |
WO2023024653A1 (en) | Image processing method, image processing apparatus, electronic device and storage medium | |
CN114120413A (en) | Model training method, image synthesis method, device, equipment and program product | |
CN103955713A (en) | Icon recognition method and device | |
CN105022480A (en) | Input method and terminal | |
CN112634182A (en) | Image correction method, device and equipment based on light field and storage medium | |
CN106846244A (en) | A kind of image processing method, equipment and terminal | |
JP2023040201A (en) | Face recognition method and device, apparatus and storage medium | |
KR20230086998A (en) | A computer program that creates virtual character contnet by adding noise to face segment regions | |
KR20230086999A (en) | A recording medium recording a virtual character content creation program | |
KR20230086996A (en) | A computer program that performs the noise addition process | |
CN115019057A (en) | Image feature extraction model determining method and device and image identification method and device | |
JP2023526809A (en) | A method for safely using a first neural network on input data and a method for learning parameters of a second neural network | |
CN112015319A (en) | Screenshot processing method and device and storage medium | |
CN113676734A (en) | Image compression method and image compression device | |
CN111738087A (en) | Method and device for generating face model of game role |
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 |
Application publication date: 20170613 |
|
RJ01 | Rejection of invention patent application after publication |