CN105843827A - Picture classification method and device for mobile terminal - Google Patents
Picture classification method and device for mobile terminal Download PDFInfo
- Publication number
- CN105843827A CN105843827A CN201510280259.0A CN201510280259A CN105843827A CN 105843827 A CN105843827 A CN 105843827A CN 201510280259 A CN201510280259 A CN 201510280259A CN 105843827 A CN105843827 A CN 105843827A
- Authority
- CN
- China
- Prior art keywords
- picture
- region
- original image
- pictures
- instruction
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a picture classification method and device for a mobile terminal with the view of solving problems in the prior art that the existing picture classification method has limitations and low picture search efficiency and poorer users' experience. The method comprises following steps: acquiring regional pictures corresponding to selected regions obtained by region selection of a first original pictures; searching second original pictures matching the regional pictures in a picture set saved in the mobile terminal; and classifying the searched second original pictures into the same category. The picture classification method and device for the mobile terminal have following beneficial effects: a classification mode is more flexible and picture searching efficiency is increased; all kinds of user's needs can be satisfied and users\ experience is improved.
Description
Technical field
The present invention relates to technical field of mobile terminals, particularly relate to the picture classification side of a kind of mobile terminal
Method and device.
Background technology
Along with developing rapidly of communication technology, mobile terminal has had become as must not in people's live and work
The means of communication that can lack, has provided the user many conditions easily, along with mobile terminal is used by user
The requirement experienced is more and more higher, and the kind of mobile terminal is more and more abundanter, and function the most from strength to strength, is clapped
According to function as one of the basic function of mobile terminal, increasingly favored by users.
In order to meet the demand of user, the internal memory of mobile terminal is increasing, and camera function is stronger,
User's storage picture number in the terminal gets more and more, therefore, and rational picture classification method energy
User is enough helped quickly to navigate to the picture wanting to check.Picture in existing mobile terminal mainly according to
The modes such as album name, picture shooting time, picture shooting place are classified, and user can be from above-mentioned classification
The picture that middle lookup oneself needs.
But, existing picture classification method has limitation, user when checking picture, only in
The conditions such as photograph album name, picture shooting time, picture shooting place carry out picture browsing;And work as picture
When quantity is bigger, user can only search figure by the way of fuzzy classification is remembered or browsed a sheet by a sheet
Sheet, the search efficiency of picture is relatively low, and Consumer's Experience is poor.
Summary of the invention
The present invention provides picture classification method and the device of a kind of mobile terminal, divides solving existing picture
Class method has limitation, and the search efficiency of picture is relatively low, the problem that Consumer's Experience is poor.
In order to solve the problems referred to above, the invention discloses the picture classification method of a kind of mobile terminal, including:
Obtain the region corresponding by carrying out selection area that regional choice obtains in the first original image
Picture;
Second matched with described region picture is searched original from the pictures that mobile terminal has stored
Picture;
The second original image found is classified as same classification.
In order to solve the problems referred to above, the invention discloses the picture classifier of a kind of mobile terminal, including:
Acquisition module, for obtaining by carrying out the selected district that regional choice obtains in the first original image
The region picture that territory is corresponding;
Search module, for searching from the pictures that mobile terminal has stored and described region picture phase
The second original image joined;
Sort module, for classifying as same classification by the second original image found.
Compared with prior art, the present invention includes advantages below:
First the present invention obtains by carrying out the selection area that regional choice obtains in the first original image
Corresponding region picture, then searches from the pictures that mobile terminal has stored and matches with region picture
The second original image, finally the second original image found is classified as same classification.Therefore, when
When user wants to check the picture with certain special object, obtain the region picture that this special object is corresponding,
The picture matched with this special object can be found and as a classification according to this region picture, look into
See that this classification can view required picture, and without browsing lookup classifying from each other again, on
State mode classification more flexible, it is possible to increase the search efficiency of picture, meet the various demands of user, carry
High Consumer's Experience.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of the picture classification method of a kind of mobile terminal of the embodiment of the present invention one;
Fig. 2 is the flow chart of steps of the picture classification method of a kind of mobile terminal of the embodiment of the present invention two;
Fig. 3 is the structured flowchart of the picture classifier of a kind of mobile terminal of the embodiment of the present invention three;
Fig. 4 is the structured flowchart of the picture classifier of a kind of mobile terminal of the embodiment of the present invention four.
Detailed description of the invention
Understandable, below in conjunction with the accompanying drawings for enabling the above-mentioned purpose of the present invention, feature and advantage to become apparent from
The present invention is further detailed explanation with detailed description of the invention.
Embodiment one
With reference to Fig. 1, it is shown that the step of the picture classification method of a kind of mobile terminal of the embodiment of the present invention one
Rapid flow chart.
The picture classification method of the mobile terminal of the present embodiment may comprise steps of:
Step 101, obtains by carrying out the selection area pair that regional choice obtains in the first original image
The region picture answered.
Mobile terminal can be mobile phone, panel computer, notebook computer etc., is not any limitation as this.
Can store substantial amounts of picture in mobile terminal, user checks picture for convenience, in mobile terminal
Picture is classified, such that it is able to check picture according to classification.In the present embodiment, enter based on user's request
Row picture classification, when picture is classified by needs, user can according to the demand of self certain or
Carrying out regional choice in some picture with selected desired zone, mobile terminal can get by above-mentioned
Certain or some pictures carries out the region picture that selection area that regional choice obtains is corresponding.Wherein, district
Territory selects or to draw to draw a circle to approve the modes such as certain region in fact on screen by smearing certain region
Existing.
In the present embodiment, in order to make a distinction with region picture, by above-mentioned certain or some carry out region choosing
The picture selected is referred to as the first original image.
Step 102, searches second matched with region picture from the pictures that mobile terminal has stored
Original image.
Wherein, the picture in the pictures that mobile terminal has stored can be the photographic head by mobile terminal
The picture gathered, it is also possible to for being sent to the picture of this mobile terminal by other-end equipment, it is also possible to
The picture downloaded from website for mobile terminal, etc., this is not any limitation as by the present embodiment.According to step
The region picture got in rapid 101 can be searched and administrative division map from the pictures that mobile terminal has stored
The second original image that sheet matches, thus obtain the picture of user's request.
Step 103, classifies as same classification by the second original image found.
Above-mentioned the second original image found is classified as same classification, when user checks and above-mentioned district
During the second original image that territory picture matches, can check that from this classification second all matched is former
Beginning picture, checks that efficiency is higher.
In the embodiment of the present invention, when user wants to check the picture with certain special object, obtain this spy
Determine the region picture that object is corresponding, can find according to this region picture and to match with this special object
Picture as a classification, checks that this classification can view required picture, and without again from each
Browsing lookup in other classification, above-mentioned mode classification is more flexible, it is possible to increase the search efficiency of picture,
Meet the various demands of user, improve Consumer's Experience.
Embodiment two
With reference to Fig. 2, it is shown that the step of the picture classification method of a kind of mobile terminal of the embodiment of the present invention two
Rapid flow chart.
The picture classification method of the mobile terminal of the present embodiment may comprise steps of:
Step 201, obtains the first original image.
If the user desired that check that the picture that mobile terminal stores includes certain special object (such as user
Individual etc.) picture, then can carry out classification based on this special object checks, first obtains first original
Picture, this first original image is the picture including above-mentioned special object, and the first original image can be one
Opening to be multiple, is not any limitation as this.
Preferably, the present embodiment can obtain the first original image in the following way: receive and moving
The picture carrying out in the pictures that terminal has stored triggering when picture selects selects instruction;Parsing picture selects
Instruction, obtain picture selection instruction instruction chooses picture;Picture will be chosen to be defined as the first original image.
In which, user can choose one or more picture from the pictures that mobile terminal has stored, its
In, the picture chosen can be the picture only including above-mentioned special object (such as individual subscriber etc.), also
It can be the picture including above-mentioned special object and other objects (such as other personage, landscape etc.).
Preferably, the present embodiment can also obtain the first original image in the following way: use mobile
The camera collection picture of terminal, is defined as the first original image by the picture of collection.In which,
Can first gather one or more picture when needing to carry out picture classification, wherein, the picture of collection can be
Only include the picture of above-mentioned special object (such as individual subscriber etc.), it is also possible to above-mentioned specific right for including
As the picture with other objects (such as other personage, landscape etc.).
Step 202, obtains by carrying out the selection area pair that regional choice obtains in the first original image
The region picture answered.
Can carry out regional choice for the first original image, regional choice refers to selected above-mentioned special object
The region at place, wherein, regional choice can by smear above-mentioned special object place region or
Draw the modes such as the region drawing a circle to approve above-mentioned special object place on screen to realize.
Preferably, in the present embodiment, this step 202 can include following sub-step:
Sub-step a1, receives the regional choice of triggering when carrying out regional choice in the first original image and refers to
Order;
Sub-step a2, resolution areas selects instruction, obtains the selection area of regional choice instruction instruction;
Sub-step a3, intercepts from the first original image and belongs to the part picture of selection area as selected district
The region picture that territory is corresponding.
Instruction, this district can be selected with toggle area when user carries out regional choice in the first original image
Territory selects can include in instruction the relevant information (such as the position etc. of selection area) of selection area;To this
Obtaining the selection area that the relevant information of above-mentioned selection area is corresponding after regional choice instruction parsing, this is selected
Region is the selection area of regional choice instruction instruction;After obtaining selection area, can be original from first
Intercepting the part picture belonging to this selection area in picture, the part picture of this intercepting is i.e. as selection area
Corresponding region picture.
Wherein, the first original image can include one or more, permissible in every first original image
Select one or more region, therefore selected by carry out in the first original image that regional choice obtains
Region picture corresponding to region can include one or more.
Step 203, searches second matched with region picture from the pictures that mobile terminal has stored
Original image.
After obtaining region picture, the picture in the pictures stored region picture and mobile terminal is carried out
Coupling, the second original image matched with region picture with lookup.In the present embodiment, can be by region
Whole pictures in the pictures that picture has stored with mobile terminal mate, it is also possible to by region picture
Part picture in the pictures stored with mobile terminal mates, and is not any limitation as this.
Therefore, in a preferred embodiment, this step 203 can be from mobile terminal stored picture
The whole pictures concentrated are searched the second original image matched with region picture.
In a further advantageous embodiment, this step 203 may include that reception stores at mobile terminal
Pictures in carry out picture select time trigger picture select instruction;Resolve picture and select instruction, obtain
What picture selection instruction indicated chooses picture;From choosing, picture is searched second matched with region picture
Original image.Instruction, this figure is selected when user carries out can triggering picture when picture selects in pictures
Sheet selects the relevant information (such as choosing the title of picture, mark etc.) that can include choosing picture in instruction;
This picture is selected instruction obtain after resolving the above-mentioned relevant information choosing picture corresponding choose picture, should
Choose picture be regional choice instruction instruction choose picture;After obtaining choosing picture, can be from choosing
Picture is searched the second original image matched with region picture.
If region picture includes multiple, then this step 203 is to search from the pictures stored with complete
The second original image that the region picture in portion matches.According to the demand of user, multiple regions can be obtained
Picture, namely there is multiple matching condition, therefore need when coupling by the picture in pictures with every
Region picture all mates, to obtain the second original image matched with whole region pictures.Example
As, region picture includes two, respectively region picture 1 and region picture 2, wherein region picture 1
For region picture corresponding for special object A, region picture 2 is region picture corresponding for special object B,
The second original image then matched with region picture should include special object A and special object B.Logical
Cross multiple administrative division map sheets to mate, user's request can be met to a greater degree, and make classification more
Precision.
For every region picture, this region picture is identical with the matching process of the picture in pictures, also
I.e. for every region picture, search from the pictures that mobile terminal has stored and this region picture phase
The process of the second original image joined is identical.
This step 203 can include following sub-step:
Sub-step b1, carries out feature extraction to region picture, obtains the fisrt feature information of region picture;
Wherein, region picture is carried out feature extraction and refers to that feature extraction refers to the picture corresponding feature of employing
Extracting method, extracts corresponding characteristic information, namely extracts the information that can determine this region picture identity,
Such as can extract this region picture following characteristics information at least one: texture feature information, color
Characteristic information, shape facility information.
Therefore, at least one during this sub-step b1 can include following sub-step b11~sub-step b13
Sub-step:
Sub-step b11, carries out texture feature extraction to region picture, obtains the first texture of region picture
Characteristic information;
Texture feature extraction information, can use the method such as geometric method or modelling to obtain the stricture of vagina of this region picture
Reason feature.
Sub-step b12, carries out color feature extracted to region picture, obtains the first color of region picture
Characteristic information;
Extract color characteristic information, color histogram method or the side such as color set method or color moments method can be used
Method, obtains the color characteristic of this region picture.
Sub-step b13, carries out Shape Feature Extraction to region picture, obtains the first shape of region picture
Characteristic information.
Extract shape facility information, the methods such as Fourier's shape description symbols method or geometry parameter method can be used,
Obtain the shape facility of this region picture.
For above-mentioned texture feature information, color characteristic information and shape facility information carry out extracting concrete
Process, those skilled in the art carry out relevant treatment according to practical experience, and the present embodiment is at this no longer
It is discussed in detail.Further, extracting method is not limited to use method as indicated above, art technology
Personnel can use any suitable method according to practical situation, and this is not any limitation as by the present embodiment.
Certainly, the present embodiment being also not limited to, region picture is carried out above three characteristic information carry
Take, it is also possible to other characteristic informations (such as Gradient Features information etc.) are extracted.
Sub-step b2, respectively the second feature information of each picture in acquisition pictures;
The second feature information of this picture is all obtained for each picture in pictures.
Preferably, the present embodiment can carry out spy to the picture of storage after mobile terminal storage picture
Levy extraction, obtain the second feature information of picture, and preserve this second feature information, therefore this sub-step
B2 may include that the second feature information obtaining each picture preserved respectively.
Preferably, in the present embodiment can also need from the pictures that mobile terminal has stored search with
During the second original image that region picture matches, second of each picture in acquisition pictures is special respectively
Reference ceases.Therefore this sub-step b2 may include that and respectively each picture in pictures carried out feature
Extract, obtain the second feature information of each picture in pictures.
In this sub-step b2, the picture in pictures is carried out the process of feature extraction and above-mentioned sub-step
Region picture carries out in b1 the process basic simlarity of feature extraction, and the feature extraction with region picture is relative
Should, the feature extraction of the picture in pictures can also extract the following characteristics information of this picture at least it
One: texture feature information, color characteristic information, shape facility information.Therefore in certain pictures
Picture carries out the process of feature extraction can include at least in following sub-step b21~sub-step b23
Sub-steps:
Sub-step b21, carries out texture feature extraction to the picture in pictures, obtains the second of this picture
Texture feature information;
Sub-step b22, carries out color feature extracted to the picture in pictures, obtains the second of this picture
Color characteristic information;
Sub-step b23, carries out Shape Feature Extraction to the picture in pictures, obtains the second of this picture
Shape facility information.
Detailed process is with reference to the associated description of above-mentioned sub-step b1, and the present embodiment is the most detailed at this
Discuss.
Sub-step b3, according to fisrt feature information and second feature information, searches and region from pictures
The second original image that picture matches.
Preferably, this sub-step b3 can include following sub-step:
Sub-step b31, for each picture in pictures, calculates fisrt feature information and this figure respectively
Matching degree between the second feature information of sheet;
For each picture in pictures, the second feature information all calculating this picture is special with above-mentioned first
Matching degree between reference breath.
Matching degree between two characteristic informations can be by the difference between feature based information correspondence numerical value
Value calculates.Therefore, it is first determined fisrt feature information correspondence numerical value numerical value corresponding with second feature information,
Also fisrt feature information and second feature information the numerical value that mobile terminal is capable of identify that will be converted into;So
After, calculate the difference between fisrt feature information correspondence numerical value numerical value corresponding with second feature information;Finally,
Determining matching degree according to difference, the least matching degree of difference is the highest.Such as, if fisrt feature information includes
First texture feature information, the first color characteristic information and the first shape facility information, second feature information
Including the second texture feature information, the second color characteristic information and the second shape facility information, count the most respectively
Calculate the difference between the first texture feature information and the second texture feature information, the first color characteristic information and
Difference between second color characteristic information, between the first shape facility information and the second shape facility information
Difference, determine mating between fisrt feature information with second feature information according to above three difference
Degree.For the process according to mathematic interpolation matching degree, those skilled in the art select according to practical experience and appoint
The mode that meaning is suitable for, for example, it is possible to set the weight of every kind of characteristic information correspondence difference, then counts
The weighting calculating various characteristic information correspondence difference obtains matching degree etc.;Again for example, it is also possible to set difference
And the corresponding relation between matching degree, obtains every kind of characteristic information correspondence difference institute according to this corresponding relation right
The matching degree answered, the weight that each matching degree is set, each difference Corresponding matching degree is weighted
To whole matching degree, etc., the present embodiment is no longer discussed in detail at this.
Sub-step b32, exceedes what the picture of predetermined threshold value was defined as matching with region picture by matching degree
Second original image.
Through above-mentioned sub-step b31, obtain the second feature information of each picture in pictures with above-mentioned
Matching degree between fisrt feature information, the picture that then matching degree exceedes predetermined threshold value is defined as and district
The second original image that territory picture matches.For the concrete numerical value of above-mentioned predetermined threshold value, art technology
Personnel carry out any suitable setting according to practical experience, such as, could be arranged to 90%, 85% etc.,
This is not any limitation as by the present embodiment.
Step 204, classifies as same classification by the second original image found.
After finding the second original image matched with region picture, can be second original by find
Picture classifies as same classification, and the picture in this classification is the second original graph including above-mentioned special object
Sheet.
Preferably, in the present embodiment, in the way of picture is marked by employing, picture can be sorted out,
Therefore this step 204 can be included as the second original image interpolation matched with region picture found
The labelling set;The second original image being added with the labelling of setting is classified as same classification.Wherein,
The labelling set can be any suitable form, such as character marking, color mark etc..The present embodiment
In, it is also possible to adopt and in other ways the second original image found is classified as same classification, to this not
It is any limitation as.
The present embodiment has the advantage that
1, existing picture classification mode has limitation, and user is when checking picture, only in phase
Volume name, picture shooting time, these conditions of picture shooting place carry out picture browsing;The present embodiment carries
The picture classification mode gone out is classified with the region picture that selection area is corresponding for standard, more existing letter
Single mode classification has had the breakthrough in theory;
2, existing picture classification mode user can only be remembered by fuzzy classification or browse a sheet by a sheet
Mode search picture, the search efficiency of picture is relatively low, and Consumer's Experience is poor;The present embodiment proposes
Picture classification mode, can improve the efficiency checking picture, helps user to find rapidly and accurately and oneself thinks
Picture to be checked, filters out the most unnecessary pictorial information;
3, existing picture classification mode user to carry out the process that picture checks relatively more passive, lacked from
The initiative of main separation content is with interesting;The picture classification mode chosen content that the present embodiment proposes has
Multiformity, no matter which kind of chosen content, effectively can classify according to the demand of user, Ke Yizeng
Strong user checks the initiative during picture and interest.
Such as, in the mobile terminal of certain user, storage has a lot of photo, has user and university classmate, use
Family is with household, individual subscriber etc..In certain classmate's party, good friend wants to see all of user
The photo of individual, at this moment can select the region of individual subscriber in certain photo, uses the present embodiment to be carried
The mode classification of confession just can draw all photo classifications including individual subscriber, both can meet good friend's
Check demand, also can improve and check efficiency, protect other privacies of user simultaneously.
For aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as a series of dynamic
Combining, but those skilled in the art should know, the present invention is not by described sequence of movement
Limiting, because according to the present invention, some step can use other orders or carry out simultaneously.Secondly,
Those skilled in the art also should know, embodiment described in this description belongs to preferred embodiment,
Necessary to involved action and the module not necessarily present invention.
Embodiment three
With reference to Fig. 3, it is shown that the knot of the picture classifier of a kind of mobile terminal of the embodiment of the present invention three
Structure block diagram.
The picture classifier of the mobile terminal of the present embodiment can include with lower module:
Acquisition module 301, for obtaining by carrying out the choosing that regional choice obtains in the first original image
Determine the region picture that region is corresponding;
Search module 302, for searching from the pictures that mobile terminal has stored and region picture phase
The second original image joined;
Sort module 303, for classifying as same classification by the second original image found.
In the embodiment of the present invention, when user wants to check the picture with certain special object, obtain this spy
Determine the region picture that object is corresponding, can find according to this region picture and to match with this special object
Picture as a classification, checks that this classification can view required picture, and without again from each
Browsing lookup in other classification, above-mentioned mode classification is more flexible, it is possible to increase the search efficiency of picture,
Meet the various demands of user, improve Consumer's Experience.
Embodiment four
With reference to Fig. 4, it is shown that the knot of the picture classifier of a kind of mobile terminal of the embodiment of the present invention four
Structure block diagram.
The picture classifier of the mobile terminal of the present embodiment can include with lower module:
Acquisition module 401, for obtaining by carrying out the choosing that regional choice obtains in the first original image
Determine the region picture that region is corresponding;
Search module 402, for searching from the pictures that mobile terminal has stored and region picture phase
The second original image joined;
Sort module 403, for classifying as same classification by the second original image found.
Preferably, the picture classifier of mobile terminal can also include:
Acquisition module 404, for obtaining by carrying out region choosing in the first original image at acquisition module
Before selecting the region picture that the selection area obtained is corresponding, use the camera collection picture of mobile terminal,
The picture of collection is defined as the first original image.
Preferably, the picture classifier of mobile terminal can also include:
Receiver module 405, for obtaining by carrying out region choosing in the first original image at acquisition module
Before selecting the region picture that the selection area obtained is corresponding, receive and carry out touching when picture selects in pictures
The picture sent out selects instruction;
Parsing module 406, is used for resolving picture and selects instruction, obtain picture and select choosing of instruction instruction
Picture;
Determine module 407, for picture will be chosen to be defined as the first original image.
Preferably, acquisition module may include that
Command reception submodule, carries out the district of triggering during regional choice for receiving in the first original image
Territory selects instruction;
Instruction analyzing sub-module, selects instruction for resolution areas, obtains the choosing of regional choice instruction instruction
Determine region;
Picture intercepts submodule, for intercepting the part picture belonging to selection area from the first original image
As the region picture that selection area is corresponding.
Preferably, search module may include that
Feature extraction submodule, for region picture is carried out feature extraction, obtains the first of region picture
Characteristic information;
Acquisition of information submodule, for obtaining the second feature information of each picture in pictures respectively;
Picture searching submodule, for according to fisrt feature information and second feature information, from pictures
Search the second original image matched with region picture.
Preferably, picture searching submodule, specifically for for each picture in described pictures, divides
Ji Suan matching degree between fisrt feature information and the second feature information of picture;Matching degree is exceeded pre-
If the picture of threshold value is defined as the second original image matched with region picture.
Preferably, feature extraction submodule, specifically at least one of: region picture is carried out stricture of vagina
Reason feature extraction, obtains the first texture feature information of region picture;Region picture is carried out color characteristic
Extract, obtain the first color characteristic information of region picture;Region picture is carried out Shape Feature Extraction,
Obtain the first shape facility information of region picture.
Preferably, sort module may include that
Picture indicia submodule, adds for the second original image matched with region picture for finding
Add the labelling of setting;
Submodule sorted out by picture, for classifying as same by the second original image of the labelling being added with setting
Classification.
Preferably, region picture includes multiple, searches module, specifically for searching from pictures with complete
The second original image that the region picture in portion matches.
The present embodiment has the advantage that
1, existing picture classification mode has limitation, and user is when checking picture, only in phase
Volume name, picture shooting time, these conditions of picture shooting place carry out picture browsing;The present embodiment carries
The picture classification mode gone out is classified with the region picture that selection area is corresponding for standard, more existing letter
Single mode classification has had the breakthrough in theory;
2, existing picture classification mode user can only be remembered by fuzzy classification or browse a sheet by a sheet
Mode search picture, the search efficiency of picture is relatively low, and Consumer's Experience is poor;The present embodiment proposes
Picture classification mode, can improve the efficiency checking picture, helps user to find rapidly and accurately and oneself thinks
Picture to be checked, filters out the most unnecessary pictorial information;
3, existing picture classification mode user to carry out the process that picture checks relatively more passive, lacked from
The initiative of main separation content is with interesting;The picture classification mode chosen content that the present embodiment proposes has
Multiformity, no matter which kind of chosen content, effectively can classify according to the demand of user, Ke Yizeng
Strong user checks the initiative during picture and interest.
It should be noted that apparatus of the present invention embodiment is the device corresponding with said method, said method
In embodiment, all implementations are all be applicable to the embodiment of device, also can reach identical technology effect
Really.
For device embodiment, due to itself and embodiment of the method basic simlarity, so the comparison described
Simply, relevant part sees the part of embodiment of the method and illustrates.
Each embodiment in this specification all uses the mode gone forward one by one to describe, and each embodiment stresses
Be all the difference with other embodiments, between each embodiment, identical similar part sees mutually
?.
The present invention can described in the general context of computer executable instructions,
Such as program module.Usually, program module includes performing particular task or realizing specific abstract data class
The routine of type, program, object, assembly, data structure etc..Can also be in a distributed computing environment
Put into practice the present invention, in these distributed computing environment, by by communication network connected remotely
Reason equipment performs task.In a distributed computing environment, program module may be located at and includes storage device
In interior local and remote computer-readable storage medium.
Finally, in addition it is also necessary to explanation, in this article, the relational terms of such as first and second or the like
It is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires
Or imply relation or the order that there is any this reality between these entities or operation.And, art
Language " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that
Must include that the process of a series of key element, method, commodity or equipment not only include those key elements, but also
Including other key elements being not expressly set out, or also include for this process, method, commodity or
The key element that equipment is intrinsic.In the case of there is no more restriction, statement " including ... " limit
Fixed key element, it is not excluded that there is also in including the process of described key element, method, commodity or equipment
Other identical element.
Picture classification method and device to mobile terminal provided by the present invention, has carried out detailed Jie above
Continuing, principle and the embodiment of the present invention are set forth by specific case used herein, above reality
The explanation executing example is only intended to help to understand method and the core concept thereof of the present invention;Simultaneously for ability
The those skilled in the art in territory, according to the thought of the present invention, the most all can
Change part, and in sum, this specification content should not be construed as limitation of the present invention.
Claims (18)
1. the picture classification method of a mobile terminal, it is characterised in that including:
Obtain the region corresponding by carrying out selection area that regional choice obtains in the first original image
Picture;
Second matched with described region picture is searched original from the pictures that mobile terminal has stored
Picture;
The second original image found is classified as same classification.
Method the most according to claim 1, it is characterised in that in described acquisition by first
Before original image carries out the step of region picture corresponding to selection area that regional choice obtains, also wrap
Include:
Use the camera collection picture of described mobile terminal, the picture of collection is defined as described first former
Beginning picture.
Method the most according to claim 1, it is characterised in that in described acquisition by first
Before original image carries out the step of region picture corresponding to selection area that regional choice obtains, also wrap
Include:
Receive the picture carrying out triggering when picture selects in described pictures and select instruction;
Resolving described picture and select instruction, obtain the selection instruction instruction of described picture chooses picture;
Picture is chosen to be defined as described first original image by described.
Method the most according to claim 1, it is characterised in that described acquisition is by former first
Beginning picture carries out the step of region picture corresponding to selection area that regional choice obtains, including:
Receive the regional choice instruction carrying out triggering during regional choice in described first original image;
Resolve the instruction of described regional choice, obtain the selection area of described regional choice instruction instruction;
Intercept from described first original image and belong to the part picture of described selection area as described choosing
Determine the region picture that region is corresponding.
Method the most according to claim 1, it is characterised in that described store from mobile terminal
Pictures in search the step of the second original image matched with described region picture, including:
Described region picture is carried out feature extraction, obtains the fisrt feature information of described region picture;
Obtain the second feature information of each picture in described pictures respectively;
According to described fisrt feature information and described second feature information, search and institute from described pictures
State the second original image that region picture matches.
Method the most according to claim 5, it is characterised in that described according to described fisrt feature
Information and described second feature information, search from described pictures and described region picture matches the
The step of two original images, including:
For each picture in described pictures, calculate described fisrt feature information and described picture respectively
Second feature information between matching degree;
Second that matching degree exceedes the picture of predetermined threshold value is defined as matching with described region picture is former
Beginning picture.
Method the most according to claim 5, it is characterised in that described described region picture is entered
Row feature extraction, obtains the step of the fisrt feature information of described region picture, including at least one of:
Described region picture is carried out texture feature extraction, obtains the first textural characteristics of described region picture
Information;
Described region picture is carried out color feature extracted, obtains the first color characteristic of described region picture
Information;
Described region picture is carried out Shape Feature Extraction, obtains the first shape facility of described region picture
Information.
Method the most according to claim 1, it is characterised in that described former by find second
Beginning picture classifies as the step of same classification and includes:
The second original image for finding adds the labelling set;
The second original image being added with the labelling of described setting is classified as same classification.
Method the most according to claim 1, it is characterised in that described region picture includes multiple,
Described search from the pictures that mobile terminal has stored and that described region picture matches is second original
The step of picture, including:
Second matched with whole described region pictures is searched former from the described pictures stored
Beginning picture.
10. the picture classifier of a mobile terminal, it is characterised in that including:
Acquisition module, for obtaining by carrying out the selected district that regional choice obtains in the first original image
The region picture that territory is corresponding;
Search module, for searching from the pictures that mobile terminal has stored and described region picture phase
The second original image joined;
Sort module, for classifying as same classification by the second original image found.
11. devices according to claim 10, it is characterised in that also include:
Acquisition module, for obtaining by carrying out region choosing in the first original image at described acquisition module
Before selecting the region picture that the selection area obtained is corresponding, use the camera collection figure of described mobile terminal
Sheet, is defined as described first original image by the picture of collection.
12. devices according to claim 10, it is characterised in that also include:
Receiver module, for obtaining by carrying out region choosing in the first original image at described acquisition module
Before selecting the region picture that the selection area obtained is corresponding, receive in described pictures, carry out picture selection
Time trigger picture select instruction;
Parsing module, is used for resolving described picture and selects instruction, obtains described picture and selects instruction instruction
Choose picture;
Determine module, for choosing picture to be defined as described first original image by described.
13. devices according to claim 10, it is characterised in that described acquisition module includes:
Command reception submodule, carries out triggering during regional choice for receiving in described first original image
Regional choice instruction;
Instruction analyzing sub-module, is used for resolving the instruction of described regional choice, obtains the instruction of described regional choice
The selection area of instruction;
Picture intercepts submodule, belongs to described selection area for intercepting from described first original image
Part picture is as region picture corresponding to described selection area.
14. devices according to claim 10, it is characterised in that described lookup module includes:
Feature extraction submodule, for described region picture is carried out feature extraction, obtains described administrative division map
The fisrt feature information of sheet;
Acquisition of information submodule, for obtaining the second feature letter of each picture in described pictures respectively
Breath;
Picture searching submodule, for according to described fisrt feature information and described second feature information, from
Described pictures are searched the second original image matched with described region picture.
15. devices according to claim 14, it is characterised in that described picture searching submodule,
Specifically for for each picture in described pictures, calculate described fisrt feature information respectively with described
Matching degree between the second feature information of picture;Matching degree is exceeded the picture of predetermined threshold value be defined as with
The second original image that described region picture matches.
16. devices according to claim 14, it is characterised in that described feature extraction submodule,
Specifically at least one of: described region picture is carried out texture feature extraction, obtains described region
First texture feature information of picture;Described region picture is carried out color feature extracted, obtains described district
First color characteristic information of territory picture;Described region picture is carried out Shape Feature Extraction, obtains described
First shape facility information of region picture.
17. devices according to claim 10, it is characterised in that described sort module includes:
Picture indicia submodule, adds, for the second original image for finding, the labelling set;
Submodule sorted out by picture, for being classified as by the second original image of the labelling being added with described setting
Same classification.
18. devices according to claim 10, it is characterised in that described region picture includes many
, described lookup module, specifically for searching and whole described region picture phases from described pictures
Second original image of coupling.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510280259.0A CN105843827A (en) | 2015-05-27 | 2015-05-27 | Picture classification method and device for mobile terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510280259.0A CN105843827A (en) | 2015-05-27 | 2015-05-27 | Picture classification method and device for mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105843827A true CN105843827A (en) | 2016-08-10 |
Family
ID=56580290
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510280259.0A Pending CN105843827A (en) | 2015-05-27 | 2015-05-27 | Picture classification method and device for mobile terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105843827A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106708994A (en) * | 2016-12-16 | 2017-05-24 | 维沃移动通信有限公司 | Picture selection method and mobile terminal |
CN106791383A (en) * | 2016-12-08 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of image processing method and device, mobile communication terminal |
CN107506362A (en) * | 2016-11-23 | 2017-12-22 | 上海大学 | Image classification based on customer group optimization imitates brain storage method |
CN108710916A (en) * | 2018-05-22 | 2018-10-26 | 重庆完美空间科技有限公司 | The method and device of picture classification |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101706793A (en) * | 2009-11-16 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for searching picture |
CN101916279A (en) * | 2010-08-16 | 2010-12-15 | 刘文萍 | Plant species inquiring system and method based on image analysis technology |
CN102609723A (en) * | 2012-02-08 | 2012-07-25 | 清华大学 | Image classification based method and device for automatically segmenting videos |
CN102637255A (en) * | 2011-02-12 | 2012-08-15 | 北京千橡网景科技发展有限公司 | Method and device for processing faces contained in images |
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 |
CN104102920A (en) * | 2014-07-15 | 2014-10-15 | 中国科学院合肥物质科学研究院 | Pest image classification method and pest image classification system based on morphological multi-feature fusion |
-
2015
- 2015-05-27 CN CN201510280259.0A patent/CN105843827A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101706793A (en) * | 2009-11-16 | 2010-05-12 | 中兴通讯股份有限公司 | Method and device for searching picture |
CN101916279A (en) * | 2010-08-16 | 2010-12-15 | 刘文萍 | Plant species inquiring system and method based on image analysis technology |
CN102637255A (en) * | 2011-02-12 | 2012-08-15 | 北京千橡网景科技发展有限公司 | Method and device for processing faces contained in images |
CN102609723A (en) * | 2012-02-08 | 2012-07-25 | 清华大学 | Image classification based method and device for automatically segmenting videos |
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 |
CN104102920A (en) * | 2014-07-15 | 2014-10-15 | 中国科学院合肥物质科学研究院 | Pest image classification method and pest image classification system based on morphological multi-feature fusion |
Non-Patent Citations (3)
Title |
---|
刘涛: "基于内容的图像检索技术研究与实现", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》 * |
李玉山: "《数字视觉视频技术》", 31 January 2006, 西安电子科技大学出版社 * |
郭宝龙 等: "《数字图像处理***工程导论》", 31 July 2012, 西安电子科技大学出版社 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107506362A (en) * | 2016-11-23 | 2017-12-22 | 上海大学 | Image classification based on customer group optimization imitates brain storage method |
CN107506362B (en) * | 2016-11-23 | 2021-02-23 | 上海大学 | Image classification brain-imitation storage method based on user group optimization |
CN106791383A (en) * | 2016-12-08 | 2017-05-31 | 北京奇虎科技有限公司 | A kind of image processing method and device, mobile communication terminal |
CN106708994A (en) * | 2016-12-16 | 2017-05-24 | 维沃移动通信有限公司 | Picture selection method and mobile terminal |
CN108710916A (en) * | 2018-05-22 | 2018-10-26 | 重庆完美空间科技有限公司 | The method and device of picture classification |
CN108710916B (en) * | 2018-05-22 | 2020-10-09 | 重庆完美空间科技有限公司 | Picture classification method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10831819B2 (en) | Hue-based color naming for an image | |
WO2017129018A1 (en) | Picture processing method and apparatus, and smart terminal | |
US8891902B2 (en) | Band weighted colour histograms for image retrieval | |
US9633448B1 (en) | Hue-based color naming for an image | |
US9076076B1 (en) | Image similarity determination | |
CN106156347A (en) | Cloud photograph album classification methods of exhibiting, device and server | |
US20150154232A1 (en) | System and method for associating images with semantic entities | |
CN108694223A (en) | The construction method and device in a kind of user's portrait library | |
CN105426497A (en) | Automatic classification method and system for photo album in intelligent terminal | |
CN104331509A (en) | Picture managing method and device | |
CN110163076A (en) | A kind of image processing method and relevant apparatus | |
CN105843827A (en) | Picture classification method and device for mobile terminal | |
CN103366186A (en) | Method and apparatus for dynamically changing terminal background | |
CN105824862A (en) | Image classification method based on electronic equipment and electronic equipment | |
US20150019532A1 (en) | Image searching scheme | |
CN105894016A (en) | Image processing method and electronic device | |
CN109426785A (en) | A kind of human body target personal identification method and device | |
CN105512255A (en) | Picture screening method and device and mobile terminal | |
CN103995864B (en) | A kind of image search method and device | |
CN106469162A (en) | A kind of picture sort method and corresponding picture storage display device | |
CN107977948A (en) | A kind of notable figure fusion method towards sociogram's picture | |
JP2014092955A (en) | Similar content search processing device, similar content search processing method and program | |
CN103020120A (en) | Hypergraph-based mixed image summary generating method | |
KR20170010826A (en) | Picture processing method and electronic device | |
CN103678458A (en) | Method and system used for image analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160810 |
|
RJ01 | Rejection of invention patent application after publication |