CN105824862A - Image classification method based on electronic equipment and electronic equipment - Google Patents
Image classification method based on electronic equipment and electronic equipment Download PDFInfo
- Publication number
- CN105824862A CN105824862A CN201510685377.XA CN201510685377A CN105824862A CN 105824862 A CN105824862 A CN 105824862A CN 201510685377 A CN201510685377 A CN 201510685377A CN 105824862 A CN105824862 A CN 105824862A
- Authority
- CN
- China
- Prior art keywords
- file
- picture
- attribute information
- sorted
- characteristic attribute
- 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
- G06F16/10—File systems; File servers
- G06F16/16—File or folder operations, e.g. details of user interfaces specifically adapted to file systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/13—File access structures, e.g. distributed indices
-
- 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
Abstract
The invention provides an image classification method based on electronic equipment and the electronic equipment. The method comprises the following steps: acquiring a folder obtained by performing prior classification on images in the electronic equipment; acquiring characteristic attribute information which corresponds to the folder, wherein the characteristic attribute information at least comprises one of the following attributes: character feature attributes and image content attributes; acquiring characteristic attribute information of to-be-classified images when the to-be-classified images are detected; acquiring a folder matched with the to-be-classified images according to the characteristic attribute information of the to-be-classified images; saving the to-be-classified images in the matched folder. According to the method disclosed by the invention, the folder can be analyzed from multiple dimensions, so that the automatic image classification process is completed, the intelligent degree is high, the image classification processing efficiency of the electronic equipment and the classification accuracy are improved, workload of sorting the images by a user is alleviated, and the automatic classifying and sorting effect is matched with the expected goal of the user.
Description
Technical field
The present invention relates to technical field of electronic equipment, particularly relate to a kind of picture classification method based on electronic equipment and a kind of electronic equipment carrying out picture classification.
Background technology
Along with the development of electronic technology, the electronic equipment with camera function is more and more universal, and the picture that user stores in the electronic device gets more and more, and this proposes requirements at the higher level to pictures management.
The means that pictures management is conventional are picture classifications, and in the prior art, picture classification often has a following two ways:
One is Manual arranging classification, i.e. user oneself is manually referred to different files picture, reaches the purpose arranged.Manual arranging classification is a loaded down with trivial details process for user, and along with getting more and more of picture, the workload of arrangement can be increasing.
Two is classification automatically, and automatic mode classification has multiple, as being sorted by time, by place classification, by human classification, is sorted out by picture from some dimension, it is simple to check or search.But these mode classifications are all some classification being easy to browse and non-real by photo finishing to different files, it is not reaching to the purpose that user wants to arrange.Further, these automatic mode classification excessively mechanizations, can only classify by wherein certain single dimension, therefore, this automatic mode classification does not reaches the effect that user wants often.
Summary of the invention
In order to overcome the above-mentioned problems in the prior art, embodiments provide a kind of a kind of based on electronic equipment picture classification method overcoming the problems referred to above and a kind of electronic equipment carrying out picture classification, solve mode classification excessively mechanization present in existing picture classification, problem that classification dimension classification results single, automatic does not reaches the effect that user wants.
In order to solve the problems referred to above, the invention discloses a kind of picture classification method based on electronic equipment, described method includes:
Obtain the file obtained of in electronic equipment, picture formerly being classified；
Obtain described file characteristic of correspondence attribute information；Described characteristic attribute information at least includes such as properties one: character features attribute, image content attribute；
When picture to be sorted being detected, obtain the characteristic attribute information of described picture to be sorted；
According to the characteristic attribute information of described picture to be sorted, obtain the file with described picture match to be sorted；
Described picture to be sorted is saved in the file of described coupling.
The invention also discloses a kind of electronic equipment carrying out picture classification, described electronic equipment includes:
File acquisition module, for obtaining the file obtained of formerly classifying picture in electronic equipment；
Folder attribute acquisition module, is used for obtaining described file characteristic of correspondence attribute information；Described characteristic attribute information at least includes such as properties one: character features attribute, image content attribute；
Picture attribute acquisition module, for when picture to be sorted being detected, obtains the characteristic attribute information of described picture to be sorted；
Matching files folder acquisition module, for the characteristic attribute information according to described picture to be sorted, obtains the file with described picture match to be sorted；
Picture preserves module, for being saved in the file of described coupling by described picture to be sorted.
Compared with prior art, the present invention includes advantages below:
In embodiments of the present invention, analysis according to the file obtained that the picture in electronic equipment is formerly classified, obtain this document folder correspondence comprises character features attribute, the characteristic attribute information such as image content attribute, when picture to be sorted being detected, obtain the file with this picture match to be sorted, and the picture that this is to be sorted is automatically saved in the file of coupling, the analysis of file is carried out from various dimensions, thus complete the automatic categorizing process of picture, intelligence degree is high, improve the picture classification treatment effeciency of electronic equipment and improve classification degree of accuracy, significantly reduce user and arrange the workload of picture, also the expection purpose of the automatic more identical user of taxonomic revision effect is allowed.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of a kind of based on electronic equipment the picture classification method embodiment one of the present invention；
Fig. 2 is the flow chart of steps of a kind of based on electronic equipment the picture classification method embodiment two of the present invention；
Fig. 3 is the triggering interface schematic diagram in a kind of based on electronic equipment the picture classification method embodiment two of the present invention；
A kind of structured flowchart of the electronic equipment embodiment carrying out picture classification of Fig. 4 present invention.
Detailed description of the invention
Understandable 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 below in conjunction with the accompanying drawings.
With reference to Fig. 1, it is shown that the flow chart of steps of a kind of based on electronic equipment the picture classification method embodiment one of the present invention, specifically may include steps of.
Step 101, obtains the file obtained of formerly classifying picture in electronic equipment.
In implementing, user can carry out Manual arranging classification to the picture (can be whole pictures or the part picture of storage in electronic equipment) in electronic equipment in advance, obtaining one or more file, each file can include one or more picture.
Step 102, obtains described file characteristic of correspondence attribute information.
For the file obtained after user's manual classification, its every pictures comprised can be analyzed by the embodiment of the present invention, and carry out collecting and sorting out by the analysis result of all pictures, obtain the classifying rules of file, i.e. file characteristic of correspondence attribute information.
As a kind of preferred exemplary of the embodiment of the present invention, characteristic attribute information at least can include such as properties one: character features attribute, image content attribute.
Wherein, character features attribute can be to be analyzed the character features in picture by face recognition technology, quantity of the mark of personage, personage etc. in the character features comprised in the picture obtained, such as picture.
Image content attribute can be the pattern features that picture is patterned analyzing the picture obtained, and such as, the picture of shooting blackboard notes, image content is that there is white fragmentary content black block, centre on a large scale；And for example, landscape figure, picture color is bright-coloured, upper half is truncated into blueness, etc..
It should be noted that, character features attribute belongs to two kinds of different analysis dimensions with image content attribute, character features attribute is mainly main being analyzed with the character features in picture, image content attribute is to be patterned into main being analyzed, in order to avoid repeating with above-mentioned character features attribute, composition analysis herein can be the analysis of other constructing elements not comprising character features.
File characteristic of correspondence attribute information in the embodiment of the present invention can have multiple, can enrich the dimension of classifying rules, improves nicety of grading.
Step 103, when picture to be sorted being detected, obtains the characteristic attribute information of described picture to be sorted.
After user triggers automating sorting function in the electronic device, if electronic equipment detects picture to be sorted, for the picture that this is to be sorted, can obtain the characteristic attribute information of this picture to be sorted, the characteristic attribute information of this picture to be sorted can also include character features attribute, image content attribute etc..
In implementing, picture to be sorted can be the picture that electronic equipment newly absorbs, it is also possible to absorbed for electronic equipment but without the picture of user's manual classification.
Step 104, according to the characteristic attribute information of described picture to be sorted, obtains the file with described picture match to be sorted.
When the characteristic attribute information obtaining picture to be sorted, and, after the characteristic attribute information of file, the characteristic attribute information of this picture to be sorted can be mated with the characteristic attribute information of file, if the match is successful, illustrate that the characteristic attribute information of this picture to be sorted matches with the classifying rules being somebody's turn to do the file that the match is successful.
Step 105, is saved in described picture to be sorted in the file of described coupling.
After the file determining the picture match to be sorted with this, the picture that this is to be sorted can be saved in the file of this coupling by the embodiment of the present invention automatically, to complete the automatic classification of this picture to be sorted.
In embodiments of the present invention, analysis according to the file obtained that the picture in electronic equipment is formerly classified, obtain this document folder correspondence comprises character features attribute, the characteristic attribute information such as image content attribute, when picture to be sorted being detected, obtain the file with this picture match to be sorted, and the picture that this is to be sorted is automatically saved in the file of coupling, the analysis of file is carried out from various dimensions, thus complete the automatic categorizing process of picture, intelligence degree is high, improve the picture classification treatment effeciency of electronic equipment and improve classification degree of accuracy, significantly reduce user and arrange the workload of picture, also the expection purpose of the automatic more identical user of taxonomic revision effect is allowed.
With reference to Fig. 2, it is shown that the flow chart of steps of a kind of based on electronic equipment the picture classification method embodiment two of the present invention, specifically may include steps of.
Step 201, obtains the file obtained of formerly classifying picture in electronic equipment.
In one embodiment, the file obtained formerly classified picture in electronic equipment can be, user manually to part picture present in electronic equipment or all picture carry out taxonomic revision, the file obtained, this document folder can store one or more picture.
In implementing, this file obtained of formerly classifying can be the file of the picture belonging to a classifying rules for storage.
Step 202, obtains described file characteristic of correspondence attribute information.
The file that user's manual classification can be obtained by the embodiment of the present invention is analyzed, and obtains user and sorts out the classifying rules of every class picture, and this classifying rules is the characteristic attribute information of this document folder.
In a kind of preferred embodiment of the embodiment of the present invention, step 202 can include farther including: obtains one or more characteristic attribute information of every pictures in described file；The characteristic attribute information of pictures every in described file is collected according to same category, obtains the characteristic attribute information of described file.
Specifically, in embodiments of the present invention, the characteristic attribute information of every pictures in the file obtained of formerly classifying at least can include one or more of following characteristic attribute information: character features attribute, image content attribute, time attribute, position attribution.Certainly, the embodiment of the present invention is not limited to above-mentioned four attribute information, and those skilled in the art obtain other characteristic attribute information of picture and are all possible.
In implementing, electronic equipment, when absorbing picture, can be that every pictures adds the information such as time attribute and position attribution, and therefore, the time attribute of every pictures and position attribution can obtain from the attribute information that picture carries.
For character features attribute, in one embodiment, can obtain by the way of recognition of face, the character features attribute obtained after recognition of face can include the information such as the quantity of the mark of personage, personage.
For image content attribute, in one embodiment, can obtain by being patterned picture analyzing, by picture being patterned analysis, obtain the pattern features of picture, such as, the picture of shooting blackboard notes, image content is that there is white fragmentary content black block, centre on a large scale；And for example, landscape figure, the composition of picture is bright in luster, upper half is truncated into blueness, etc..
In another embodiment, image content attribute can also be obtained by tonal analysis, it realizes process: the color space of picture is divided into sufficiently small color block, and manually mark the color of each color block, then the color block belonging to pixel each to picture searching, and by the way of statistics, obtain the tone composition of a pictures.
It should be noted that, character features attribute belongs to two kinds of different analysis dimensions with image content attribute, character features attribute is mainly main being analyzed with the character features in picture, image content attribute is to be patterned into main being analyzed, in order to avoid repeating with above-mentioned character features attribute, composition analysis herein can be the analysis of other constructing elements not comprising character features.
Certainly, the above-mentioned acquisition mode about character features attribute and image content attribute is only the example of the present embodiment, those skilled in the art adopt and analyze the character features attribute of picture in other ways and image content attribute is all possible, the embodiment of the present invention to this without being any limitation as.
In practice, after one or more characteristic attribute information obtaining every pictures, the characteristic attribute information of this picture can be saved in storage medium with picture identification for index.Such as, in storage medium, can be as follows with example with the various features attribute information that picture identification is this picture of index preservation.
Place (P): xx saves, xx city, xx district, xx street.
Time (T): 2015-8-411:20:50.
Personage (F): face numbering 13.
Content (C): mass-tone is adjusted to black, colour #000000；Surrounding is white tone.
Being applied to the embodiment of the present invention, obtain in file after one or more characteristic attribute information of every pictures, in can being pressed from both sides by this document, the characteristic attribute information of all pictures carries out Macro or mass analysis according to same category, obtains the characteristic attribute information of this document folder.
Such as, in acquisition file after the character features attribute of all pictures, being collected according to character features attribute by all pictures in file, the character features attribute obtaining this document folder can be: all comprises and only comprises A；Or, all comprise A, X pictures also comprise in B, Y pictures simultaneously and comprise C；Or, X pictures comprises A, Y pictures comprises in B, Z pictures and comprise C, etc..
And for example, in acquisition file after the position attribution of all pictures, being collected according to position attribution by all pictures in file, the position attribution obtaining this document folder can be: is all place A1；Or, for place A1/B1/C1, wherein A1/B1/C1 belongs to certain region XX；Or, X open place be A1, Y pictures place be B1, Z pictures place be C1, etc..
After file is collected according to the characteristic attribute information of each classification, the summarized results of the characteristic attribute information of tissue all categories, obtain the characteristic attribute information of file, such as, the characteristic attribute information of file " Bigfamily " can be: picture under a of place and the picture (position attribution information and character features attribute information being collected) comprising personage A/B/C/D/E/F.
The embodiment of the present invention breaks through single classification dimension, the classifying rules (i.e. characteristic attribute information) of each file is comprehensively analyzed so that the classification to picture is more accurate from multiple dimensions (time attribute, position attribution, character features attribute, image content attribute).
Step 203, when picture to be sorted being detected, obtains the characteristic attribute information of described picture to be sorted.
After analyzing the classification rule of each file, when the picture to be sorted in current electronic device being detected, the characteristic attribute information of this picture to be sorted can be obtained.As a kind of example, the characteristic attribute information of this picture to be sorted can also include time attribute, position attribution, character features attribute, image content attribute etc. accordingly.
In implementing, picture to be sorted can be the picture that electronic equipment newly absorbs, or, absorb but for not carrying out the picture of any classification (such as user's manual classification).
Step 204, according to the characteristic attribute information of described picture to be sorted, obtains the file with described picture match to be sorted.
After the characteristic attribute information obtaining picture to be sorted, the characteristic attribute information of this feature attribute information with all files formerly classified and obtain can be mated, if the match is successful, then using this file that the match is successful as the file with this picture match to be sorted.
In a kind of preferred embodiment of the embodiment of the present invention, step 204 may include that formerly classifies in the file obtained to picture described, searches whether to there is the file mated with the characteristic attribute information of described picture to be sorted；If existing, then the file characteristic attribute information of described and described picture to be sorted mated, as the file with described picture match to be sorted；If not existing, then create the new folder mated with the characteristic attribute information of described picture to be sorted, using described new folder as the file with described picture match to be sorted.
Specifically, after the characteristic attribute information obtaining picture to be sorted, picture formerly can be classified in the file obtained above-mentioned, search the file mated with the characteristic attribute information of this picture to be sorted.In one embodiment, above-mentioned search procedure can be: calculates the first similarity of the characteristic attribute information of picture to be sorted and the characteristic attribute information of the above-mentioned file obtained of formerly classifying picture；Search whether the file that there is the first similarity more than or equal to predetermined threshold value.The file of predetermined threshold value it is more than or equal to if there is the first similarity, illustrate the file formerly classified exists the file mated with the characteristic attribute information of this picture to be sorted, then this first similarity can be more than or equal to the file of predetermined threshold value as the file with this picture match to be sorted.
The file of predetermined threshold value it is more than or equal to if there is no the first similarity, then illustrate the file formerly classified does not exists the file that the characteristic attribute information of the picture to be sorted with this is mated, now, the new folder that the characteristic attribute information of the picture to be sorted with this is mated can be created, using this new folder as the file with described picture match to be sorted, wherein, new folder can be named with the characteristic attribute information of this picture to be sorted.
In implementing, there is likely to be the first similarity more than or equal to the file of predetermined threshold value is two or more situation, for this situation, what the embodiment of the present invention was exemplary provides the following two kinds solution, certainly, the embodiment of the present invention is not limited to this, and those skilled in the art use other solutions to reach same purpose and are all possible.
Solution one: if there is two or more first similarities file more than or equal to predetermined threshold value, by file corresponding for the characteristic attribute information of the first similarity maximum, as the file with described picture match to be sorted.
Concrete, when the file with picture match to be sorted is two or more, and first similarity of file of this two or more coupling also differs, now can be by file corresponding for the characteristic attribute information of the first similarity maximum, as the file with this picture match to be sorted.
Such as, the characteristic attribute information of file " Bigfamily " including: picture under a of place and comprise the picture of personage A/B/C/D/E/F；The characteristic attribute information of file " Me " including: the picture of personage A.If only photograph that picture to be sorted is personage A, this picture to be sorted is 0.6 with the first similarity of file " Bigfamily ", it is 0.9 with the first similarity of file " Me ", all exceed predetermined threshold value 0.5, now, can be by file maximum for the first similarity, i.e. file " Me " is as the file with picture match to be sorted.
For the situation that the first similarity of the file of these two or more couplings is identical, solution two can be taked.
Solution two: if there is two or more first similarities file more than or equal to predetermined threshold value, obtain said two or the plural first similarity adjustment characteristic attribute information more than or equal to the file of predetermined threshold value the most respectively, and calculate the characteristic attribute information of described picture to be sorted and the second similarity of described adjustment characteristic attribute information respectively, by file corresponding for the adjustment characteristic attribute information that the second similarity is maximum, as the file with described picture match to be sorted.
Wherein, described adjustment characteristic attribute information can be after the characteristic attribute information of the difference obtained between two or more first similarities file more than or equal to predetermined threshold value, adds the information that the characteristic attribute information of described difference generates in the characteristic attribute information of described file.
Specifically, when the file with picture match to be sorted accompanies two, then can compare the characteristic attribute information of the picture that these two files are comprised, obtain the characteristic attribute information of difference between these two files, on the basis of these two original characteristic attribute information of file, add the characteristic attribute information of this difference, the adjustment characteristic attribute information of these two files can be obtained.Now, can calculate further the characteristic attribute information of picture to be sorted respectively with the second similarity of the adjustment characteristic attribute information of above-mentioned two file, and using file corresponding for adjustment characteristic attribute information that the second similarity is maximum as the file with described picture match to be sorted.
Such as, the characteristic attribute information in file " Bigfamily " includes: picture under a of place and the picture comprising personage A/B/C/D/E/F；The characteristic attribute information of file " Me " includes the picture of personage A.If only photograph that picture to be sorted is A, this picture to be sorted is all higher than predetermined threshold value with the first similarity of above-mentioned file " Bigfamily " and file " Me ", now, can the characteristic attribute information of difference between Study document folder " Bigfamily " and file " Me " further, the characteristic attribute information of the difference obtained be file " Bigfamily " be the group photo comprising A, file " Me " is for comprising only photograph of A, can the adjustment characteristic attribute information in more new folder " Bigfamily " be then: picture under a of place and comprise personage A/B/C/D/E/F's, the picture of the group photo of A；The adjustment characteristic attribute information of more new folder " Me " is: the picture of only photograph of personage A.After obtaining the adjustment characteristic attribute information of two files, can calculate further the characteristic attribute information of picture to be sorted respectively with the second similarity of the adjustment characteristic attribute information of above-mentioned two file: be 0.5 with the second similarity of file " Bigfamily ", be 0.95 with the second similarity of file " Me ".At this point it is possible to using file (file " Me ") maximum for the second similarity as the file with described picture match to be sorted.
And for example, the characteristic attribute information that file " works " includes: the picture under the x of place；The characteristic attribute information of file " daily life " including: place is the picture under x/y.Both comprise the picture that place is x.Now, can Study document folder " work " and the characteristic attribute information of picture of file " daily life " further, obtain the characteristic attribute information of the difference between two files: the picture in " work " file, have in 3 pictures and comprise a same background block a1 (such as little blank), 4 pictures additionally comprise same background block b1；And the picture in " daily life " does not comprise a1 or b1.The adjustment characteristic attribute information that then characteristic attribute information to two files obtains after being adjusted is: file " work " be place be the picture comprising a1 or b1 in x and image content；File " daily life " be place be the picture of x/y, simultaneously place be x image content in do not comprise a1 or b1.
Accompanying plural situation for the file of picture match to be sorted, the file being referred to picture match above-mentioned Yu to be sorted accompanies the mode of two, compares two-by-two, obtains the file of final coupling.
It should be noted that the embodiment of the present invention to the calculation of the first similarity and the second similarity without being any limitation as, it is for instance possible to use the modes such as general cosine similarity, similar calculating based on hash method, Similarity Measure based on theme calculate.
Step 205, is saved in described picture to be sorted in the file of described coupling.
After obtaining the file of coupling corresponding to picture to be sorted, the picture that this is to be sorted can be saved in the file of this coupling, to complete the automatic clustering of this picture to be sorted.
Step 206, when detecting that user moves operation to the picture of the described file formerly classified and obtain, according to moving the picture after operation in described file, updates described file characteristic of correspondence attribute information.
Being applied to the embodiment of the present invention, user manually can move operation to the picture of the file obtained of formerly classifying, such as, and the picture removing or increasing in file.If user detected to the mobile operation of the picture of file, the characteristic attribute information of this document folder can be reacquired, to update this document folder characteristic of correspondence attribute information according to file moves the picture after operation.
It should be noted that, the process that picture is classified by the embodiment of the present invention automatically, by user, one key operation of electronic equipment can be triggered, as shown in the triggering interface schematic diagram of Fig. 3, picture at electronic equipment stores in position, when user clicks on a key sort on interface, then trigger the automatic categorizing process of the embodiment of the present invention, make the classification to picture more intelligent, significantly reduce user and arrange the workload of picture, the treatment effeciency of electronic equipment is higher, and user need not be vexatious in arranging picture, improves Consumer's Experience.
nullIn embodiments of the present invention，Analysis according to the file obtained that the picture in electronic equipment is formerly classified，Obtain this document folder correspondence comprises character features attribute、The characteristic attribute information such as image content attribute，When picture to be sorted being detected，Obtain the file with this picture match to be sorted，And the picture that this is to be sorted is automatically saved in the file of coupling，The analysis of file is carried out from various dimensions，Thus complete the automatic categorizing process of picture，Intelligence degree is high，And，When detecting that user moves operation to the picture of the described file formerly classified and obtain，According to file moves the picture after operation，More new folder characteristic of correspondence attribute information，The embodiment of the present invention is for the classifying rules (i.e. characteristic attribute information) of each file，With user, the mobile operation of picture in file can be constantly updated，Make the classification to picture more accurate，The classification the most more agreeing with user sets.
Based on same inventive concept, with reference to Fig. 4, it is shown that the structured flowchart of a kind of electronic equipment embodiment carrying out picture classification of the present invention, can include such as lower module.
File acquisition module 401, for obtaining the file obtained of formerly classifying picture in electronic equipment.
Folder attribute acquisition module 402, is used for obtaining described file characteristic of correspondence attribute information；Described characteristic attribute information at least includes such as properties one: character features attribute, image content attribute.
Picture attribute acquisition module 403, for when picture to be sorted being detected, obtains the characteristic attribute information of described picture to be sorted.
Matching files folder acquisition module 404, for the characteristic attribute information according to described picture to be sorted, obtains the file with described picture match to be sorted.
Picture preserves module 405, for being saved in the file of described coupling by described picture to be sorted.
In a kind of preferred embodiment of the embodiment of the present invention, described matching files folder acquisition module 404 includes:
Search submodule, for picture formerly being classified in the file obtained described, search whether to there is the file mated with the characteristic attribute information of described picture to be sorted.
Matching files folder obtains submodule, for when there is the file mated with the characteristic attribute information of described picture to be sorted, the file characteristic attribute information of described and described picture to be sorted mated, as the file with described picture match to be sorted.
File creates submodule, when the file mated in the characteristic attribute information not existed with described picture to be sorted, create the new folder mated with the characteristic attribute information of described picture to be sorted, using described new folder as the file with described picture match to be sorted, wherein, described new folder is named with the characteristic attribute information of described picture to be sorted.
In a kind of preferred embodiment of the embodiment of the present invention, described lookup submodule includes:
First similarity calculated, is used for the first similarity of the characteristic attribute information calculating described picture to be sorted and the characteristic attribute information of the described file obtained of formerly classifying picture.
Search unit, for searching whether the file that there is the first similarity more than or equal to predetermined threshold value.
In a kind of preferred embodiment of the embodiment of the present invention, described matching files folder obtains submodule and includes:
, for when there is the file that two or more first similarities are more than or equal to predetermined threshold value, by file corresponding for the characteristic attribute information of the first similarity maximum, as the file with described picture match to be sorted in the first matching unit.
Or,
Second matching unit, for when there is the file that two or more first similarities are more than or equal to predetermined threshold value, obtain said two or the plural first similarity adjustment characteristic attribute information more than or equal to the file of predetermined threshold value respectively, and calculate the characteristic attribute information of described picture to be sorted and the second similarity of described adjustment characteristic attribute information respectively, by file corresponding for the adjustment characteristic attribute information that the second similarity is maximum, as the file with described picture match to be sorted.
Wherein, described adjustment characteristic attribute information is after the characteristic attribute information of the difference obtained between said two or the plural first similarity file more than or equal to predetermined threshold value, adds the information that the characteristic attribute information of described difference generates in the characteristic attribute information of described file.
In a kind of preferred embodiment of the embodiment of the present invention, the described file obtained of formerly classifying picture includes plurality of pictures.
Described folder attribute acquisition module 402 includes:
Picture attribute obtains submodule, for obtaining one or more characteristic attribute information of every pictures in described file.
Collect submodule, for the characteristic attribute information of pictures every in described file is collected according to same category, obtain the characteristic attribute information of described file.
In a kind of preferred embodiment of the embodiment of the present invention, described electronic equipment also includes:
More new module, for when detecting that user moves operation to the picture of the described file formerly classified and obtain, according to moving the picture after operation in described file, updates described file characteristic of correspondence attribute information.
In a kind of preferred embodiment of the embodiment of the present invention, described file characteristic of correspondence attribute information also includes: time attribute and/or position attribution.
Each embodiment in this specification all uses the mode gone forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, and between each embodiment, identical similar part sees mutually.
Those skilled in the art are it should be appreciated that the embodiment of the embodiment of the present invention can be provided as method, device or computer program.Therefore, the form of the embodiment in terms of the embodiment of the present invention can use complete hardware embodiment, complete software implementation or combine software and hardware.And, the embodiment of the present invention can use the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory, CD-ROM, optical memory etc.) wherein including computer usable program code.
The embodiment of the present invention is to describe with reference to method, terminal unit (system) and the flow chart of computer program according to embodiments of the present invention and/or block diagram.It should be understood that can be by the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing terminal equipment so that the instruction performed by the processor of computer or other programmable data processing terminal equipment is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing terminal equipment work in a specific way, the instruction making to be stored in this computer-readable memory produces the manufacture including command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded on computer or other programmable data processing terminal equipment, make to perform sequence of operations step on computer or other programmable terminal equipment to produce computer implemented process, thus the instruction performed on computer or other programmable terminal equipment provides the step of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame for realization.
Although having been described for the preferred embodiment of the embodiment of the present invention, but those skilled in the art once know basic creative concept, then these embodiments can be made other change and amendment.So, claims are intended to be construed to include preferred embodiment and fall into all changes and the amendment of range of embodiment of the invention.
Finally, it can further be stated that, in this article, the relational terms of such as first and second or the like is used merely to separate an entity or operation with another entity or operating space, and not necessarily requires or imply the relation or sequentially that there is any this reality between these entities or operation.And, term " includes ", " comprising " or its any other variant are intended to comprising of nonexcludability, so that include that the process of a series of key element, method, article or terminal unit not only include those key elements, but also include other key elements being not expressly set out, or also include the key element intrinsic for this process, method, article or terminal unit.In the case of there is no more restriction, statement " including ... " key element limited, it is not excluded that there is also other identical element in including the process of described key element, method, article or terminal unit.
Above a kind of picture classification method based on electronic equipment provided by the present invention and electronic equipment are described in detail, principle and the embodiment of the present invention are set forth by specific case used herein, and the explanation of above example is only intended to help to understand method and the core concept thereof of the present invention；Simultaneously for one of ordinary skill in the art, according to the thought of the present invention, the most all will change, in sum, this specification content should not be construed as limitation of the present invention.
Claims (14)
1. a picture classification method based on electronic equipment, it is characterised in that described method includes:
Obtain the file obtained of in electronic equipment, picture formerly being classified；
Obtain described file characteristic of correspondence attribute information；Described characteristic attribute information at least includes such as properties one: character features attribute, image content attribute；
When picture to be sorted being detected, obtain the characteristic attribute information of described picture to be sorted；
According to the characteristic attribute information of described picture to be sorted, obtain the file with described picture match to be sorted；
Described picture to be sorted is saved in the file of described coupling.
Method the most according to claim 1, it is characterised in that the described characteristic attribute information according to described picture to be sorted, the step of the file of acquisition and described picture match to be sorted, including:
Described, picture is formerly classified in the file obtained, search whether to there is the file mated with the characteristic attribute information of described picture to be sorted；
If existing, then the file characteristic attribute information of described and described picture to be sorted mated, as the file with described picture match to be sorted；
If not existing, then create the new folder mated with the characteristic attribute information of described picture to be sorted, using described new folder as the file with described picture match to be sorted, wherein, described new folder is named with the characteristic attribute information of described picture to be sorted.
Method the most according to claim 2, it is characterised in that described formerly classify picture in the file obtained described, searches whether that the step that there is the file mated with the characteristic attribute information of described picture to be sorted includes:
Calculate the first similarity of the characteristic attribute information of described picture to be sorted and the characteristic attribute information of the described file obtained that picture is formerly classified；
Search whether the file that there is the first similarity more than or equal to predetermined threshold value.
Method the most according to claim 3, it is characterised in that exist if described, then the file characteristic attribute information of described and described picture to be sorted mated, as the step with the file of described picture match to be sorted, including:
If there is two or more first similarities file more than or equal to predetermined threshold value, then by file corresponding for the characteristic attribute information that the first similarity is maximum, as the file with described picture match to be sorted；
Or,
If there is two or more first similarities file more than or equal to predetermined threshold value, obtain said two or the plural first similarity adjustment characteristic attribute information more than or equal to the file of predetermined threshold value the most respectively, and calculate the characteristic attribute information of described picture to be sorted and the second similarity of described adjustment characteristic attribute information respectively, by file corresponding for the adjustment characteristic attribute information that the second similarity is maximum, as the file with described picture match to be sorted；
Wherein, described adjustment characteristic attribute information is after the characteristic attribute information of the difference obtained between said two or the plural first similarity file more than or equal to predetermined threshold value, adds the information that the characteristic attribute information of described difference generates in the characteristic attribute information of described file.
5. according to the method described in claim 1 or 2 or 3 or 4, it is characterised in that the described file obtained of formerly classifying picture includes plurality of pictures；
The step of described acquisition described file characteristic of correspondence attribute information includes:
Obtain one or more characteristic attribute information of every pictures in described file；
The characteristic attribute information of pictures every in described file is collected according to same category, obtains the characteristic attribute information of described file.
Method the most according to claim 1, it is characterised in that also include:
When detecting that user moves operation to the picture of the described file formerly classified and obtain, according to described file moves the picture after operation, update described file characteristic of correspondence attribute information.
7. according to the method described in claim 1 or 2 or 3 or 4 or 6, it is characterised in that described file characteristic of correspondence attribute information also includes: time attribute and/or position attribution.
8. the electronic equipment carrying out picture classification, it is characterised in that described electronic equipment includes:
File acquisition module, for obtaining the file obtained of formerly classifying picture in electronic equipment；
Folder attribute acquisition module, is used for obtaining described file characteristic of correspondence attribute information；Described characteristic attribute information at least includes such as properties one: character features attribute, image content attribute；
Picture attribute acquisition module, for when picture to be sorted being detected, obtains the characteristic attribute information of described picture to be sorted；
Matching files folder acquisition module, for the characteristic attribute information according to described picture to be sorted, obtains the file with described picture match to be sorted；
Picture preserves module, for being saved in the file of described coupling by described picture to be sorted.
Electronic equipment the most according to claim 8, it is characterised in that described matching files folder acquisition module includes:
Search submodule, for picture formerly being classified in the file obtained described, search whether to there is the file mated with the characteristic attribute information of described picture to be sorted；
Matching files folder obtains submodule, for when there is the file mated with the characteristic attribute information of described picture to be sorted, the file characteristic attribute information of described and described picture to be sorted mated, as the file with described picture match to be sorted；
File creates submodule, when the file mated in the characteristic attribute information not existed with described picture to be sorted, create the new folder mated with the characteristic attribute information of described picture to be sorted, using described new folder as the file with described picture match to be sorted, wherein, described new folder is named with the characteristic attribute information of described picture to be sorted.
Electronic equipment the most according to claim 9, it is characterised in that described lookup submodule includes:
First similarity calculated, is used for the first similarity of the characteristic attribute information calculating described picture to be sorted and the characteristic attribute information of the described file obtained of formerly classifying picture；
Search unit, for searching whether the file that there is the first similarity more than or equal to predetermined threshold value.
11. electronic equipments according to claim 10, it is characterised in that described matching files folder obtains submodule and includes:
, for when there is the file that two or more first similarities are more than or equal to predetermined threshold value, by file corresponding for the characteristic attribute information of the first similarity maximum, as the file with described picture match to be sorted in the first matching unit；
Or,
Second matching unit, for when there is the file that two or more first similarities are more than or equal to predetermined threshold value, obtain said two or the plural first similarity adjustment characteristic attribute information more than or equal to the file of predetermined threshold value respectively, and calculate the characteristic attribute information of described picture to be sorted and the second similarity of described adjustment characteristic attribute information respectively, by file corresponding for the adjustment characteristic attribute information that the second similarity is maximum, as the file with described picture match to be sorted；
Wherein, described adjustment characteristic attribute information is after the characteristic attribute information of the difference obtained between said two or the plural first similarity file more than or equal to predetermined threshold value, adds the information that the characteristic attribute information of described difference generates in the characteristic attribute information of described file.
Electronic equipment described in 12. according to Claim 8 or 9 or 10 or 11, it is characterised in that the described file obtained of formerly classifying picture includes plurality of pictures；
Described folder attribute acquisition module includes:
Picture attribute obtains submodule, for obtaining one or more characteristic attribute information of every pictures in described file；
Collect submodule, for the characteristic attribute information of pictures every in described file is collected according to same category, obtain the characteristic attribute information of described file.
13. electronic equipments according to claim 8, it is characterised in that also include:
More new module, for when detecting that user moves operation to the picture of the described file formerly classified and obtain, according to moving the picture after operation in described file, updates described file characteristic of correspondence attribute information.
Electronic equipment described in 14. according to Claim 8 or 9 or 10 or 11 or 13, it is characterised in that described file characteristic of correspondence attribute information also includes: time attribute and/or position attribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510685377.XA CN105824862A (en) | 2015-10-20 | 2015-10-20 | Image classification method based on electronic equipment and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510685377.XA CN105824862A (en) | 2015-10-20 | 2015-10-20 | Image classification method based on electronic equipment and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105824862A true CN105824862A (en) | 2016-08-03 |
Family
ID=56513441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510685377.XA Pending CN105824862A (en) | 2015-10-20 | 2015-10-20 | Image classification method based on electronic equipment and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105824862A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106547846A (en) * | 2016-10-17 | 2017-03-29 | 上海传英信息技术有限公司 | A kind of method and device for arranging repetitive picture |
| CN106547893A (en) * | 2016-11-03 | 2017-03-29 | 福建中金在线信息科技有限公司 | A kind of photo sort management system and photo sort management method |
| CN108121816A (en) * | 2017-12-28 | 2018-06-05 | 广东欧珀移动通信有限公司 | Picture classification method, device, storage medium and electronic equipment |
| CN108304563A (en) * | 2018-02-08 | 2018-07-20 | 百度在线网络技术（北京）有限公司 | Image processing method, device and equipment |
| CN108959316A (en) * | 2017-05-24 | 2018-12-07 | 北京搜狗科技发展有限公司 | A kind of method and apparatus adding a webpage to collection |
| CN109426759A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of the visualization archive of article |
| CN109471841A (en) * | 2018-10-31 | 2019-03-15 | 维沃移动通信有限公司 | A kind of file classifying method and device |
| CN109522405A (en) * | 2018-09-29 | 2019-03-26 | 南昌与德软件技术有限公司 | File information processing method, electronic equipment and computer-readable deposit medium |
| CN109634920A (en) * | 2018-11-19 | 2019-04-16 | 北京奇虎科技有限公司 | File consolidation method and device |
| CN112308088A (en) * | 2020-09-16 | 2021-02-02 | 广州忆游科技有限公司 | Method for intelligently screening full-transparent pictures |
| CN112836759A (en) * | 2021-02-09 | 2021-05-25 | 重庆紫光华山智安科技有限公司 | Method and device for evaluating machine-selected picture, storage medium and electronic equipment |
| WO2023138353A1 (en) * | 2022-01-21 | 2023-07-27 | 京东方科技集团股份有限公司 | Picture processing method, electronic device and computer readable medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007207254A (en) * | 2007-02-13 | 2007-08-16 | Seiko Epson Corp | Classification of image file |
| CN102077179A (en) * | 2008-06-30 | 2011-05-25 | 日立系统解决方案有限公司 | File management device |
| CN102917126A (en) * | 2012-10-11 | 2013-02-06 | 中兴通讯股份有限公司 | Method and system for processing photos |
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
| CN103995889A (en) * | 2014-06-03 | 2014-08-20 | 广东欧珀移动通信有限公司 | Method and device for classifying pictures |
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
| CN104915344A (en) * | 2014-03-10 | 2015-09-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
-
2015
- 2015-10-20 CN CN201510685377.XA patent/CN105824862A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007207254A (en) * | 2007-02-13 | 2007-08-16 | Seiko Epson Corp | Classification of image file |
| CN102077179A (en) * | 2008-06-30 | 2011-05-25 | 日立系统解决方案有限公司 | File management device |
| CN103207870A (en) * | 2012-01-17 | 2013-07-17 | 华为技术有限公司 | Method, server, device and system for photo sort management |
| CN102917126A (en) * | 2012-10-11 | 2013-02-06 | 中兴通讯股份有限公司 | Method and system for processing photos |
| CN104915344A (en) * | 2014-03-10 | 2015-09-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN103995889A (en) * | 2014-06-03 | 2014-08-20 | 广东欧珀移动通信有限公司 | Method and device for classifying pictures |
| CN104615769A (en) * | 2015-02-15 | 2015-05-13 | 小米科技有限责任公司 | Image classification method and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106547846A (en) * | 2016-10-17 | 2017-03-29 | 上海传英信息技术有限公司 | A kind of method and device for arranging repetitive picture |
| CN106547893A (en) * | 2016-11-03 | 2017-03-29 | 福建中金在线信息科技有限公司 | A kind of photo sort management system and photo sort management method |
| CN108959316B (en) * | 2017-05-24 | 2021-08-20 | 北京搜狗科技发展有限公司 | Method and device for adding webpage to favorites |
| CN108959316A (en) * | 2017-05-24 | 2018-12-07 | 北京搜狗科技发展有限公司 | A kind of method and apparatus adding a webpage to collection |
| CN109426759A (en) * | 2017-08-22 | 2019-03-05 | 阿里巴巴集团控股有限公司 | The method, apparatus and electronic equipment of the visualization archive of article |
| CN108121816A (en) * | 2017-12-28 | 2018-06-05 | 广东欧珀移动通信有限公司 | Picture classification method, device, storage medium and electronic equipment |
| CN108304563A (en) * | 2018-02-08 | 2018-07-20 | 百度在线网络技术（北京）有限公司 | Image processing method, device and equipment |
| CN108304563B (en) * | 2018-02-08 | 2022-09-27 | 百度在线网络技术（北京）有限公司 | Picture processing method, device and equipment |
| CN109522405A (en) * | 2018-09-29 | 2019-03-26 | 南昌与德软件技术有限公司 | File information processing method, electronic equipment and computer-readable deposit medium |
| CN109471841A (en) * | 2018-10-31 | 2019-03-15 | 维沃移动通信有限公司 | A kind of file classifying method and device |
| CN109634920A (en) * | 2018-11-19 | 2019-04-16 | 北京奇虎科技有限公司 | File consolidation method and device |
| CN112308088A (en) * | 2020-09-16 | 2021-02-02 | 广州忆游科技有限公司 | Method for intelligently screening full-transparent pictures |
| CN112836759A (en) * | 2021-02-09 | 2021-05-25 | 重庆紫光华山智安科技有限公司 | Method and device for evaluating machine-selected picture, storage medium and electronic equipment |
| WO2023138353A1 (en) * | 2022-01-21 | 2023-07-27 | 京东方科技集团股份有限公司 | Picture processing method, electronic device and computer readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105824862A (en) | Image classification method based on electronic equipment and electronic equipment | |
| CN108108657B (en) | Method for correcting locality sensitive Hash vehicle retrieval based on multitask deep learning | |
| CN109284729B (en) | Method, device and medium for acquiring face recognition model training data based on video | |
| US11157550B2 (en) | Image search based on feature values | |
| CN107833213B (en) | Weak supervision object detection method based on false-true value self-adaptive method | |
| CN103186538A (en) | Image classification method, image classification device, image retrieval method and image retrieval device | |
| CN111797239B (en) | Application program classification method and device and terminal equipment | |
| CN101369281A (en) | Retrieval method based on video abstract metadata | |
| KR20120109591A (en) | Methods and apparatuses for facilitating content-based image retrieval | |
| CN104463177A (en) | Similar face image obtaining method and device | |
| CN111242899B (en) | Image-based flaw detection method and computer-readable storage medium | |
| CN105045900A (en) | Data extraction method and apparatus | |
| CN107430604A (en) | The semantic expressiveness of picture material | |
| CN104537341A (en) | Human face picture information obtaining method and device | |
| CN107330027A (en) | A kind of Weakly supervised depth station caption detection method | |
| CN111583180A (en) | Image tampering identification method and device, computer equipment and storage medium | |
| CN105630975A (en) | Information processing method and electronic device | |
| Boato et al. | Exploiting visual saliency for increasing diversity of image retrieval results | |
| CN110414124B (en) | Analysis method and device for similarity of model member files | |
| CN104410867A (en) | Improved video shot detection method | |
| CN105095468A (en) | Novel image retrieval method and system | |
| CN103699612A (en) | Image retrieval ranking method and device | |
| CN111353504A (en) | Source and machine identification method based on image block diversity selection and residual prediction module | |
| Le et al. | Improving logo spotting and matching for document categorization by a post-filter based on homography | |
| Nguyen et al. | Video instance search via spatial fusion of visual words and object proposals |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |