CN110222207A - Picture sorting method and device and intelligent terminal - Google Patents
Picture sorting method and device and intelligent terminal Download PDFInfo
- Publication number
- CN110222207A CN110222207A CN201910439414.7A CN201910439414A CN110222207A CN 110222207 A CN110222207 A CN 110222207A CN 201910439414 A CN201910439414 A CN 201910439414A CN 110222207 A CN110222207 A CN 110222207A
- Authority
- CN
- China
- Prior art keywords
- picture
- pictorial information
- subpixel area
- target pixel
- pixel location
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000002131 composite material Substances 0.000 claims abstract description 5
- 230000000694 effects Effects 0.000 claims description 44
- 230000015572 biosynthetic process Effects 0.000 claims description 38
- 238000003786 synthesis reaction Methods 0.000 claims description 38
- 238000010586 diagram Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 abstract description 5
- 230000002194 synthesizing effect Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 238000005457 optimization Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
Abstract
The application discloses a picture arrangement method and device and an intelligent terminal. The method comprises the following steps: acquiring pictures to be sorted; classifying the acquired pictures to be sorted according to the background; the pictures to be sorted of the same background are classified into one type; if the number of the pictures to be sorted in the same background is larger than or equal to a first threshold, synthesizing the pictures to be sorted in the same background to obtain a synthesized picture; and the picture information of the target pixel position of the synthesized picture is obtained according to the picture information of the same position with the target pixel position in the plurality of pictures to be sorted. Therefore, the user can quickly screen out satisfactory pictures from the composite pictures, and the screening efficiency is improved.
Description
Technical field
This application involves photo finishing technical field more particularly to a kind of method for sorting of picture, device and intelligent terminal.
Background technique
At present, taking pictures using more more and more universal and extensive in intelligent terminal.Common intelligent terminal includes mobile phone, shooting
About several different-effects of photo mode: first is that it is background blurring, second is that face it is clear, third is that panorama is clear.Based on same
One background, user wish to take different-effect, since user's majority is not professional, during taking pictures, although carrying out
Various adjustment, but effect may be unobvious, and user may clap many to take the photo of same background.Generally, it claps
The photo taken the photograph can be stored entirely in the file of a default, after taking pictures, need to take much time to shooting with regard to user
A large amount of photo screened, at this moment, may compare and check repeatedly, think that the optimal photo of effect is protected to find out user
Friend is deposited or issues, screening efficiency is very low.
Summary of the invention
The purpose of the application is to provide the method for sorting, device and intelligent terminal of a kind of picture, to solve in the related technology
The low problem of photo screening efficiency.
The purpose of the application is achieved through the following technical solutions:
A kind of method for sorting of picture is applied in intelligent terminal, which comprises
Obtain picture to be arranged；
Classify to picture to be arranged described in acquisition according to background；Wherein, same background is described to be arranged
Picture is divided into one kind；
If the number of the picture to be arranged in same background is more than or equal to first threshold, will be in same background
Multiple described pictures to be arranged carry out synthesis processing, obtain synthesising picture；Wherein, the object pixel position of the synthesising picture
The pictorial information set is the pictorial information in picture to be arranged according to multiple with the target pixel location same position
It obtains.
Optionally, the synthesis processing, comprising:
According to identical pixel region division rule, by picture segmentation to be arranged described in every at multiple sub-pixel areas
Domain；
Each target pixel location of the synthesising picture is determined according to each subpixel area；
The corresponding pictorial information of each subpixel area in picture to be arranged described in obtaining every respectively；
According to the corresponding pictorial information of each subpixel area of acquisition, the picture of each target pixel location is determined
Information；
The pictorial information of determining each target pixel location is synthesized, a synthesising picture is obtained.
Optionally, the corresponding pictorial information of each subpixel area according to acquisition, determines each target picture
The pictorial information of plain position, comprising:
Clarity identification is carried out to the corresponding pictorial information of each subpixel area of acquisition；
Clarity classification is carried out to the pictorial information of each subpixel area of acquisition according to the clarity of identification；
Determine the synthetic effect of the synthesising picture；The synthetic effect includes: that background blurring, face is clear or panorama
Clearly；
It is classified, is determined according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area
The pictorial information of each target pixel location.
Optionally, according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area point
Grade, determines the pictorial information of each target pixel location, comprising:
If it is determined that the synthetic effect of the synthesising picture includes background blurring, the background of the acquisition picture to be arranged；
Determine the corresponding target pixel location of the background of the acquisition；The object pixel corresponding for the background of the acquisition
Position selects the pictorial information of the fuzzy subpixel area from the pictorial information of corresponding each subpixel area,
And the pictorial information of the fuzzy subpixel area of selection is handled to obtain the object pixel using preset algorithm
The pictorial information of position；For the corresponding target pixel location in region other than the background of the acquisition, from corresponding each
The pictorial information of the clearly subpixel area is selected in the pictorial information of the subpixel area, and uses the pre- imputation
The picture that method is handled to obtain the target pixel location to the pictorial information of the clearly described subpixel area of selection is believed
Breath；
If it is determined that the synthetic effect of the synthesising picture includes that face is clear, using the human face recognition model, from each institute
It states in picture to be arranged and identifies face, determine the corresponding target pixel location of the face of the identification；For the knowledge
The corresponding target pixel location of other face, selects clearly from the pictorial information of corresponding each subpixel area
The pictorial information of the subpixel area, and using preset algorithm to the pictorial information of the clearly described subpixel area of selection
It is handled to obtain the pictorial information of the target pixel location；It is corresponding for the region other than the face of the identification described
Target pixel location selects the figure of the fuzzy subpixel area from the pictorial information of corresponding each subpixel area
Piece information, and the pictorial information of the fuzzy subpixel area of selection is handled to obtain institute using the preset algorithm
State the pictorial information of target pixel location；
If it is determined that the synthetic effect of the synthesising picture includes that panorama is clear, for each target pixel location, from
The pictorial information of the clearly subpixel area is selected in the pictorial information of corresponding each subpixel area.
Optionally, the preset algorithm includes fuzzy algorithmic approach.
Optionally, further includes:
Show the synthesising picture.
Optionally, the display synthesising picture, comprising:
The synthesising picture is shown on editable interface.
Optionally, if the number of the picture to be arranged in the same background be less than first threshold, to it is described to
The picture of arrangement optimizes processing.
Optionally, the optimization processing, including deblurring processing.
Optionally, picture to be arranged described in multiple by same background carries out synthesis processing, obtains composite diagram
Piece, comprising:
The feature of target object is carried out to the picture to be arranged using the Feature Selection Model of preset target object
It extracts；
According to the feature of the target object of extraction, the similarity between each picture to be arranged is calculated；
According to the similarity of calculating, picture to be arranged described in multiple in same background is classified；Wherein, most phase
As the picture to be arranged be divided into one kind；
In every class it is most like described in picture to be arranged, picture to be arranged described in multiple is subjected to synthesis processing,
Obtain a synthesising picture.
Optionally, it is described it is most like in every class described in picture to be arranged, by picture to be arranged described in multiple into
Row synthesis processing, after obtaining a synthesising picture, further includes:
By it is all kinds of it is most like described in the corresponding synthesising picture of picture to be arranged carry out synthesis processing, obtain an opening and closing at
Picture.
Optionally, described to obtain picture to be arranged, comprising: the figure to be arranged is obtained from the first memory space
Piece；
After the picture to be arranged of described pair of acquisition is classified according to background, the method also includes: it will be same
The picture to be arranged of one background is stored in the second memory space；
The synthesising picture is stored in first memory space.
Optionally, it is described picture to be arranged described in same background is stored in the second memory space after, it is described
Method includes:
The prompt information for whether deleting the picture to be arranged shown；
If receiving the input operation for retaining the picture to be arranged, determines final memory space and show comprising institute
State the position of final memory space and the prompt information of committed memory；
If receiving the input operation for deleting the picture to be arranged, the prompt information deleted with caution is shown；If
The input operation for deleting the picture to be arranged is received again, deletes the picture to be arranged.
Optionally, the similarity according to calculating, picture to be arranged described in multiple in same background is divided
After class, the method also includes:
By it is a kind of it is most like described in picture to be arranged be stored in third memory space.
A kind of collating unit of picture, comprising:
Module is obtained, for obtaining picture to be arranged；
Categorization module, for classifying to picture to be arranged described in acquisition according to background；Wherein, same background
The picture to be arranged is divided into one kind；
Synthesis module, if the number for picture to be arranged described in same background is more than or equal to the first threshold
Value, carries out synthesis processing for picture to be arranged described in multiple in same background, obtains synthesising picture；Wherein, the synthesis
The pictorial information of the target pixel location of picture is same with the target pixel location in picture to be arranged according to multiple
What the pictorial information of one position obtained.
A kind of intelligent terminal, comprising:
Processor, and the memory being connected with the processor；
The memory is for storing computer program；
The processor is for calling and executing the computer program in the memory, to execute such as any of the above
The method for sorting of picture described in.
The application uses above technical scheme, has the following beneficial effects:
In the scheme of the application, it can classify to picture according to background, the picture of same background is divided into one kind, is convenient for
User is quickly searched, and, if number is more, can carry out synthesis processing automatically for the picture of same background based on this,
The pictorial information of corresponding target pixel location in synthesising picture is obtained according to the pictorial information of same position in plurality of pictures, is obtained
To synthesising picture, to reduce the quantity of picture, it is true that the pictorial information of synthesising picture, which derives from original pictorial information,
Picture, in this way, user can quickly filter out satisfied picture from synthesising picture, to improve screening efficiency.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow chart of the method for sorting for picture that the application one embodiment provides.
Fig. 2 is a kind of structural schematic diagram of the collating unit for picture that another embodiment of the application provides.
Fig. 3 is a kind of structural schematic diagram for intelligent terminal that another embodiment of the application provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of the application clearer, the technical solution of the application will be carried out below
Detailed description.Obviously, described embodiments are only a part of embodiments of the present application, instead of all the embodiments.Base
Embodiment in the application, those of ordinary skill in the art are obtained all without making creative work
Other embodiment belongs to the range that the application is protected.
Embodiment
It is a kind of flow chart of the method for sorting for picture that the application one embodiment provides referring to Fig. 1, Fig. 1.
As shown in Figure 1, a kind of method for sorting of picture provided in this embodiment, is applied in intelligent terminal, the present embodiment
Method include at least following steps:
Step 11 obtains picture to be arranged；
Step 12 classifies to the picture to be arranged of acquisition according to background；Wherein, the figure to be arranged of same background
Piece is divided into one kind；
If the number of the picture to be arranged in step 13, same background is more than or equal to first threshold, by same back
Multiple pictures to be arranged in scape carry out synthesis processing, obtain synthesising picture；Wherein, the target pixel location of synthesising picture
Pictorial information is obtained according to the pictorial information in multiple pictures to be arranged with target pixel location same position.
Picture therein can be, but not limited to photo, which can be obtained from external equipment, be also possible to local
The original photo of acquisition correspondingly, above-mentioned intelligent terminal can be the intelligent terminal with camera function, for example has function of taking pictures
Can mobile phone, plate, etc..
Wherein, the pixel size of picture is identical, and generally, a size is picture for the picture of H column pixel * L row pixel
It is same position that coordinate position, which is that coordinate position is the pixel b of (h, l) in the pixel a and picture B of (h, l), in A.
In the scheme of the application, it can classify to picture according to background, the picture of same background is divided into one kind, is convenient for
User is quickly searched, and, if number is more, can carry out synthesis processing automatically for the picture of same background based on this,
The pictorial information of corresponding target pixel location in synthesising picture is obtained according to the pictorial information of same position in plurality of pictures, is obtained
To synthesising picture, to reduce the quantity of picture, it is true that the pictorial information of synthesising picture, which derives from original pictorial information,
Picture, in this way, user can quickly filter out satisfied picture from synthesising picture, to improve screening efficiency.
The executing subject of the scheme of the present embodiment can be, but not limited to be in intelligent terminal or intelligent terminal based on hardware
And/or the functional module of software.
In implementation, there are many specific implementations of above-mentioned synthesis processing.For example, a kind of specific synthesis processing mode can
To be: according to identical pixel region division rule, by every picture segmentation to be arranged at multiple subpixel areas；According to each
Subpixel area determines each target pixel location of synthesising picture；Each subpixel area in every picture to be arranged is obtained respectively
Corresponding pictorial information；According to the corresponding pictorial information of each subpixel area of acquisition, the picture of each target pixel location is determined
Information；The pictorial information of determining each target pixel location is synthesized, a synthesising picture is obtained.
Wherein, the quantity of the subpixel area of segmentation can be configured according to practical application, herein without limitation.Specifically
, pixel region division rule can be and carry out horizontal partition, longitudinally split according to abscissa, ordinate.It, can be in implementation
The subpixel area of segmentation is marked, to be corresponded to.
If above-mentioned picture is photo, in some scenes, user has taken many photos sometimes, may be without a Zhang Zhao
Piece is that user wants, it may appear that the entirety for clapping this is all not bad, is exactly that certain places are bad, can then be repeated and select,
The time of user's many can be occupied.Therefore, carry out synthesis processing when, when can take pictures with reference to user demand take pictures effect into
The synthesis of row picture is handled.Generally, the effect taken pictures include it is background blurring, face is clear and panorama is clear.Wherein, background blurring
Refer to background than the region blur other than background.Wherein, face clearly refers to that face is more clear than the region other than face.Wherein,
Panorama clearly refers to from being all clearly as far as the scenery closely entirely shot.So, in some embodiments, according to each of acquisition
The corresponding pictorial information of subpixel area, determines the pictorial information of each target pixel location, the specific can be that:
Clarity identification is carried out to the corresponding pictorial information of each subpixel area of acquisition.Clarity knowledge is carried out in this step
Other scheme is a kind of technology of maturation, be will not enumerate herein.
Clarity classification is carried out to the pictorial information of each subpixel area of acquisition according to the clarity of identification；Clarity
Rank includes at least clear and fuzzy.Wherein, the rank of the clarity of the pictorial information of sub-picture region can also be marked
Note is to be searched.
Determine the synthetic effect of synthesising picture；Synthetic effect include: it is background blurring, face is clear or panorama is clear.This
It, can be according to the clearly each sub-pixel area for including in picture to be integrated when determining the synthetic effect of synthesising picture in step
The quantity of the quantity in domain and fuzzy each subpixel area is determined, for example, if the clearly quantity of each subpixel area
When more than or equal to second threshold, it is believed that substantially whole region is all the synthetic effect packet for clearly determining synthesising picture
Include that panorama is clear, if when clearly the quantity of each subpixel area is more than or equal to third threshold value and is less than second threshold,
Thinking most of is that clearly, only background parts are fuzzy, determines that the synthetic effect of synthesising picture includes background blurring, if clearly
The quantity of clear each subpixel area is less than third threshold value, it is believed that only this sub-fraction of face is clearly, to determine composite diagram
The synthetic effect of piece includes that face is clear.Wherein, second threshold, third threshold value specific value can be carried out according to practical application
Setting, herein without limitation.
It is classified, is determined according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area
The pictorial information of each target pixel location.
Specifically, according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area point
Grade, determines the pictorial information of each target pixel location, may is that
If it is determined that the synthetic effect of synthesising picture include it is background blurring, obtain the background of picture to be arranged；It determines and obtains
The corresponding target pixel location of background；Target pixel location corresponding for the background of acquisition, from corresponding each sub-pixel area
The pictorial information of fuzzy subpixel area is selected in the pictorial information in domain, and using preset algorithm to the fuzzy sub- picture of selection
The pictorial information in plain region is handled to obtain the pictorial information of target pixel location；For the region pair other than the background of acquisition
The target pixel location answered selects the picture of clearly subpixel area to believe from the pictorial information of corresponding each subpixel area
Breath, and the pictorial information of the clearly subpixel area of selection is handled to obtain target pixel location using preset algorithm
Pictorial information；
If it is determined that the synthetic effect of synthesising picture includes that face is clear, using human face recognition model, from figure respectively to be arranged
Face is identified in piece, determines the corresponding target pixel location of face of identification；Object pixel position corresponding for the face of identification
It sets, the pictorial information of clearly subpixel area is selected from the pictorial information of corresponding each subpixel area, and using default
Algorithm is handled to obtain the pictorial information of target pixel location to the pictorial information of the clearly subpixel area of selection；For
The corresponding target pixel location in region other than the face of identification, selects mould from the pictorial information of corresponding each subpixel area
The pictorial information of the subpixel area of paste, and carried out using pictorial information of the preset algorithm to the fuzzy subpixel area of selection
Processing obtains the pictorial information of target pixel location；
If it is determined that the synthetic effect of synthesising picture includes that panorama is clear, for each target pixel location, from corresponding each
The pictorial information of clearly subpixel area is selected in the pictorial information of subpixel area, and using preset algorithm to the clear of selection
The pictorial information of clear subpixel area is handled to obtain the pictorial information of target pixel location.
Above-mentioned preset algorithm includes fuzzy algorithmic approach.Wherein, fuzzy algorithmic approach can be mean value fuzzy algorithmic approach, for example, can incite somebody to action
The pictorial information of the corresponding each subpixel area of target pixel location is averaged based on the sliding window of default size, obtains target
The pictorial information of location of pixels can specifically refer to the relevant technologies.
In the present embodiment, the effect of taking pictures that user wants is gone out according to picture analyzing to be arranged, then according to taking pictures effect,
The pictorial information of satisfactory subpixel area is found from each subpixel area, in this way, the pictorial information of synthesising picture is equal
From the pictorial information of original photo, the effect that only user can not take pictures is synthesized according to these pictorial informations, can
To obtain perfect effect, obtained picture can preferably cater to the demand of user, improve the experience effect of user.
In implementation, when carrying out clarity classification, clarity can also be classified further according to the range of clarity,
It is general clear including being apparent.Wherein, obscuring also can also further be classified, including very fuzzy, general fuzzy.Correspondingly, also
The clarity rank of the pictorial information of the corresponding subpixel area of each target pixel location can be predefined, then reselection
The subpixel area of appropriate level.For example, can choose general fuzzy, general clearly subpixel area on the boundary of background
Pictorial information selects the pictorial information of very fuzzy subpixel area within background, selects the sub- picture being apparent within non-background
The pictorial information in plain region.It can choose the pictorial information of general clear, generally fuzzy subpixel area on the boundary of face,
The pictorial information of very fuzzy subpixel area is selected within non-face, and the figure for the subpixel area being apparent is selected within face
Piece information.
It is understood that also to show synthesising picture after synthesising picture.Specifically, can be shown on editable interface
Show synthesising picture.In this way, user can not only check the picture of synthesis, can also on editable interface edit-modify and wash with watercolours
Dye, to realize customized adjustment, and the customized Suitable content of learning and memory, automatically similarly adjusts subsequent synthesising picture
It is whole.
In implementation, if the number of the picture to be arranged in same background is less than first threshold, treat the picture of arrangement into
Row optimization processing.Optionally, there are many implementations of optimization processing.For example, deblurring processing can be carried out, so that wait arrange
Picture be more clear.Specifically, the scheme of deblurring processing can refer to the relevant technologies, will not enumerate herein.
The specific numerical value of first threshold can be configured according to actual needs.
For example, the value of first threshold is 2-5, it is optionally 2.For single picture, processing is only optimized, is obtained
Clearly picture.
Based in the above related embodiment, in above-mentioned steps 13, multiple pictures to be arranged in same background are carried out
Synthesis processing, obtains synthesising picture, specific it may also is that the Feature Selection Model using preset target object treats arrangement
The feature extraction of picture progress target object；According to the feature of the target object of extraction, calculate between picture respectively to be arranged
Similarity；According to the similarity of calculating, multiple pictures to be arranged in same background are classified；Wherein, most like
Picture to be arranged is divided into one kind；In the most like picture to be arranged of every class, multiple pictures to be arranged are synthesized
Processing, obtains a synthesising picture.In this way, most like picture can be synthesized, synthetic effect is more preferable.Further,
Multiple pictures to be arranged can also be subjected to synthesis processing, obtain an opening and closing in the most like picture to be arranged of every class
After picture, the corresponding synthesising picture of all kinds of most like pictures to be arranged is subjected to synthesis processing, obtain an opening and closing at
Picture.Further enhance the effect of synthesising picture.
Wherein, the feature extraction of target object may include that face characteristic extracts model and/or limbs Feature Selection Model,
Etc..Specifically, the Feature Selection Model of target object can be trained to obtain by convolutional neural networks, specific implementation can
To refer to the relevant technologies, will not enumerate herein.
Wherein, similarity can refer to cosine similarity, can specifically implement with reference to the relevant technologies, details are not described herein again.
In above-mentioned steps 11, picture to be arranged is obtained, it is specific: figure to be arranged is obtained from the first memory space
Piece；After classifying to the picture to be arranged of acquisition according to background, the picture to be arranged of same background is stored in
In two memory spaces；Synthesising picture is stored in the first memory space.
Wherein, the first memory space can refer to the memory space of default, for example can be the text of the photograph album of system default
Part folder.
In the present embodiment, in order to facilitate ordinary user's use habit, searches, only synthesising picture is stored in silent convenient for user
In the memory space recognized, and by the storage of sorted photo into other memory space, also, for the figure of same background
Piece is automatically saved in the same memory space, is realized and is automatically distinguished the photo of same background and different background, returns
Class, convenient for searching.
Wherein, above-mentioned memory space can refer to file.Above-mentioned first memory space is the file of default.
When the picture wait arrange of same background is stored in the second memory space, for different backgrounds, establish different
File, and the photo under same background is automatically put into a file, and named using preset naming method, than
Such as it is named with the time.
Similarly, may be used also after multiple pictures to be arranged in same background are classified according to the similarity of calculating
A kind of most like picture to be arranged to be stored in third memory space, orderly management is further realized.
In addition, will not often be clapped before also having forgotten sometimes at once by photo delete processing after user's select photo
This photo, causes photo that may always exist in the memory of mobile phone, and it is inadequate to will lead to mobile phone EMS memory space for a long time, therefore,
After the picture to be arranged of same background is stored in the second memory space, it can also show whether delete figure to be arranged
The prompt information of piece；If receiving the input operation for retaining picture to be arranged, determines final memory space and displaying includes
The position of final memory space and the prompt information of committed memory；If receiving the input operation for deleting picture to be arranged,
Show the prompt information deleted with caution；If receiving the input operation for deleting picture to be arranged again, figure to be arranged is deleted
Piece.In this way, user can be prompted to delete photo in time, memory space is cleared up.Above-mentioned second memory space is one interim
Memory space, so, it, can the memory space as known to user designated user after user's determination will retain picture.
It is installed in the intelligent terminals such as mobile phone it should be noted that the scheme of the application can be packaged into application program,
After user opens arrangement function, starts triggering and execute the process of this programme, specifically, corresponding runnable interface can be provided,
It is run in front end, picture to be arranged is selected on runnable interface for user, it is of course also possible in running background, periodically
The photo of shooting is arranged.
Referring to fig. 2, Fig. 2 is a kind of structural schematic diagram of the collating unit for picture that another embodiment of the application provides.
As shown in Fig. 2, the present embodiment provides a kind of collating units of picture, comprising:
Module 201 is obtained, for obtaining picture to be arranged；
Categorization module 202 is classified for the picture to be arranged to acquisition according to background；Wherein, same background
Picture to be arranged is divided into one kind；
Synthesis module 203, if the number for the picture to be arranged in same background is more than or equal to first threshold,
Multiple pictures to be arranged in same background are subjected to synthesis processing, obtain synthesising picture；Wherein, the target picture of synthesising picture
The pictorial information of plain position is obtained according to the pictorial information in multiple pictures to be arranged with target pixel location same position
's.
Optionally, synthesis module is specifically used for:
According to identical pixel region division rule, by every picture segmentation to be arranged at multiple subpixel areas；
Each target pixel location of synthesising picture is determined according to each subpixel area；
The corresponding pictorial information of each subpixel area in every picture to be arranged is obtained respectively；
According to the corresponding pictorial information of each subpixel area of acquisition, the pictorial information of each target pixel location is determined；
The pictorial information of determining each target pixel location is synthesized, a synthesising picture is obtained.
Optionally, according to the corresponding pictorial information of each subpixel area of acquisition, the picture of each target pixel location is determined
When information, synthesis module is specifically used for:
Clarity identification is carried out to the corresponding pictorial information of each subpixel area of acquisition；
Clarity classification is carried out to the pictorial information of each subpixel area of acquisition according to the clarity of identification；
Determine the synthetic effect of synthesising picture；Synthetic effect include: it is background blurring, face is clear or panorama is clear；
It is classified, is determined according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area
The pictorial information of each target pixel location.
Optionally, according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area point
Grade, when determining the pictorial information of each target pixel location, synthesis module is specifically used for:
If it is determined that the synthetic effect of synthesising picture include it is background blurring, obtain the background of picture to be arranged；It determines and obtains
The corresponding target pixel location of background；Target pixel location corresponding for the background of acquisition, from corresponding each sub-pixel area
The pictorial information of fuzzy subpixel area is selected in the pictorial information in domain, and using preset algorithm to the fuzzy sub- picture of selection
The pictorial information in plain region is handled to obtain the pictorial information of target pixel location；For the region pair other than the background of acquisition
The target pixel location answered selects the picture of clearly subpixel area to believe from the pictorial information of corresponding each subpixel area
Breath, and the pictorial information of the clearly subpixel area of selection is handled to obtain target pixel location using preset algorithm
Pictorial information；
If it is determined that the synthetic effect of synthesising picture includes that face is clear, using human face recognition model, from figure respectively to be arranged
Face is identified in piece, determines the corresponding target pixel location of face of identification；Object pixel position corresponding for the face of identification
It sets, the pictorial information of clearly subpixel area is selected from the pictorial information of corresponding each subpixel area, and using default
Algorithm is handled to obtain the pictorial information of target pixel location to the pictorial information of the clearly subpixel area of selection；For
The corresponding target pixel location in region other than the face of identification, selects mould from the pictorial information of corresponding each subpixel area
The pictorial information of the subpixel area of paste, and carried out using pictorial information of the preset algorithm to the fuzzy subpixel area of selection
Processing obtains the pictorial information of target pixel location；
If it is determined that the synthetic effect of synthesising picture includes that panorama is clear, for each target pixel location, from corresponding each
The pictorial information of clearly subpixel area is selected in the pictorial information of subpixel area.
Optionally, preset algorithm includes fuzzy algorithmic approach.
Optionally, the device of the present embodiment further includes display module, is used for:
Show synthesising picture.
Optionally, display module is specifically used for:
Synthesising picture is shown on editable interface.
It optionally, further include optimization processing module, if the number for the picture to be arranged in same background is less than
One threshold value, the picture for treating arrangement optimize processing.
Optionally, optimization processing module is specifically used for deblurring and handles.
Optionally, synthesis module is specifically used for:
The feature extraction of target object is carried out using the picture that the Feature Selection Model of preset target object treats arrangement；
According to the feature of the target object of extraction, the similarity between picture respectively to be arranged is calculated；
According to the similarity of calculating, multiple pictures to be arranged in same background are classified；Wherein, most like
Picture to be arranged is divided into one kind；
In the most like picture to be arranged of every class, multiple pictures to be arranged are subjected to synthesis processing, obtain one
Synthesising picture.
Optionally, in the most like picture to be arranged of every class, multiple pictures to be arranged is subjected to synthesis processing, are obtained
To after a synthesising picture, synthesis module is also used to:
The corresponding synthesising picture of all kinds of most like pictures to be arranged is subjected to synthesis processing, obtains a composite diagram
Piece.
Optionally, module is obtained, is specifically used for: obtaining picture to be arranged from the first memory space；
The device of the present embodiment further includes preserving module, is classified for the picture to be arranged to acquisition according to background
Later, the picture to be arranged of same background is stored in the second memory space；Synthesising picture is stored in the first storage sky
Between in.
Optionally, after the picture to be arranged of same background being stored in the second memory space, display module is also used
In:
The prompt information for whether deleting picture to be arranged shown；
If preserving module is also used to receive the input operation for retaining picture to be arranged, final memory space is determined,
Display module is also used to show the prompt information of the position comprising final memory space and committed memory；
Display module shows the prompt deleted with caution if being also used to receive the input operation for deleting picture to be arranged
Information；Preserving module, if deleting picture to be arranged for receiving the input operation for deleting picture to be arranged again.
Optionally, preserving module is also used to the similarity according to calculating, by multiple pictures to be arranged in same background
After being classified, a kind of most like picture to be arranged is stored in third memory space.
The specific embodiment of the collating unit of picture provided by the embodiments of the present application can refer to the figure of any of the above example
The embodiment of the method for sorting of piece, details are not described herein again.
It is a kind of structural schematic diagram for intelligent terminal that another embodiment of the application provides referring to Fig. 3, Fig. 3.
As shown in figure 3, the present embodiment provides a kind of intelligent terminals, comprising:
Processor 301, and the memory 302 being connected with processor 301；
Memory 302 is for storing computer program；
Processor 301 is for calling and executing the computer program in memory, to execute such as any of the above embodiment institute
The method for sorting for the picture stated.
The specific embodiment of intelligent terminal provided by the embodiments of the present application can be with reference to picture described in any of the above example
Method for sorting embodiment, details are not described herein again.
It is understood that same or similar part can mutually refer in the various embodiments described above, in some embodiments
Unspecified content may refer to the same or similar content in other embodiments.
It should be noted that term " first ", " second " etc. are used for description purposes only in the description of the present application, without
It can be interpreted as indication or suggestion relative importance.In addition, in the description of the present application, unless otherwise indicated, the meaning of " multiple "
Refer at least two.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the application includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be by the application
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each section of the application can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, can integrate in a processing module in each functional unit in each embodiment of the application
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of method for sorting of picture, which is characterized in that be applied in intelligent terminal, which comprises
Obtain picture to be arranged；
Classify to picture to be arranged described in acquisition according to background；Wherein, the picture to be arranged of same background
It is divided into one kind；
If the number of the picture to be arranged in same background is more than or equal to first threshold, will be more in same background
Picture Zhang Suoshu to be arranged carries out synthesis processing, obtains synthesising picture；Wherein, the target pixel location of the synthesising picture
Pictorial information is that the pictorial information in picture to be arranged according to multiple with the target pixel location same position obtains
's.
2. the method according to claim 1, wherein the synthesis is handled, comprising:
According to identical pixel region division rule, by picture segmentation to be arranged described in every at multiple subpixel areas；
Each target pixel location of the synthesising picture is determined according to each subpixel area；
The corresponding pictorial information of each subpixel area in picture to be arranged described in obtaining every respectively；
According to the corresponding pictorial information of each subpixel area of acquisition, the picture letter of each target pixel location is determined
Breath；
The pictorial information of determining each target pixel location is synthesized, a synthesising picture is obtained.
3. according to the method described in claim 2, it is characterized in that, described corresponding according to each subpixel area of acquisition
Pictorial information determines the pictorial information of each target pixel location, comprising:
Clarity identification is carried out to the corresponding pictorial information of each subpixel area of acquisition；
Clarity classification is carried out to the pictorial information of each subpixel area of acquisition according to the clarity of identification；
Determine the synthetic effect of the synthesising picture；The synthetic effect include: it is background blurring, face is clear or panorama is clear
It is clear；
It is classified according to the clarity of the fixed synthetic effect and the pictorial information of each subpixel area, determines each institute
State the pictorial information of target pixel location.
4. according to the method described in claim 3, determination is each it is characterized in that, described according to the fixed synthetic effect
The pictorial information of the target pixel location, comprising:
If it is determined that the synthetic effect of the synthesising picture includes background blurring, the background of the acquisition picture to be arranged；It determines
The corresponding target pixel location of the background of the acquisition；The object pixel position corresponding for the background of the acquisition
It sets, the pictorial information of the fuzzy subpixel area is selected from the pictorial information of corresponding each subpixel area, and
It is handled to obtain the object pixel position using pictorial information of the preset algorithm to the fuzzy subpixel area of selection
The pictorial information set；For the corresponding target pixel location in region other than the background of the acquisition, from corresponding each institute
The pictorial information for selecting the clearly subpixel area in the pictorial information of subpixel area is stated, and uses the preset algorithm
The pictorial information of the clearly described subpixel area of selection is handled to obtain the pictorial information of the target pixel location；
If it is determined that the synthetic effect of the synthesising picture includes that face is clear, using the human face recognition model, from it is each it is described to
Face is identified in the picture of arrangement, determines the corresponding target pixel location of the face of the identification；For the identification
The corresponding target pixel location of face selects clearly described from the pictorial information of corresponding each subpixel area
The pictorial information of subpixel area, and carried out using pictorial information of the preset algorithm to the clearly described subpixel area of selection
Processing obtains the pictorial information of the target pixel location；For the corresponding target in region other than the face of the identification
Location of pixels selects the picture of the fuzzy subpixel area to believe from the pictorial information of corresponding each subpixel area
Breath, and the pictorial information of the fuzzy subpixel area of selection is handled to obtain the mesh using the preset algorithm
Mark the pictorial information of location of pixels；
If it is determined that the synthetic effect of the synthesising picture includes that panorama is clear, for each target pixel location, from correspondence
Each subpixel area pictorial information in select the pictorial information of the clearly subpixel area.
5. the method according to claim 1, wherein figure to be arranged described in multiple by same background
Piece carries out synthesis processing, obtains synthesising picture, comprising:
The feature extraction of target object is carried out to the picture to be arranged using the Feature Selection Model of preset target object；
According to the feature of the target object of extraction, the similarity between each picture to be arranged is calculated；
According to the similarity of calculating, picture to be arranged described in multiple in same background is classified；Wherein, most like
The picture to be arranged is divided into one kind；
In every class it is most like described in picture to be arranged, picture to be arranged described in multiple is subjected to synthesis processing, is obtained
One synthesising picture.
6. according to the method described in claim 5, it is characterized in that, it is described it is most like in every class described in picture to be arranged
In, picture to be arranged described in multiple is subjected to synthesis processing, after obtaining a synthesising picture, further includes:
By it is all kinds of it is most like described in the corresponding synthesising picture of picture to be arranged carry out synthesis processing, obtain a composite diagram
Piece.
7. according to the method according to claim 1, wherein described obtain picture to be arranged, comprising: from first
The picture to be arranged is obtained in memory space；
After the picture to be arranged of described pair of acquisition is classified according to background, the method also includes: by same back
The picture to be arranged of scape is stored in the second memory space；
The synthesising picture is stored in first memory space.
8. the method according to the description of claim 7 is characterized in that described save picture to be arranged described in same background
After in the second memory space, which comprises
The prompt information for whether deleting the picture to be arranged shown；
If receiving the input operation of the reservation picture to be arranged, determines final memory space and show comprising described in most
The position of whole memory space and the prompt information of committed memory；
If receiving the input operation for deleting the picture to be arranged, the prompt information deleted with caution is shown；If again
The input operation for deleting the picture to be arranged is received, the picture to be arranged is deleted.
9. a kind of collating unit of picture characterized by comprising
Module is obtained, for obtaining picture to be arranged；
Categorization module, for classifying to picture to be arranged described in acquisition according to background；Wherein, same background is described
Picture to be arranged is divided into one kind；
Synthesis module will if the number for picture to be arranged described in same background is more than or equal to first threshold
Multiple described pictures to be arranged in same background carry out synthesis processing, obtain synthesising picture；Wherein, the synthesising picture
The pictorial information of target pixel location, be in picture to be arranged according to multiple with the target pixel location same position
Pictorial information obtain.
10. a kind of intelligent terminal characterized by comprising
Processor, and the memory being connected with the processor；
The memory is for storing computer program；
The processor is for calling and executing the computer program in the memory, to execute such as claim 1-8
The method for sorting of described in any item pictures.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439414.7A CN110222207B (en) | 2019-05-24 | 2019-05-24 | Picture sorting method and device and intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910439414.7A CN110222207B (en) | 2019-05-24 | 2019-05-24 | Picture sorting method and device and intelligent terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222207A true CN110222207A (en) | 2019-09-10 |
| CN110222207B CN110222207B (en) | 2021-03-30 |
Family
ID=67818138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910439414.7A Active CN110222207B (en) | 2019-05-24 | 2019-05-24 | Picture sorting method and device and intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222207B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577475A (en) * | 2012-08-03 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Picture automatic sorting method, picture processing method and devices thereof |
| CN104361572A (en) * | 2014-11-27 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Picture processing method and device |
| US20150286899A1 (en) * | 2014-04-04 | 2015-10-08 | Canon Kabushiki Kaisha | Image processing apparatus, control method, and recording medium |
| CN105120335A (en) * | 2015-08-17 | 2015-12-02 | 无锡天脉聚源传媒科技有限公司 | A method and apparatus for processing television program pictures |
| CN108932703A (en) * | 2018-06-19 | 2018-12-04 | Oppo（重庆）智能科技有限公司 | Image processing method, picture processing unit and terminal device |
| CN108961267A (en) * | 2018-06-19 | 2018-12-07 | Oppo广东移动通信有限公司 | Image processing method, picture processing unit and terminal device |
-
2019
- 2019-05-24 CN CN201910439414.7A patent/CN110222207B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103577475A (en) * | 2012-08-03 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Picture automatic sorting method, picture processing method and devices thereof |
| US20150286899A1 (en) * | 2014-04-04 | 2015-10-08 | Canon Kabushiki Kaisha | Image processing apparatus, control method, and recording medium |
| CN104361572A (en) * | 2014-11-27 | 2015-02-18 | 百度在线网络技术（北京）有限公司 | Picture processing method and device |
| CN105120335A (en) * | 2015-08-17 | 2015-12-02 | 无锡天脉聚源传媒科技有限公司 | A method and apparatus for processing television program pictures |
| CN108932703A (en) * | 2018-06-19 | 2018-12-04 | Oppo（重庆）智能科技有限公司 | Image processing method, picture processing unit and terminal device |
| CN108961267A (en) * | 2018-06-19 | 2018-12-07 | Oppo广东移动通信有限公司 | Image processing method, picture processing unit and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222207B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7760956B2 (en) | System and method for producing a page using frames of a video stream | |
| JP5934653B2 (en) | Image classification device, image classification method, program, recording medium, integrated circuit, model creation device | |
| EP3334144B1 (en) | Image processing apparatus, control method, and program for automatically generating a photoalbum as from images having a score and reflecting a desired theme | |
| US9344642B2 (en) | Method and apparatus for capturing a first image using a first configuration of a camera and capturing a second image using a second configuration of a camera | |
| US10506110B2 (en) | Image processing apparatus, control method, and storage medium | |
| US20130304743A1 (en) | Keyword assignment device, information storage device, and keyword assignment method | |
| EP2023288A1 (en) | Object recognition device, object recognition program, and image search service providing method | |
| CN107547803B (en) | Video segmentation result edge optimization processing method and device and computing equipment | |
| CN110717058B (en) | Information recommendation method and device and storage medium | |
| JP6174894B2 (en) | Image processing apparatus and image processing method | |
| CN104700442A (en) | Image processing method and system for automatic filter and character adding | |
| CN113689324A (en) | Automatic adding and deleting method and device for portrait object based on two classification labels | |
| JP2014092955A (en) | Similar content search processing device, similar content search processing method and program | |
| CN110049180A (en) | Shoot posture method for pushing and device, intelligent terminal | |
| CN107743195A (en) | A kind of photographic method, mobile terminal and storage medium | |
| JP2007036737A (en) | Image display device | |
| CN113253890A (en) | Video image matting method, system and medium | |
| CN112580750A (en) | Image recognition method and device, electronic equipment and storage medium | |
| US12045963B2 (en) | Detecting object relationships and editing digital images based on the object relationships | |
| US20240171848A1 (en) | Removing distracting objects from digital images | |
| CN110222207A (en) | Picture sorting method and device and intelligent terminal | |
| WO2012032971A1 (en) | Keyword applying device and recording medium | |
| CN112529765A (en) | Image processing method, apparatus and storage medium | |
| JP2004023656A (en) | Image processing device, image processing method, and program | |
| CN109977247A (en) | Image processing method and image processing apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |