CN104408130A - Picture collating method and device - Google Patents
Picture collating method and device Download PDFInfo
- Publication number
- CN104408130A CN104408130A CN201410705146.6A CN201410705146A CN104408130A CN 104408130 A CN104408130 A CN 104408130A CN 201410705146 A CN201410705146 A CN 201410705146A CN 104408130 A CN104408130 A CN 104408130A
- Authority
- CN
- China
- Prior art keywords
- classification
- classifications
- module
- operations
- clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2132—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on discrimination criteria, e.g. discriminant analysis
Abstract
The invention discloses a picture collating method and device to be used for improving the clustering algorithm and improve the clustering accuracy. The picture collating method comprises the following steps of outputting a plurality of categories of existing pictures after clustering processing according to the clustering algorithm; receiving a disassembling operation of the at least one category in the plurality of categories, wherein the disassembling operation is used for disassembling the category into at least two categories; disassembling the category into at least two categories according to the disassembling operation; establishing a mutual exclusion relationship between the two categories, wherein the mutual exclusion relationship is used for recording a fixed mutual exclusion category in subsequently clustering processing. According to the picture collating method, the clustering algorithm is improved based on the user operation on the categories and the clustering accuracy can be improved when the clustering algorithm is subsequently adopted again.
Description
Technical field
The disclosure relates to computer disposal field, particularly relates to method and the device of photo finishing.
Background technology
Along with the development of electronic technology, mobile terminal is generally applied, and updates quickly.Mobile terminal from initial call function, develop into present to take pictures, the function such as online.Further, the hardware configuration of mobile terminal is more and more higher, and progressively useful mobile terminal replaces the trend of digital camera.People can utilize mobile terminal to carry out autodyning or whip to clap.
Inventor of the present disclosure finds, in correlation technique, a large amount of photos can store in the terminal, also can be stored in Cloud Server.No matter be stored in mobile terminal or be stored in Cloud Server, all can relate to the problem that photo arranges.
But, exist and arrange photo complex operation or arrange inaccurate situation.
Summary of the invention
For overcoming Problems existing in correlation technique, the disclosure provides a kind of method and device of photo finishing.
According to the first aspect of disclosure embodiment, a kind of method of photo finishing is provided, comprises:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment is based on the fractured operation of user to classification, set up the mutex relation between classification, so that when again carrying out clustering processing, the classification with mutex relation can not be carried out clustering processing, improve clustering algorithm, make clustering processing more accurate.
In one embodiment, described method also comprises:
When again carrying out clustering processing to existing picture, judge to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
When needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbid carrying out clustering processing to described two classifications of carrying out cluster that need.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: when a picture in the present embodiment in a classification and a picture in another classification belong to two mutual exclusion classifications in mutex relation, clustering processing can not be carried out to these two classifications, make clustering processing result more accurate.
In one embodiment, described method also comprises:
Add up the number of times of described fractured operation;
Judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment, according to the similarity threshold in the number of times adjustment clustering algorithm of fractured operation, realizes the improvement to clustering algorithm, improves the accuracy of clustering processing.
In one embodiment, described method also comprises:
Receive the union operation at least two classifications in described multiple classification.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment, except support fractured operation, also supports union operation.
In one embodiment, described method also comprises:
Add up the number of times of described union operation;
Judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment, according to the similarity threshold in the number of times adjustment clustering algorithm of union operation, realizes the improvement to clustering algorithm, improves the accuracy of clustering processing.
In one embodiment, described output carries out the multiple classifications after clustering processing according to clustering algorithm to existing picture, comprising:
Export, according to clustering algorithm, similarity the most much higher classification after clustering processing is carried out to existing picture.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment exports the higher limited multiple classification of similarity, makes Output rusults more accurate, reduces the interference to user.
In one embodiment, described method also comprises:
For the multiple classifications exported, judge whether to exist the classification not carrying out operating;
When the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
When described non-number of operations is greater than default non-number of operations threshold value, described in foundation, do not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect: the present embodiment, for the classification do not operated, also can determine the relation of this classification and other classification, contributes to improving clustering algorithm, improves the accuracy of clustering processing.
According to the second aspect of disclosure embodiment, a kind of device of photo finishing is provided, comprises:
Output module, carries out multiple classifications clustering processing after according to clustering algorithm to existing picture for exporting;
First receiver module, for receiving the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
Split module, for according to described fractured operation, a described classification is split as at least two classifications;
First sets up module, and for setting up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
In one embodiment, described device also comprises:
Mutual exclusion judge module, during for again carrying out clustering processing to existing picture, judges to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
Disabled module, for when needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbids carrying out clustering processing to described two classifications of carrying out cluster that need.
In one embodiment, described device also comprises:
First statistical module, for adding up the number of times of described fractured operation;
First ratio in judgement module, for judging whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
Heighten module, when the ratio for accounting for total number of operations at the number of times of described fractured operation is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
In one embodiment, described device also comprises:
Second receiver module, for receiving the union operation at least two classifications in described multiple classification.
In one embodiment, described device also comprises:
Second statistical module, for adding up the number of times of described union operation;
Second ratio in judgement module, for judging whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
Turn down module, when the ratio for accounting for total number of operations at the number of times of described union operation is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
In one embodiment, described output module exports and carries out similarity the most much higher classification after clustering processing according to clustering algorithm to existing picture.
In one embodiment, described device also comprises:
Non-operation judges module, for for the multiple classifications exported, judges whether to exist the classification not carrying out operating;
Update module, for when the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
Second sets up module, for when described non-number of operations is greater than default non-number of operations threshold value, does not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated described in foundation.
According to the third aspect of disclosure embodiment, a kind of device of photo finishing is provided, comprises:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows and meets embodiment of the present disclosure, and is used from instructions one and explains principle of the present disclosure.
Fig. 1 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment.
Fig. 2 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment.
Fig. 3 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment.
Fig. 4 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment.
Fig. 5 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Fig. 6 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Fig. 7 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Fig. 8 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Fig. 9 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Figure 10 is the block diagram of the device of a kind of photo finishing according to an exemplary embodiment.
Figure 11 is the block diagram of a kind of device according to an exemplary embodiment.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.
In correlation technique, user can take a large amount of photo, is stored in mobile terminal or Cloud Server.Mobile terminal or Cloud Server can help user's summarizing photo automatically, as the photo with same personage is included into a file, or the photo with same style are included into a file.This is included into process is have employed clustering algorithm, is returned together by more much higher for a similarity photo.But, may exist and the photo not being same people has been included into a file, or the multiple pictures of same people has been included into different files.Clustering processing is not accurate enough.
For solving this problem, the present embodiment, based on the operation of user to classification, improves clustering algorithm, makes clustering processing more accurate.
Fig. 1 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment, and as shown in Figure 1, the method can be realized by mobile terminal or server, comprises the following steps:
In a step 101, export foundation clustering algorithm and the multiple classifications after clustering processing are carried out to existing picture.
In a step 102, receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications.
In step 103, according to described fractured operation, a described classification is split as at least two classifications.
At step 104, set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
Wherein, fixing mutual exclusion classification refers to can not carry out clustering processing to the classification with mutex relation in follow-up clustering processing, namely disregards the similarity between classification that calculator has a mutex relation.Such as, classification A and classification B is mutual exclusion classification, when there being classification C, calculates classification C and classification A, and the similarity of classification C and classification B, does not need the similarity calculating classification A and classification B.
The present embodiment, according to the fractured operation of user to classification, sets up the mutex relation between classification.This mutex relation is applied in clustering algorithm, when carrying out clustering processing, need with reference to this mutex relation, and forbid cluster between multiple classifications with mutex relation.Had by mutex relation and stablized and classify accurately, efficiency and the accuracy rate of clustering processing can have been significantly improved.
Clustering algorithm in the present embodiment can be hierarchical clustering algorithm etc.Such as, user utilizes mobile terminal to have taken a large amount of photos.Mobile terminal comparison film carries out automatic clustering.During initial classification, each photo is a class, calculates the similarity (or claiming distance) between two classes, when similarity is greater than default similarity threshold, two classes is classified as a class.Iteration like this, until classification is stablized.
Classification stable after showing clustering processing to user, such as, have classification A and classification C.Picture a1, a2, a3 and b1 is had in classification A (file A).Picture c1 is had in classification C.After user sees classification A and classification C, from classification A, split out picture b1, such as, picture b1 has been shifted out from file A.Then according to the fractured operation of user, for picture b1 sets up classification B.Picture in classification A becomes picture a1, a2 and a3.Then the mutex relation of classification A and classification B is set up, namely picture a1, a2 and a3 and picture b1 mutual exclusion.
When there being picture b2 again, need again to carry out cluster operation.Then according to mutex relation, the clustering algorithm after namely improving, calculates the similarity of picture b2 and classification A-classification C, does not need to calculate the similarity between classification A and classification B.After calculating, determine that the similarity of b2 and classification B is nearest, and be greater than default similarity threshold, then b2 is included in classification B.Because classification A and classification B is two stable classifications, again do not need the similarity both calculating during cluster, improve the efficiency of clustering processing, and improve the accuracy of cluster.
In one embodiment, described method also comprises step H1 and step H2.
In step H1, when again carrying out clustering processing to existing picture, judge to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
In step H2, when needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbid carrying out clustering processing to described two classifications of carrying out cluster that need.
When needing the picture carried out in two classifications of cluster not belong to the mutual exclusion classification of described mutex relation record, the similarity between two classifications can be calculated, and then determine whether cluster.
When again carrying out clustering processing in the present embodiment, to calculating and the judgement not carrying out similarity between the classification recorded in mutex relation, can reduce the calculated amount of clustering algorithm; And the classification with mutex relation belongs to stable classification, carry out clustering processing accordingly, the accuracy of process can be improved.
In one embodiment, described method also comprises step I1-step I3.
In step I1, add up the number of times of described fractured operation.
In step I2, judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value; When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, continue step I3; When the ratio that the number of times of described fractured operation accounts for total number of operations is not more than the first default proportion threshold value, terminate this flow process.
In step I3, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
In the present embodiment, if user has carried out more fractured operation, then illustrate that the classification that this clustering processing should not merge merges, namely this dissimilar classification has been judged as similar.Can determine to judge that similar yardstick is comparatively loose, namely similarity threshold is on the low side, suitably can heighten similarity threshold, to judge similar with stricter yardstick, improves the accuracy merged, and also claims to improve recall rate.
Such as, user opens the file that certain has picture, and this file is classification A.Then user clicks recommendation button, wishes that mobile terminal is recommended to belong to of a sort picture with classification A to user.Mobile terminal, under the triggering recommending button, can carry out clustering processing in whole memory space ranges, finds and belongs to of a sort picture with classification A.Mobile terminal calculates the similarity between other picture (comprising other classification, namely other file) and classification A by clustering algorithm.Check whether classification A has mutual exclusion classification, if had, then the mutual exclusion classification of classification A does not participate in this clustering processing by mutex relation simultaneously.Such as, determine after clustering processing that classification A1, classification A2, classification B1, classification B2 and classification B3 and classification A belong to of a sort picture, carried out merging treatment.Result is shown to user.Classification B1, classification B2 and classification B3 split by user from the classification A after merging.Mobile terminal is according to the fractured operation of user, classification B1, classification B2 and classification B3 are shifted out from the classification A after merging, and set up the mutex relation of classification A and classification B1, classification B2 and classification B3, and be independently a class or 3 classes by classification B1, classification B2 and classification B3.And the fractured operation of mobile terminal to user is added up, user has carried out 3 operations altogether, and 3 times are fractured operation.The ratio that the number of times of fractured operation accounts for total number of operations is 100%, exceed default the first proportion threshold value (as 60%), then current similarity threshold (as 85%) is heightened, if the similarity threshold after heightening is 90% according to the first step-length (as 5%) preset.
In one embodiment, user is except carrying out except fractured operation to classification, and can also carry out union operation to classification, then described method also comprises: step J1.
In step J1, receive the union operation at least two classifications in described multiple classification.
Union operation based on user in the present embodiment merges classification, and the classification after merging is more stable, no longer this classification inside is carried out to the calculating of similarity, also can not carry out deconsolidation process to this classification.Make when follow-up clustering processing, treatment effeciency is higher, more accurately.
Show the classification after clustering processing to user, such as, have classification A1, classification A2, classification A3 and classification C.User has carried out union operation to classification A1, classification A2 and classification A3, merges into classification A1.Then classification A1 is for stablize classification, when follow-up clustering processing, does not split classification A1, does not also need to calculate the similarity between classification A1 inside again.
In one embodiment, described method also comprises: step K 1-step K 3.
In step K 1, add up the number of times of described union operation.
In step K 2, judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value; When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, continue step K 3; When the ratio that the number of times of described union operation accounts for total number of operations is not more than the second default proportion threshold value, terminate this flow process.
In step K 3, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
In the present embodiment, if user has carried out more union operation, then illustrate that the classification that this clustering processing should not split merges, namely originally similar classification has been judged as dissmilarity.Can determine to judge that similar yardstick is comparatively strict, namely similarity threshold is higher, suitably can turn down similarity threshold, to judge similar with stricter yardstick, improves the accuracy merged, and also claims to improve recall rate.
Such as, user uploads a large amount of photos to cloud server.Cloud server needs comparison film to sort out after receiving photo, and the newly-built classification of possibility, also may be included into existing classification by photo.Server for all newly-built independently classification of each photo newly received, in conjunction with existing mutex relation, calculates the similarity between newly-built classification according to clustering algorithm, and the similarity between newly-built classification and existing classification.Similarity between existing classification can be selected not calculate, and thinks that existing classification belongs to stable classification.Such as, classification is defined after clustering processing: classification A1, classification A2, classification B1, classification B2 and classification B3.This result is shown to user by mobile terminal.Classification A1 and classification A2 merges by user, and by classification B1, classification B2 and classification B3.Classification A1 and classification A2, according to the union operation of user, is merged into classification A1 by server, and classification B1, classification B2 and classification B3 are merged into classification B1.And the union operation of server to user is added up, user has carried out 3 operations altogether, and 3 times are union operation.The ratio that the number of times of union operation accounts for total number of operations is 100%, exceed default the second proportion threshold value (as 60%), then current similarity threshold (as 90%) is turned down, if the similarity threshold after turning down is 85% according to the second step-length (as 5%) preset.
In one embodiment, step 101 can also be embodied as step L1.
In step L1, export, according to clustering algorithm, similarity the most much higher classification after clustering processing is carried out to existing picture.
In the present embodiment, when exporting multiple classification to user, can select several classifications that similarity is higher, the meaning that similarity is higher refers to, the similarity of the classification of output is all higher than the similarity of the classification do not exported.The classification that similarity is on the low side may not be the classification required for user, if export to user, then can bring interference to user, and take more display space.
Such as, upload a pictures in the search column that user provides at mobile terminal, wish the picture that search is similar with this picture in the terminal, such as there is the picture etc. of identical face.Mobile terminal searches the picture with this picture with identical face in the storage space of this locality.Mobile terminal calculates the similarity of all pictures and this picture in storage space according to clustering algorithm, for existing classification, calculates the similarity of classification and this picture.Determine that similarity is greater than the classification of default similarity threshold.Determine to be greater than n the classification that in the classification of similarity threshold, similarity is the highest further, n be greater than 1 integer, such as n=5.Right rear line exports 5 the highest classifications of similarity.User can merge or fractured operation the classification exported.
Forgoing describe user to split or union operation the classification exported.But also may there is a kind of situation, be exactly that user did not both split certain classification, also do not merge.For this part classification, also mutex relation can be set up, to improve clustering algorithm.
In one embodiment, described in
Method also comprises: step M1-step M3.
In step M1, for the multiple classifications exported, judge whether to exist the classification not carrying out operating.
In step M2, when the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding.
In step M3, when described non-number of operations is greater than default non-number of operations threshold value, described in foundation, do not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated.
If export repeatedly same classification to user in the present embodiment, with not splitting or union operation this classification per family, then can be this classification and set up the mutex relation with other classification.The present embodiment considers that user does not split or union operation this classification, may be because the carelessness of user, all this classification is not operated if repeatedly exported, so can think that this is not cause not operating due to user's carelessness, essence reason is that this classification is stablized, should be independently a classification, the mutex relation therefore set up be more accurate, makes the clustering algorithm after improving also more accurate.
Such as, user is repeatedly to cloud server upload pictures.Cloud server exports classification A and classification C to user at every turn.With not splitting or union operation to classification A and classification C per family.Record the classification that user does not operate at every turn after server exports, judge whether that the number of times (i.e. non-number of operations) that classification is recorded reaches non-number of operations threshold value (as 3 times), if had, then for this classification sets up mutex relation.Such as user does not split or union operation to classification A and classification C for continuous 3 times, reaches non-number of operations threshold value.Server can be classification A and classification C sets up mutex relation, illustrates that classification A and classification C is stable classification.
In one embodiment, when carrying out clustering processing, cluster can not be carried out to two classifications with mutex relation.Such as, mutex relation is had between classification A and classification C.After carrying out clustering processing, export classification A and classification C to user.User can split or union operation the classification exported.Such as, user carries out union operation to classification A and classification C.Have mutex relation between classification A and classification C, but user merges to classification A and classification C again.Now, a kind of mode forbids merging treatment.Another kind of mode is that mobile terminal or server can export information to user, has mutex relation between reminding user classification A and classification C.User can select to continue to merge, and also can select to cancel to merge.If user selects to continue to merge, then under user selects the triggering operated, classification A and classification C merges by mobile terminal or server, and upgrades mutex relation, namely cancels the mutex relation between classification A and classification C.Merge if user selects to cancel, then terminate this flow process.
In one embodiment, user is when having carried out union operation to certain classification, and the mutual exclusion classification that the classification of merging is corresponding also needs to merge.Such as, classification A1 and classification B1 mutual exclusion, classification A2 and classification B2 mutual exclusion.Classification A1 and classification A2 merges by user, and the classification after merging is classification A1.Then mobile terminal or server are while merging classification A1 and classification A2, are merged by classification B1 and classification B2 in the mutex relation that classification A1 is corresponding, namely in the mutual exclusion classification that classification A1 is corresponding, increase classification B2.Meanwhile, also increase classification A1 in the mutual exclusion classification that classification B2 is corresponding, in other words classification A2 is changed to classification A1.
In one embodiment, need to calculate the similarity between classification in cluster process.If a classification contains a large amount of pictures, then when calculating the similarity between classification, calculated amount is larger.For solving this problem, the present embodiment can select representative picture for each classification, and such as classification A comprises 200 pictures, therefrom selects 50 pictures representatively picture.When calculating the similarity between classification, calculate the similarity between representative picture in a classification and the representative picture in another classification.Significantly can reduce calculated amount like this, improve the efficiency of clustering processing.
Wherein, select the strategy of representative picture to have multiple, as the distribution situation according to unique point selects representative picture, each representative picture comprises more unique point.All representative pictures can cover all unique points substantially.Other strategies can also be had, be all applicable to the present embodiment.
In one embodiment, a classification essence can be a file, and file has title.When carrying out clustering processing, can process in conjunction with Folder Name.Such as, the categories combination with same names is a classification, and the classification with different names is mutual exclusion classification each other.Such as, there is the name of two files all to cry " Zhang San ", then these two files are merged into a file.And for example, being named as " Zhang San " of a file, being named as " Li Si " of a file, the name of these two files is completely different, then these two files are mutual exclusion classification each other, can be recorded in mutex relation.
The implementation procedure of photo finishing is introduced in detail below by several embodiment.
Fig. 2 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment, and as shown in Figure 2, the method can be realized by mobile terminal or server, comprises the following steps:
In step 201, multiple picture is obtained.
In step 202., according to clustering algorithm, clustering processing is carried out to multiple picture, obtain the multiple classifications after process.
In step 203, the multiple classifications after output processing.
In step 204, the fractured operation at least one classification in described multiple classification is received.
In step 205, according to described fractured operation, a described classification is split as at least two classifications.
In step 206, set up the mutex relation between described two classifications, described mutex relation can not carry out the mutual exclusion classification of cluster to the classification with mutex relation in follow-up clustering processing for being recorded in.
In step 207, the number of times of described fractured operation is added up.This step synchronously can be carried out with step 206.
In a step 208, judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value; When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, continue step 209; When the ratio that the number of times of described fractured operation accounts for total number of operations is not more than the first default proportion threshold value, terminate this flow process.
In step 209, the similarity threshold in described clustering algorithm is heightened according to the first step-length preset.
The present embodiment establishes mutex relation according to the fractured operation of user, determines stable classification, can improve clustering algorithm.Meanwhile, according to the fractured operation adjustable similarity threshold of user, to improve clustering algorithm, make clustering processing more accurate.
Fig. 3 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment, and as shown in Figure 3, the method can be realized by mobile terminal or server, comprises the following steps:
In step 301, export foundation clustering algorithm and the multiple classifications after clustering processing are carried out to existing picture.
In step 302, the union operation at least two classifications in described multiple classification is received.
In step 303, according to described union operation, be a classification by described two categories combinations.
In step 304, in mutex relation by mutual exclusion categories combination corresponding for described two classifications.Be equivalent to the mutex relation upgrading described two classifications and mutual exclusion classification corresponding to described two classifications.
In step 305, the number of times of described union operation is added up.
Within step 306, judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value; When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, continue step 307; When the ratio that the number of times of described union operation accounts for total number of operations is not more than the second default proportion threshold value, terminate this flow process.
In step 307, the similarity threshold in described clustering algorithm is turned down according to the second step-length preset.
The present embodiment have updated mutex relation according to the union operation of user, to improve clustering algorithm, improves efficiency and the accuracy of clustering processing.Meanwhile, according to the union operation adjustable similarity threshold of user, to improve clustering algorithm, make clustering processing more accurate.
Fig. 4 is the process flow diagram of the method for a kind of photo finishing according to an exemplary embodiment, and as shown in Figure 4, the method can be realized by mobile terminal, comprises the following steps:
Such as, user opens a file folder on mobile terminals, clicks and recommends button.
In step 401, under the triggering recommending button, obtain the classification in storage space.This classification can be a file comprising picture, also can be an independent picture.Obtain all categories about picture in local storage space as far as possible.
In step 402, according to mutex relation and Folder Name, calculate the similarity between representative picture and the classification of acquisition in current file folder.
In step 403, determine that similarity is greater than the classification of default similarity threshold.
In step 404, n the classification that in the classification of similarity threshold, similarity is the highest is determined to be greater than.
In step 405, n the classification determined is exported.
In a step 406, using current file folder as classification respectively with a described n categories combination.
If user has fractured operation to n classification, then carry out deconsolidation process, if do not had, then carry out merging treatment.
Mutex relation and Folder Name are combined by the present embodiment, can significantly improve efficiency and the accuracy of clustering processing.Further, when calculating similarity, only adopting representative picture to calculate, one can be entered and improve treatment effeciency.When output processing result, export several classifications that similarity is the highest, Output rusults more meets the demand of user, reduces the interference to user simultaneously.
By being described above the implementation procedure of having separated photo finishing, this process is realized by mobile terminal or server, is introduced below for the inner structure of equipment and function.
Fig. 5 is the device schematic diagram of a kind of photo finishing according to an exemplary embodiment.With reference to Fig. 5, this device comprises: output module 501, first receiver module 502, fractionation module 503 and first set up module 504.
Output module 501, carries out multiple classifications clustering processing after according to clustering algorithm to existing picture for exporting.
First receiver module 502, for receiving the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications.
Split module 503, for according to described fractured operation, a described classification is split as at least two classifications.
First sets up module 504, and for setting up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
In one embodiment, as shown in Figure 6, described device also comprises: mutual exclusion judge module 505 and disabled module 506.
Mutual exclusion judge module 505, during for again carrying out clustering processing to existing picture, judges to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record.
Disabled module 506, for when needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbids carrying out clustering processing to described two classifications of carrying out cluster that need.
In one embodiment, as shown in Figure 7, described device also comprises: the first statistical module 507, first ratio in judgement module 508 and heighten module 509.
First statistical module 507, for adding up the number of times of described fractured operation.
First ratio in judgement module 508, for judging whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value.
Heighten module 509, when the ratio for accounting for total number of operations at the number of times of described fractured operation is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
In one embodiment, as shown in Figure 8, described device also comprises: the second receiver module 510.
Second receiver module 510, for receiving the union operation at least two classifications in described multiple classification.
In one embodiment, as shown in Figure 9, described device also comprises: the second statistical module 511, second ratio in judgement module 512 and turn down module 513.
Second statistical module 511, for adding up the number of times of described union operation.
Second ratio in judgement module 512, for judging whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value.
Turn down module 513, when the ratio for accounting for total number of operations at the number of times of described union operation is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
In one embodiment, described output module 501 exports and carries out similarity the most much higher classification after clustering processing according to clustering algorithm to existing picture.
In one embodiment, as shown in Figure 10, described device also comprises: non-operation judges module 514, update module 515 and second set up module 516.
Non-operation judges module 514, for for the multiple classifications exported, judges whether to exist the classification not carrying out operating.
Update module 515, for when the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding.
Second sets up module 516, for when described non-number of operations is greater than default non-number of operations threshold value, does not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated described in foundation.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
Figure 11 is the block diagram of a kind of device 1100 for photo finishing according to an exemplary embodiment.Such as, device 1100 can be mobile phone, computing machine, digital broadcast terminal, messaging devices, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc.
With reference to Figure 11, device 1100 can comprise following one or more assembly: processing components 1102, storer 1104, power supply module 1106, multimedia groupware 1108, audio-frequency assembly 1110, the interface 1112 of I/O (I/O), sensor module 1114, and communications component 1116.
The integrated operation of the usual control device 1100 of processing components 1102, such as with display, call, data communication, camera operation and record operate the operation be associated.Processing components 1102 can comprise one or more processor 1120 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 1102 can comprise one or more module, and what be convenient between processing components 1102 and other assemblies is mutual.Such as, processing element 1102 can comprise multi-media module, mutual with what facilitate between multimedia groupware 1108 and processing components 1102.
Storer 1104 is configured to store various types of data to be supported in the operation of equipment 1100.The example of these data comprises for any application program of operation on device 1100 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 1104 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
The various assemblies that electric power assembly 1106 is device 1100 provide electric power.Electric power assembly 1106 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for device 1100 and be associated.
Multimedia groupware 1108 is included in the screen providing an output interface between described device 1100 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 1108 comprises a front-facing camera and/or post-positioned pick-up head.When equipment 1100 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 1110 is configured to export and/or input audio signal.Such as, audio-frequency assembly 1110 comprises a microphone (MIC), and when device 1100 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 1104 further or be sent via communications component 1116.In certain embodiments, audio-frequency assembly 1110 also comprises a loudspeaker, for output audio signal.
I/O interface 1112 is for providing interface between processing components 1102 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 1114 comprises one or more sensor, for providing the state estimation of various aspects for device 1100.Such as, sensor module 1114 can detect the opening/closing state of equipment 1100, the relative positioning of assembly, such as described assembly is display and the keypad of device 1100, the position of an assembly of all right pick-up unit 1100 of sensor module 1114 or device 1100 changes, the presence or absence that user contacts with device 1100, the temperature variation of device 1100 orientation or acceleration/deceleration and device 1100.Sensor module 1114 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 1114 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 1114 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 1116 is configured to the communication being convenient to wired or wireless mode between device 1100 and other equipment.Device 1100 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communication component 1116 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communication component 1116 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, device 1100 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 1104 of instruction, above-mentioned instruction can perform said method by the processor 1120 of device 1100.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A device for photo finishing, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
Described processor can also be configured to:
When again carrying out clustering processing to existing picture, judge to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
When needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbid carrying out clustering processing to described two classifications of carrying out cluster that need.
Described processor can also be configured to:
Add up the number of times of described fractured operation;
Judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
Described processor can also be configured to:
Receive the union operation at least two classifications in described multiple classification.
Described processor can also be configured to:
Add up the number of times of described union operation;
Judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
Described processor can also be configured to:
Described output carries out the multiple classifications after clustering processing according to clustering algorithm to existing picture, comprising:
Export, according to clustering algorithm, similarity the most much higher classification after clustering processing is carried out to existing picture.
Described processor can also be configured to:
For the multiple classifications exported, judge whether to exist the classification not carrying out operating;
When the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
When described non-number of operations is greater than default non-number of operations threshold value, described in foundation, do not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of mobile terminal, make mobile terminal can perform a kind of method of photo finishing, described method comprises:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
Instruction in described storage medium can also comprise:
When again carrying out clustering processing to existing picture, judge to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
When needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbid carrying out clustering processing to described two classifications of carrying out cluster that need.
Instruction in described storage medium can also comprise:
Add up the number of times of described fractured operation;
Judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
Instruction in described storage medium can also comprise:
Receive the union operation at least two classifications in described multiple classification.
Instruction in described storage medium can also comprise:
Add up the number of times of described union operation;
Judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
Instruction in described storage medium can also comprise:
Described output carries out the multiple classifications after clustering processing according to clustering algorithm to existing picture, comprising:
Export, according to clustering algorithm, similarity the most much higher classification after clustering processing is carried out to existing picture.
Instruction in described storage medium can also comprise:
For the multiple classifications exported, judge whether to exist the classification not carrying out operating;
When the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
When described non-number of operations is greater than default non-number of operations threshold value, described in foundation, do not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated.
Those skilled in the art, at consideration instructions and after putting into practice invention disclosed herein, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.
Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.
Claims (15)
1. a method for photo finishing, is characterized in that, comprising:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
2. the method for photo finishing according to claim 1, is characterized in that, described method also comprises:
When again carrying out clustering processing to existing picture, judge to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
When needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbid carrying out clustering processing to described two classifications of carrying out cluster that need.
3. the method for photo finishing according to claim 1, is characterized in that, described method also comprises:
Add up the number of times of described fractured operation;
Judge whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
When the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
4. the method for photo finishing according to claim 1, is characterized in that, described method also comprises:
Receive the union operation at least two classifications in described multiple classification.
5. the method for photo finishing according to claim 4, is characterized in that, described method also comprises:
Add up the number of times of described union operation;
Judge whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
When the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
6. the method for photo finishing according to claim 1, is characterized in that, described output carries out the multiple classifications after clustering processing according to clustering algorithm to existing picture, comprising:
Export, according to clustering algorithm, similarity the most much higher classification after clustering processing is carried out to existing picture.
7. the method for photo finishing according to claim 1, is characterized in that, described method also comprises:
For the multiple classifications exported, judge whether to exist the classification not carrying out operating;
When the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
When described non-number of operations is greater than default non-number of operations threshold value, described in foundation, do not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated.
8. a device for photo finishing, is characterized in that, comprising:
Output module, carries out multiple classifications clustering processing after according to clustering algorithm to existing picture for exporting;
First receiver module, for receiving the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
Split module, for according to described fractured operation, a described classification is split as at least two classifications;
First sets up module, and for setting up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
9. the device of photo finishing according to claim 8, is characterized in that, described device also comprises:
Mutual exclusion judge module, during for again carrying out clustering processing to existing picture, judges to need the picture carried out in two classifications of cluster whether to belong to the mutual exclusion classification of described mutex relation record;
Disabled module, for when needing the picture carried out in two classifications of cluster to belong to the mutual exclusion classification of described mutex relation record, forbids carrying out clustering processing to described two classifications of carrying out cluster that need.
10. the device of photo finishing according to claim 8, is characterized in that, described device also comprises:
First statistical module, for adding up the number of times of described fractured operation;
First ratio in judgement module, for judging whether the ratio that the number of times of described fractured operation accounts for total number of operations is greater than the first default proportion threshold value;
Heighten module, when the ratio for accounting for total number of operations at the number of times of described fractured operation is greater than the first default proportion threshold value, heighten the similarity threshold in described clustering algorithm according to the first step-length preset.
The device of 11. photo finishings according to claim 8, is characterized in that, described device also comprises:
Second receiver module, for receiving the union operation at least two classifications in described multiple classification.
The device of 12. photo finishings according to claim 11, is characterized in that, described device also comprises:
Second statistical module, for adding up the number of times of described union operation;
Second ratio in judgement module, for judging whether the ratio that the number of times of described union operation accounts for total number of operations is greater than the second default proportion threshold value;
Turn down module, when the ratio for accounting for total number of operations at the number of times of described union operation is greater than the second default proportion threshold value, turn down the similarity threshold in described clustering algorithm according to the second step-length preset.
The device of 13. photo finishings according to claim 8, is characterized in that, described output module exports and carries out similarity the most much higher classification after clustering processing according to clustering algorithm to existing picture.
The device of 14. photo finishings according to claim 8, is characterized in that, described device also comprises:
Non-operation judges module, for for the multiple classifications exported, judges whether to exist the classification not carrying out operating;
Update module, for when the classification operated is not carried out in existence, the non-number of operations that the classification not carrying out described in renewal operating is corresponding;
Second sets up module, for when described non-number of operations is greater than default non-number of operations threshold value, does not carry out the mutex relation of other classification in multiple classifications of classification and the described output operated described in foundation.
The device of 15. 1 kinds of photo finishings, is characterized in that, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Export, according to clustering algorithm, the multiple classifications after clustering processing are carried out to existing picture;
Receive the fractured operation at least one classification in described multiple classification, described fractured operation is used for a classification to be split as at least two classifications;
According to described fractured operation, a described classification is split as at least two classifications;
Set up the mutex relation between described two classifications, described mutex relation is for being recorded in mutual exclusion classification fixing in follow-up clustering processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705146.6A CN104408130B (en) | 2014-11-26 | 2014-11-26 | The method and device of photo finishing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705146.6A CN104408130B (en) | 2014-11-26 | 2014-11-26 | The method and device of photo finishing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104408130A true CN104408130A (en) | 2015-03-11 |
| CN104408130B CN104408130B (en) | 2018-04-27 |
Family
ID=52645761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410705146.6A Active CN104408130B (en) | 2014-11-26 | 2014-11-26 | The method and device of photo finishing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104408130B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784270A (en) * | 2019-01-11 | 2019-05-21 | 厦门大学嘉庚学院 | A kind of processing method promoting face picture identification integrality |
| CN111177388A (en) * | 2019-12-30 | 2020-05-19 | 联想(北京)有限公司 | Processing method and computer equipment |
| CN113407716A (en) * | 2021-05-14 | 2021-09-17 | 桂林电子科技大学 | Human behavior text data set construction and processing method based on crowdsourcing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020029232A1 (en) * | 1997-11-14 | 2002-03-07 | Daniel G. Bobrow | System for sorting document images by shape comparisons among corresponding layout components |
| CN103914518A (en) * | 2014-03-14 | 2014-07-09 | 小米科技有限责任公司 | Clustering method and clustering device |
| CN104123339A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Method and device for image management |
-
2014
- 2014-11-26 CN CN201410705146.6A patent/CN104408130B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020029232A1 (en) * | 1997-11-14 | 2002-03-07 | Daniel G. Bobrow | System for sorting document images by shape comparisons among corresponding layout components |
| CN103914518A (en) * | 2014-03-14 | 2014-07-09 | 小米科技有限责任公司 | Clustering method and clustering device |
| CN104123339A (en) * | 2014-06-24 | 2014-10-29 | 小米科技有限责任公司 | Method and device for image management |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109784270A (en) * | 2019-01-11 | 2019-05-21 | 厦门大学嘉庚学院 | A kind of processing method promoting face picture identification integrality |
| CN109784270B (en) * | 2019-01-11 | 2023-05-26 | 厦门大学嘉庚学院 | Processing method for improving face picture recognition integrity |
| CN111177388A (en) * | 2019-12-30 | 2020-05-19 | 联想(北京)有限公司 | Processing method and computer equipment |
| CN111177388B (en) * | 2019-12-30 | 2023-07-21 | 联想(北京)有限公司 | Processing method and computer equipment |
| CN113407716A (en) * | 2021-05-14 | 2021-09-17 | 桂林电子科技大学 | Human behavior text data set construction and processing method based on crowdsourcing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104408130B (en) | 2018-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104166689B (en) | The rendering method and device of e-book | |
| CN104105169B (en) | From method and the device of the WLAN (wireless local area network) that is dynamically connected | |
| CN106776890A (en) | The method of adjustment and device of video playback progress | |
| CN104281432A (en) | Method and device for regulating sound effect | |
| CN106126052A (en) | Text selection method and device | |
| CN105487863A (en) | Interface setting method and device based on scene | |
| CN105338409A (en) | Network video pre-loading method and device | |
| CN104951336A (en) | Application program installation method and device | |
| CN105069073A (en) | Contact information recommendation method and device | |
| CN104834559A (en) | Notification message display method and device | |
| CN104238912A (en) | Application control method and application control device | |
| CN105389304A (en) | Event extraction method and apparatus | |
| CN104267881B (en) | The operating method and device of toolbar | |
| CN107102772A (en) | Touch control method and device | |
| CN104461348A (en) | Method and device for selecting information | |
| CN105447109A (en) | Key word searching method and apparatus | |
| CN103914148A (en) | Function interface display method and device and terminal equipment | |
| CN105550643A (en) | Medical term recognition method and device | |
| CN105094904A (en) | Application program installation method and device | |
| CN104598534A (en) | Picture folding method and device | |
| CN105242837A (en) | Application page acquisition method and terminal | |
| CN104408130A (en) | Picture collating method and device | |
| CN105183586A (en) | Method and apparatus for restoring accidentally deleted file in EXT file system and intelligent device | |
| CN104268149A (en) | Clustering method and clustering device | |
| CN105224950A (en) | The recognition methods of filter classification and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |