CN106777007A - Photograph album Classified optimization method, device and mobile terminal - Google Patents
Photograph album Classified optimization method, device and mobile terminal Download PDFInfo
- Publication number
- CN106777007A CN106777007A CN201611116167.XA CN201611116167A CN106777007A CN 106777007 A CN106777007 A CN 106777007A CN 201611116167 A CN201611116167 A CN 201611116167A CN 106777007 A CN106777007 A CN 106777007A
- Authority
- CN
- China
- Prior art keywords
- picture
- similarity
- characteristic
- album
- definition
- 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
- G06F16/162—Delete operations
-
- 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
- G06F16/17—Details of further file system functions
- G06F16/178—Techniques for file synchronisation in 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
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The present invention provides a kind of photograph album Classified optimization method, device and mobile terminal, and the photograph album Classified optimization method comprises the following steps：Image similarity identification is carried out to each picture of system photograph album, multigroup picture of the similarity between image feature data in default similarity dimensions is determined, and multigroup picture is stored to the other temporary folder of respective sets respectively；All pictures in each temporary folder carry out image definition identification, mark the picture less than predetermined definition respectively according to described image characteristic；Labeled picture and synchronous updating system photograph album is deleted according to predetermined set or user instruction.The present invention carries out the classification and optimization of picture by carrying out similarity identification and definition identification to album picture, it is achieved thereby that the picture in automatic phasing volume is arranged, and can quickly clear up the not good fuzzy photo of quality in photograph album, save storage area, efficiency is improve, Consumer's Experience is improved.
Description
Technical field
The present invention relates to technical field of image processing and moving communicating field, more particularly to a kind of photograph album Classified optimization
Method, device and mobile terminal.
Background technology
With the popularization of smart mobile phone and digital camera, photograph taking increasingly day-to-day, magnanimity.But with what is clapped
Photo is more and more, and this has brought a worry, is how to store and manage these photos.
Taken pictures when user is daily now or travels outdoors, inevitably produce many blurred image, usual user
These photos will not in time be processed in shooting process, cause to store a large amount of underproof photos in photograph album, wasted
Memory space, and being deleted manually, it is necessary to check one by one when user needs treatment in the future, operation and its numerous
It is trivial, inefficiency.Meanwhile, user often shoots multiple pictures when travelling outdoors by background of same sight spot, generates perhaps
More similar similar photo, due to not sorting out to these photos so that the photo in photograph album seems disorderly and unsystematic,
Inconvenient user is managed to these photos in the future.
It can be seen that, existing technical scheme can not be realized to a large amount of photos according to the feature in different background or picture simultaneously
Thing is classified and is filtered out the function of picture quality preferably picture automatically, and it is substantial amounts of manually operated to increased user, user
Experience is poor.As can be seen here, traditional approach can not meet the demand of user on classification, optimization and management photo, cause photo
Disorderly and unsystematic, user's search efficiency is low.
The content of the invention
In view of the above problems, the present invention proposes a kind of photograph album Classified optimization method and its corresponding device, by photograph album
Picture carries out similarity identification and definition identification, realizes automatic Classified optimization and the management of album picture.
The present invention also provides a kind of mobile terminal for performing photograph album Classified optimization method of the invention.
To solve the above problems, the present invention uses the technical scheme of following each side：
In a first aspect, the present invention provides a kind of album picture Classified optimization method, comprise the following steps：
Image similarity identification is carried out to each picture of system photograph album, determines the similarity between image feature data in default phase
Like the multigroup picture in the range of degree, and multigroup picture is stored to the other temporary folder of respective sets respectively；
All pictures in each temporary folder carry out image definition identification, according to described image characteristic difference
Mark the picture less than predetermined definition；
Labeled picture and synchronous updating system photograph album is deleted according to predetermined set or user instruction.
With reference in a first aspect, in the first implementation of first aspect, also including：
Construction includes the catalogue relation between all pictures that the temporary folder and each temporary folder are included
Index, the index is shown to be visualized in response to user's call instruction.
With reference in a first aspect, in second implementation of first aspect, also including following previous step：
Receive the triggering command of classification each picture of photograph album of user input.
With reference in a first aspect, in the third implementation of first aspect, the characteristic at least includes following
Meaning is a kind of or any various：
The Hash codes of whole picture file, rotate insensitive data, definition characteristic and overall profile data.
It is described to respectively facing in the 4th kind of implementation of first aspect with reference to the third implementation of first aspect
When file in all pictures carry out image definition identification, marked respectively less than predetermined according to described image characteristic
In the step of picture of definition, specifically include：
Decoding Analysis are carried out to the picture, the definition characteristic of the picture is extracted；
When the definition characteristic is less than predetermined threshold value, then the picture is marked automatically.
It is described that figure is carried out to each picture of system photograph album with reference in a first aspect, in the 5th kind of implementation of first aspect
As similarity identification, determine that multigroup picture of the similarity between image feature data in default similarity dimensions is specifically included：
The characteristic of each picture is extracted, the characteristic is contrasted with the characteristic of reference picture, it is determined that
Similarity between the characteristic of each picture and the characteristic of the reference picture；
Each similarity for determining is contrasted with default minimum similarity degree threshold value, by similarity more than or equal to this most
The picture of small similarity threshold is classified as the same packet of the reference picture, according to the multiple packets of multiple reference pictures packet.
It is described with reference to figure in the 6th kind of implementation of first aspect with reference to the 5th kind of implementation of first aspect
Piece is the picture for being randomly selected from album picture or being selected according to certain order, when comparing similarity every time, for a ginseng
Examine picture to be compared, all pictures close therewith and the reference picture are divided into same group, subsequently only to remaining picture
Classified according to similarity, until all picture classifications are finished.
It is described according to predetermined set or user instruction with reference in a first aspect, in the 7th kind of implementation of first aspect
In the step of deleting labeled picture and synchronous updating system photograph album, specifically include：
The quantity of the picture according to the described each packet for pre-setting, deletes labeled picture according to similarity automatically,
And the relatively low picture of similarity is preferentially deleted, the quantity is not delete the transformation of picture；
Or receiving the instruction screened to the picture of user input, the picture labeled to each packet is carried out
Delete.
With reference to the 7th kind of implementation of first aspect, in the 8th kind of implementation of first aspect, to described each point
When the labeled picture of group is deleted, when the picture number of the temporary folder is less than the described each packet for pre-setting
During the quantity of picture, terminate the deletion action.
With reference in a first aspect, in the 9th kind of implementation of first aspect, receiving the setting implemented for specific cluster
The setting of the packet picture number, sets the maximum of picture number in the packet, when picture number exceedes this in temporary folder
During maximum, it is automatically deleted the relatively low picture of wherein similarity to meet the constraint of the maximum.
With reference to the first implementation of first aspect, in the tenth kind of implementation of first aspect, the visualization
With in the step of being shown in the form of photograph album folder structure when showing the temporary folder, the preview of each temporary folder
Picture is shown with the preview graph of a wherein pictures.
Second aspect, the present invention provides a kind of album picture Classified optimization method, comprises the following steps：
Similarity identification module, for carrying out image similarity identification to each picture of system photograph album, determines characteristics of image number
According to multigroup picture of the similarity in default similarity dimensions, and multigroup picture is stored other to respective sets respectively
Temporary folder；
Definition identification module, image definition identification, foundation are carried out for all pictures in each temporary folder
Described image characteristic marks the picture less than predetermined definition respectively；
Optimization module, for deleting labeled picture and synchronous updating system phase according to predetermined set or user instruction
Volume.
With reference to second aspect, in the first implementation of second aspect, also include：
Display module, between all pictures included comprising the temporary folder and each temporary folder for construction
Catalogue relation index, to visualize in response to user's call instruction the display index.
With reference to second aspect, in second implementation of second aspect, also include：
Trigger module, the triggering command of the classification each picture of photograph album for receiving user input.
With reference to second aspect, in the third implementation of second aspect, the characteristic at least includes following
Meaning is a kind of or any various：
The Hash codes of whole picture file, rotate insensitive data, definition characteristic and overall profile data.
With reference to the third implementation of second aspect, in the 4th kind of implementation of second aspect, the definition
In identification module, specifically include：
Extraction unit, for carrying out Decoding Analysis to the picture, extracts the definition characteristic of the picture；
Indexing unit, for when the definition characteristic is less than predetermined threshold value, then marking the picture automatically.
With reference to second aspect, in the 5th kind of implementation of second aspect, specifically wrapped in the similarity identification module
Include：
Comparison unit, the characteristic for extracting each picture, by the characteristic and the characteristic of reference picture
Contrasted, determined the similarity between the characteristic of each picture and the characteristic of the reference picture；
Grouped element, for each similarity for determining to be contrasted with default minimum similarity degree threshold value, by similarity
The same packet of the reference picture is classified as more than or equal to the picture of the minimum similarity degree threshold value, is grouped according to multiple reference pictures
Multiple packet.
It is described with reference to figure in the 6th kind of implementation of second aspect with reference to the 5th kind of implementation of second aspect
Piece is the picture for being randomly selected from album picture or being selected according to certain order, when comparing similarity every time, for a ginseng
Examine picture to be compared, all pictures close therewith and the reference picture are divided into same group, subsequently only to remaining picture
Classified according to similarity, until all picture classifications are finished.
With reference to second aspect, in the 7th kind of implementation of second aspect, in the optimization module, specifically include：
The quantity of the picture according to the described each packet for pre-setting, deletes labeled picture according to similarity automatically,
And the relatively low picture of similarity is preferentially deleted, the quantity is not delete the transformation of picture；
Or receiving the instruction screened to the picture of user input, the picture labeled to each packet is carried out
Delete.
With reference to the 7th kind of implementation of second aspect, in the 8th kind of implementation of second aspect, to described each point
When the labeled picture of group is deleted, when the picture number of the temporary folder is less than the described each packet for pre-setting
During the quantity of picture, terminate the deletion action.
With reference to second aspect, in the 9th kind of implementation of second aspect, the setting implemented for specific cluster is received
The setting of the packet picture number, sets the maximum of picture number in the packet, when picture number exceedes this in temporary folder
During maximum, it is automatically deleted the relatively low picture of wherein similarity to meet the constraint of the maximum.
With reference to the first implementation of second aspect, in the tenth kind of implementation of second aspect, the display mould
In block, the preview picture of each temporary folder is shown with the preview graph of a wherein pictures.
The third aspect, the present invention provides a kind of mobile terminal, including：
Touch-sensitive display, for showing user interface, realizes man-machine interaction；
One or more processors；
Memory；
One or more application programs, wherein one or more of application programs are stored in the memory and quilt
It is configured to by one or more of computing devices；
One or more of programs perform above-mentioned first party for driving one or more of processors to be configured to
The module of the method in face.
Relative to prior art, technical scheme at least possesses following advantage：
The present invention proposes a kind of photograph album Classified optimization method and its corresponding device, and image phase is carried out by album picture
Be divided into one group with by close picture like degree identification, then it is carried out image definition identification with will shoot unintelligible quality compared with
Poor picture is deleted, so as to realize to the automatic Classified optimization of terminal album picture and management.
Can realize that the picture in automatic phasing volume is managed by implementation of the invention, quickly can clear up in photograph album
The not good fuzzy photo of quality, improves the efficiency of management.Picture particularly in shooting process in time to current shooting is carried out
Analyzing and processing so that the picture being stored in during shooting in photograph album is all high-quality picture, it is to avoid underproof picture is stored in into phase
Memory space is taken in volume, is deleted manually one by one from photograph album again after the completion of being shot without user, improve efficiency, improved
Consumer's Experience.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to that will make needed for embodiment description
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for
For those skilled in the art, on the premise of not paying creative work, can also obtain other attached according to these accompanying drawings
Figure.
Fig. 1 is a kind of FB(flow block) of photograph album Classified optimization embodiment of the method one of the invention；
Fig. 2 is a kind of FB(flow block) of photograph album Classified optimization embodiment of the method two of the invention；
Fig. 3 is a kind of structural representation of photograph album Classified optimization device embodiment one of the invention；
Fig. 4 is a kind of structural representation of photograph album Classified optimization device embodiment two of the invention；
Fig. 5 is a kind of mobile terminal part-structure block diagram of the invention.
Specific embodiment
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention
Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention.
In some flows of description in description and claims of this specification and above-mentioned accompanying drawing, contain according to
Multiple operations of particular order appearance, but it should be clearly understood that these operations can not be according to the suitable of its appearance herein
Sequence is performed or executed in parallel, and sequence number such as S11, S12 of operation etc. be only used for distinguishing each different operation, sequence number
Any execution sequence is not represented for itself.In addition, these flows can include more or less operation, and these operations can
To perform in order or executed in parallel.It should be noted that " first ", " second " herein etc. describes, it is for distinguishing not
Same message, equipment, module etc., does not represent sequencing, and it is different types also not limit " first " and " second ".
It will appreciated by the skilled person that unless expressly stated, singulative " " used herein, " one
It is individual ", " described " and " being somebody's turn to do " may also comprise plural form.It is to be further understood that what is used in specification of the invention arranges
Diction " including " refer to the presence of the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their group.It should be understood that when we claim unit
Part is " connected " or during " coupled " to another element, and it can be directly connected or coupled to other elements, or can also exist
Intermediary element.Additionally, " connection " used herein or " coupling " can include wireless connection or wireless coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes or any cell of listing item and all combines.
It will appreciated by the skilled person that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), with art of the present invention in those of ordinary skill general understanding identical meaning.Should also
Understand, those terms defined in such as general dictionary, it should be understood that with the context with prior art
The consistent meaning of meaning, and unless by specific definitions as here, will not otherwise use idealization or excessively formal implication
To explain.
Cloud photograph album sorting technique of the present invention is primarily adapted for use in intelligent mobile phone terminal or Intelligent flat terminal etc. to be had
The terminal of communication function, is not restricted to the type of its operating system, can be the operating systems such as Android, IOS, WP, Saipan.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, wherein same or similar label represents same or similar element or with same or like function from start to finish
Element.Obviously, described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, the every other implementation that those skilled in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Fig. 1 is referred to, in a kind of photograph album Classified optimization method provided by the present invention, in a kind of specific implementation method,
Specifically include following steps：
S11, image similarity identification is carried out to each picture of system photograph album, determine the similarity between image feature data pre-
If the multigroup picture in similarity dimensions, and multigroup picture is stored to the other temporary folder of respective sets respectively.
Preferably following scheme of the invention carries out similarity identification to each picture of photograph album：
One, the characteristic for extracting each picture, the characteristic is contrasted with the characteristic of reference picture,
Determine the similarity between the characteristic of each picture and the characteristic of the reference picture.
The characteristic at least Hash codes including whole picture file, the insensitive data of rotation, definition characteristic
According to and overall profile data.Wherein, the Hash codes are used to recognize duplicate image；The insensitive data of the anglec of rotation are used for
Anti-rotation, mirror image；Definition characteristic is used to weigh picture clarity；Overall profile data are used for anti-edged, obscure, and make an uproar
Point, watermark, slight PS.Extract after the characteristic, a synthesis is obtained after the characteristic is carried out into complex calculation
Similarity, carry out the classification of picture by contrasting the comprehensive similarity.
Preferably, the reference picture is to be randomly selected from album picture or according to certain order such as shooting time order
Selected picture, when carrying out similarity-rough set every time, is contrasted according to the different reference pictures chosen, and a reference picture is made
It is a Comparison of standards picture for packet, all pictures close with the reference picture is divided into same group, according to similar side
Method, remaining picture is classified according to similarity, until all picture classifications are finished.
Certainly, skilled person will appreciate that, the characteristic is not limited only to above-mentioned each characteristic, and it can also be
The Local textural feature data of the data of other representative picture features such as picture.
In a kind of possible design, the characteristic is the Local textural feature data of picture, during classification, according to texture
Feature i.e. LBP algorithms of being classified are classified to the characteristic.
The general principle of the algorithm is the angle from texture to be analyzed, i.e., the textural characteristics of certain pixel on image, greatly
It refer in most cases the relation put in the relation of this point and surrounding pixel point, i.e. this point and its field.From which angle
Degree extracts feature to this relation, is formed different types of characteristic information.Having characteristic information can just be carried out according to texture
Classification.LBP constructs a kind of relation for weighing a pixel and its surrounding pixel point.
From the general principle of above-mentioned LBP algorithms, can be by extracting certain local each pixel of each picture in photograph album
Textural characteristics be each pixel and surrounding pixel point relation i.e. LBP values, each LBP values for extracting constitute a representative image
The N-dimensional vector of local feature, when comparing similarity, similarity-rough set is carried out by the N-dimensional vector, so as to realize picture feature data
Extraction and picture classification.
Secondly, by determine each similarity contrasted with default minimum similarity degree threshold value, by similarity be more than or wait
The same packet of the reference picture is classified as in the picture of the minimum similarity degree threshold value, according to multiple points of multiple reference pictures packet
Group.
The characteristic of each picture calculated according to previous step and the similarity of the characteristic of the reference picture, will
Each similarity is compared with a default minimum similarity degree threshold value, and similarity is more than or equal into the minimum similarity degree
The picture of threshold value is classified as the same packet of the reference picture, and the characteristic is closer to the similarity of its two pictures is bigger.
In a kind of possible design, calculate two similarities of characteristic and calculated by measuring similarity function.
The similarity measurements flow function is used to weigh the similitude between the characteristic that different pictures are extracted.The similarity measurement letter
Number includes：Vector space cosine similarity, Pearson correlation coefficients, adjustment cosine similarity etc..
The textural characteristics of certain local each pixel of each picture are each pixel and week in the characteristic is photograph album
Enclose the relation of pixel i.e. LBP values when, can extract multiple LBP values for each pictures, the multiple LBP values constitute one
Represent the N-dimensional vector of the picture local feature.Preferably, can be by calculating the cosine value of the angle of described two N-dimensionals vector
To determine the similarity of two pictures of correspondence.
Specifically, multiple characteristics such as LBP values are extracted to each picture file constitutes a feature for representing the picture
Vector, when similarity is contrasted, it is only necessary to calculate the cosine value of the characteristic vector angle of any two picture.Such as picture text
The characteristic vector of part A is A (A1, A2 ... ..An), and the characteristic vector of picture file B is B (B1, B2 ... .Bn), wherein
A1...An and B1 ... .Bn be correspondence picture locally in each region each pixel LBP values.According to similarity measurements flow function
Wherein, molecule is two dot products of vector, and | | A | | is the length of vector, from formula, with the change of angle
, the included angle cosine span is [- 1,1].Vectorial angle cosine value then represents two similarities of vector.More than angle
String it is bigger represent two pictures similarity it is bigger, and cosine value it is bigger when two vectors angle it is smaller, conversely, two vectors
Angle it is bigger.When two directions of vector overlap, included angle cosine takes maximum 1, now, represents two pictures just the same.
According to above-mentioned similarity identification principle of classification, the picture of each packet will be stored in temporary file after each picture classification
Press from both sides for subsequently carrying out screening arrangement.
S12, to each temporary folder in all pictures carry out image definition identification, according to described image characteristic
The picture less than predetermined definition is marked respectively.
Preferably, the step of all pictures during the present invention is to each temporary folder carry out image definition and recognize and mark
It is as follows：
First, Decoding Analysis are carried out to the picture, the definition characteristic of the picture is extracted；
Decoding Analysis are carried out to picture, the definition characteristic of picture is obtained, its implementation can be by hardware solution
By the way of code (carrying out hard decoder using dsp chip), speed is fast, it would however also be possible to employ the mode of software decoding, i.e., using existing
Algorithm carry out Decoding Analysis.
Picture clarity as image procossing and an important indicator of identification, in embodiments of the present invention, using figure
Defined as evaluation function.For example, the evaluation function of frequency characteristic of field can be based on, i.e., Fourier transform is realized by algorithm, profit
The evaluation to image definition is realized with frequency spectrum function, image definition characteristic is obtained.The portion of techniques is more existing, no
Repeat again.
2nd, when the definition characteristic is less than predetermined threshold value, then the picture is marked automatically.
User can such as directly input corresponding numerical value, or specify a reference picture, terminal with self-defined setting threshold value
Automatically the definition characteristic value of the reference picture is obtained and as threshold value.If less than predetermined threshold value, the picture is illustrated
Definition is relatively low, undesirable, then be marked the picture；If it exceeds predetermined threshold value, illustrates the definition of the picture
Meet the requirements, then the picture is not processed, retain the picture.
In a kind of possible design, predetermined threshold value can set two or more, such as set the first predetermined threshold value and the
Two predetermined threshold values, and the first predetermined threshold value is less than the second predetermined threshold value.When the definition characteristic of picture is preset less than first
During threshold value, then the picture is automatically deleted；When the definition characteristic of picture is between the first predetermined threshold value and the second predetermined threshold value
Between when, then point out user delete the picture；When definition is more than the second predetermined threshold value, then retain the picture.
S13, the picture and synchronous updating system photograph album that are labeled according to predetermined set or user instruction deletion.
When the definition for finding picture is undesirable, terminal can be automatically deleted picture, save memory space.Or
Person, or user perform the one-touch deletion labeled picture by a button in terminal.Or, it is also possible to
Prompting user's deletion picture, such as pop-up dialogue box, are asked the user whether to delete, and the picture is deleted if user's selection is, if with
Family selection otherwise retains the picture.
Specifically, the present invention is deleted the labeled picture by following two modes：
The quantity of the picture of described each packet that one, basis pre-set, deletes what is be labeled according to similarity automatically
Picture, and the relatively low picture of preferential deletion similarity, the quantity is not delete the transformation of picture；
For each temporary folder, user can with sets itself its retain number of photos number and its title, set
Each file is retained after the quantity of picture, can perform the operation that one-touch automatic batch is arranged.This programme is to each packet
When labeled picture is deleted, when the picture number of the temporary folder is less than the figure of the described each packet for pre-setting
During the quantity of piece, terminate the deletion action, screening and arrangement to each file picture are completed, preferentially by poor image quality
Picture is all weeded out automatically.
Secondly, receive the instruction screened to the picture of user input, the picture labeled to each packet
Deleted.
User can perform the one-touch deletion labeled picture, it is also possible to which reception is directed to by the button in terminal
The setting for setting the packet picture number that specific cluster is implemented, sets the maximum of picture number in the packet, works as temporary file
When picture number exceedes the maximum in folder, it is automatically deleted the relatively low picture of wherein similarity to meet the constraint of the maximum.
Fig. 2 is referred to, in another embodiment of the present invention, is also used to receive user input including a step S10
Classification each picture of photograph album triggering command.
Terminal can carry out Classified optimization when meeting pre-conditioned to album picture, such as carry out once at regular intervals
Picture number in optimization and collation, photograph album carries out the picture newly-increased quantity in optimization and collation, a photograph album when reaching default number
Reaching default number carries out optimization and collation etc.；User can also at any time issue instruction starting guide and arrange.The photograph album
It, for storing the memory space of photo (including picture) (such as file), can be the photograph album of terminal local to refer to.
In a kind of possible application scenarios, the editing interface that user enters picture library photograph album (means that user is intended for editor
The operation of class, so now carrying out image recognition for optimal scene), user actively initiates the operation that intelligent batch arranges photo,
After system receives housekeeping instruction, system is identified packet according to image recognition technology, and similarity is met into default constraint bar
The picture of part builds up several temporary folders and completes classification, photo opporunity point, geographical position can be also combined if necessary it is entered
One step is grouped.Temporary folder is set up into, has both facilitated the image traversal in single file folder, be also convenient for user and manually sieved
Choosing.
Please continue to refer to Fig. 2, in another embodiment, also it is used to construct comprising the interim text including a step S14
The index of the catalogue relation between all pictures that part is pressed from both sides and each temporary folder is included, with response to user's call instruction
Visualization shows the index.
Each packet is well built up several temporary folders by each picture classification by terminal afterwards, and is constructed comprising described
The index of the catalogue relation between all pictures that temporary folder and each temporary folder are included, calls with response to user
Instruct and visualize and show the index.It is described index by it is a kind of be easy to user search in the way of be shown in user interface.Wherein, institute
The preview picture of each temporary folder is stated to be shown with the preview graph of a wherein pictures.
Specifically, the front cover of the picture equivalent to file of top is stacked in the temporary folder, can be from figure
One is randomly choosed in piece as front cover, it is also possible to specify one as front cover by user.The display format of the file can
With different from other single photos, such as so that frame is highlighted, frame fillet form is shown.And also can be in the file
The picture number in temporary folder is marked on folder, such as picture number is shown in the temporary folder lower right corner.When user's point
When hitting the temporary folder, then the picture in the group is launched automatically, so treatment causes that the picture shown in photograph album is simpler
Single clear, user more facilitates when checking picture.
With reference to shown in Fig. 3, in order to be further illustrated to photograph album Classified optimization method of the present invention, mould is carried out to it
A kind of blockization explanation, there is provided photograph album Classified optimization device, in a kind of embodiment, including similarity identification module 11, definition is known
Other module 12, optimization module 13, in addition in embodiment as shown in Figure 4, the device also includes trigger module 10 and display module 14.
Wherein,
Similarity identification module 11：For carrying out image similarity identification to each picture of system photograph album, characteristics of image is determined
The multigroup picture of similarity between data in default similarity dimensions, and multigroup picture is stored to corresponding group respectively
Temporary folder.
Preferably following scheme of the invention carries out similarity identification to each picture of photograph album：
Comparison unit：Characteristic for extracting each picture, by the characteristic and the characteristic of reference picture
Contrasted, determined the similarity between the characteristic of each picture and the characteristic of the reference picture.
The characteristic at least Hash codes including whole picture file, the insensitive data of rotation, definition characteristic
According to and overall profile data.Wherein, the Hash codes are used to recognize duplicate image；The insensitive data of the anglec of rotation are used for
Anti-rotation, mirror image；Definition characteristic is used to weigh picture clarity；Overall profile data are used for anti-edged, obscure, and make an uproar
Point, watermark, slight PS.Extract after the characteristic, a synthesis is obtained after the characteristic is carried out into complex calculation
Similarity, carry out the classification of picture by contrasting the comprehensive similarity.
Preferably, the reference picture is to be randomly selected from album picture or according to certain order such as shooting time order
Selected picture, when carrying out similarity-rough set every time, is contrasted according to the different reference pictures chosen, and a reference picture is made
It is a Comparison of standards picture for packet, all pictures close with the reference picture is divided into same group, according to similar side
Method, remaining picture is classified according to similarity, until all picture classifications are finished.
Certainly, skilled person will appreciate that, the characteristic is not limited only to above-mentioned each characteristic, and it can also be
The Local textural feature data of the data of other representative picture features such as picture.
In a kind of possible design, the characteristic is the Local textural feature data of picture, during classification, according to texture
Feature i.e. LBP algorithms of being classified are classified to the characteristic.
The general principle of the algorithm is the angle from texture to be analyzed, i.e., the textural characteristics of certain pixel on image, greatly
It refer in most cases the relation put in the relation of this point and surrounding pixel point, i.e. this point and its field.From which angle
Degree extracts feature to this relation, is formed different types of characteristic information.Having characteristic information can just be carried out according to texture
Classification.LBP constructs a kind of relation for weighing a pixel and its surrounding pixel point.
From the general principle of above-mentioned LBP algorithms, can be by extracting certain local each pixel of each picture in photograph album
Textural characteristics be each pixel and surrounding pixel point relation i.e. LBP values, each LBP values for extracting constitute a representative image
The N-dimensional vector of local feature, when comparing similarity, similarity-rough set is carried out by the N-dimensional vector, so as to realize picture feature data
Extraction and picture classification.
Grouped element：For each similarity for determining to be contrasted with default minimum similarity degree threshold value, by similarity
The same packet of the reference picture is classified as more than or equal to the picture of the minimum similarity degree threshold value, is grouped according to multiple reference pictures
Multiple packet.
The characteristic of each picture calculated according to previous step and the similarity of the characteristic of the reference picture, will
Each similarity is compared with a default minimum similarity degree threshold value, and similarity is more than or equal into the minimum similarity degree
The picture of threshold value is classified as the same packet of the reference picture, and the characteristic is closer to the similarity of its two pictures is bigger.
In a kind of possible design, calculate two similarities of characteristic and calculated by measuring similarity function.
The similarity measurements flow function is used to weigh the similitude between the characteristic that different pictures are extracted.The similarity measurement letter
Number includes：Vector space cosine similarity, Pearson correlation coefficients, adjustment cosine similarity etc..
The textural characteristics of certain local each pixel of each picture are each pixel and week in the characteristic is photograph album
Enclose the relation of pixel i.e. LBP values when, can extract multiple LBP values for each pictures, the multiple LBP values constitute one
Represent the N-dimensional vector of the picture local feature.Preferably, can be by calculating the cosine value of the angle of described two N-dimensionals vector
To determine the similarity of two pictures of correspondence.
Specifically, multiple characteristics such as LBP values are extracted to each picture file constitutes a feature for representing the picture
Vector, when similarity is contrasted, it is only necessary to calculate the cosine value of the characteristic vector angle of any two picture.Such as picture text
The characteristic vector of part A is A (A1, A2 ... ..An), and the characteristic vector of picture file B is B (B1, B2 ... .Bn), wherein
A1...An and B1 ... .Bn be correspondence picture locally in each region each pixel LBP values.According to similarity measurements flow function
Wherein, molecule is two dot products of vector, and | | A | | is the length of vector, from formula, with the change of angle
, the included angle cosine span is [- 1,1].Vectorial angle cosine value then represents two similarities of vector.More than angle
String it is bigger represent two pictures similarity it is bigger, and cosine value it is bigger when two vectors angle it is smaller, conversely, two vectors
Angle it is bigger.When two directions of vector overlap, included angle cosine takes maximum 1, now, represents two pictures just the same.
According to above-mentioned similarity identification principle of classification, the picture of each packet will be stored in temporary file after each picture classification
Press from both sides for subsequently carrying out screening arrangement.
Definition identification module 12：Image definition identification is carried out for all pictures in each temporary folder, according to
The picture less than predetermined definition is marked respectively according to described image characteristic.
Preferably, the step of all pictures during the present invention is to each temporary folder carry out image definition and recognize and mark
It is as follows：
Extraction unit：For carrying out Decoding Analysis to the picture, the definition characteristic of the picture is extracted；
Decoding Analysis are carried out to picture, the definition characteristic of picture is obtained, its implementation can be by hardware solution
By the way of code (carrying out hard decoder using dsp chip), speed is fast, it would however also be possible to employ the mode of software decoding, i.e., using existing
Algorithm carry out Decoding Analysis.
Picture clarity as image procossing and an important indicator of identification, in embodiments of the present invention, using figure
Defined as evaluation function.For example, the evaluation function of frequency characteristic of field can be based on, i.e., Fourier transform is realized by algorithm, profit
The evaluation to image definition is realized with frequency spectrum function, image definition characteristic is obtained.The portion of techniques is more existing, no
Repeat again.
Indexing unit：For when the definition characteristic is less than predetermined threshold value, then marking the picture automatically.
User can such as directly input corresponding numerical value, or specify a reference picture, terminal with self-defined setting threshold value
Automatically the definition characteristic value of the reference picture is obtained and as threshold value.If less than predetermined threshold value, the picture is illustrated
Definition is relatively low, undesirable, then be marked the picture；If it exceeds predetermined threshold value, illustrates the definition of the picture
Meet the requirements, then the picture is not processed, retain the picture.
In a kind of possible design, predetermined threshold value can set two or more, such as set the first predetermined threshold value and the
Two predetermined threshold values, and the first predetermined threshold value is less than the second predetermined threshold value.When the definition characteristic of picture is preset less than first
During threshold value, then the picture is automatically deleted；When the definition characteristic of picture is between the first predetermined threshold value and the second predetermined threshold value
Between when, then point out user delete the picture；When definition is more than the second predetermined threshold value, then retain the picture.
Optimization module 13：For deleting labeled picture and synchronous updating system phase according to predetermined set or user instruction
Volume.
When the definition for finding picture is undesirable, terminal can be automatically deleted picture, save memory space.Or
Person, or user perform the one-touch deletion labeled picture by a button in terminal.Or, it is also possible to
Prompting user's deletion picture, such as pop-up dialogue box, are asked the user whether to delete, and the picture is deleted if user's selection is, if with
Family selection otherwise retains the picture.
Specifically, the present invention is deleted the labeled picture by following two modes：
The quantity of the picture of described each packet that one, basis pre-set, deletes what is be labeled according to similarity automatically
Picture, and the relatively low picture of preferential deletion similarity, the quantity is not delete the transformation of picture；
For each temporary folder, user can with sets itself its retain number of photos number and its title, set
Each file is retained after the quantity of picture, can perform the operation that one-touch automatic batch is arranged.This programme is to each packet
When labeled picture is deleted, when the picture number of the temporary folder is less than the figure of the described each packet for pre-setting
During the quantity of piece, terminate the deletion action, screening and arrangement to each file picture are completed, preferentially by poor image quality
Picture is all weeded out automatically.
Secondly, receive the instruction screened to the picture of user input, the picture labeled to each packet
Deleted.
User can perform the one-touch deletion labeled picture, it is also possible to which reception is directed to by the button in terminal
The setting for setting the packet picture number that specific cluster is implemented, sets the maximum of picture number in the packet, works as temporary file
When picture number exceedes the maximum in folder, it is automatically deleted the relatively low picture of wherein similarity to meet the constraint of the maximum.
Fig. 4 is refer to, it is in another embodiment of the present invention, also defeated for receiving user including a trigger module 10
The triggering command of the classification each picture of photograph album for entering.
Terminal can carry out Classified optimization when meeting pre-conditioned to album picture, such as carry out once at regular intervals
Picture number in optimization and collation, photograph album carries out the picture newly-increased quantity in optimization and collation, a photograph album when reaching default number
Reaching default number carries out optimization and collation etc.；User can also at any time issue instruction starting guide and arrange.The photograph album
It, for storing the memory space of photo (including picture) (such as file), can be the photograph album of terminal local to refer to.
In a kind of possible application scenarios, the editing interface that user enters picture library photograph album (means that user is intended for editor
The operation of class, so now carrying out image recognition for optimal scene), user actively initiates the operation that intelligent batch arranges photo,
After system receives housekeeping instruction, system is identified packet according to image recognition technology, and similarity is met into default constraint bar
The picture of part builds up several temporary folders and completes classification, photo opporunity point, geographical position can be also combined if necessary it is entered
One step is grouped.This programme takes the form for setting up temporary folder, has both facilitated the image traversal in single file folder, is also convenient for using
Family carries out artificial screening.
Please continue to refer to Fig. 4, in another embodiment, also it is used to construct comprising described interim including a display module 14
The index of the catalogue relation between all pictures that file and each temporary folder are included, with response to user's call instruction
And visualize and show the index.
Each packet is well built up several temporary folders by each picture classification by terminal afterwards, and is constructed comprising described
The index of the catalogue relation between all pictures that temporary folder and each temporary folder are included, calls with response to user
Instruct and visualize and show the index.It is described index by it is a kind of be easy to user search in the way of be shown in user interface.Wherein, institute
The preview picture of each temporary folder is stated to be shown with the preview graph of a wherein pictures.
Specifically, the front cover of the picture equivalent to file of top is stacked in the temporary folder, can be from figure
One is randomly choosed in piece as front cover, it is also possible to specify one as front cover by user.The display format of the file can
With different from other single photos, such as so that frame is highlighted, frame fillet form is shown.And also can be in the file
The picture number in temporary folder is marked on folder, such as picture number is shown in the temporary folder lower right corner.When user's point
When hitting the temporary folder, then the picture in the group is launched automatically, so treatment causes that the picture shown in photograph album is simpler
Single clear, user more facilitates when checking picture.
Understood with reference to the above embodiments, the maximum effect of the present invention is that the present invention proposes a kind of photograph album Classified optimization
Method and its corresponding device, one group is divided into by carrying out image similarity identification to album picture with by close picture；
Image definition identification is carried out to it again, especially by the definition feature of the picture in the picture or photograph album that obtain current shooting
Data, are estimated according to definition characteristic to the definition of picture, for the undesirable picture of definition, then from
It is dynamic to delete or prompting user's deletion.It is achieved thereby that the picture in automatic phasing volume is managed, quickly can clear up in photograph album
The not good blurred picture of quality, improves the efficiency of management.
Picture particularly in shooting process in time to current shooting is analyzed treatment so that photograph album is stored in during shooting
In picture be all high-quality picture, it is to avoid underproof picture is stored in photograph album and memory space is taken, without user
Deleted manually one by one from photograph album again after the completion of shooting, improve efficiency, improve Consumer's Experience.Simultaneously by by same background
Lower captured picture and similar picture carry out packet display and set up temporary folder so that picture can be in photograph album more
Simple and clear displaying, facilitates user to check in the future and be managed to similar picture, such as deletes part picture and retains shooting
The relatively good photo of effect.
The embodiment of the present invention also provides one kind a kind of mobile terminal, as shown in figure 5, for convenience of description, illustrate only
The part related to the embodiment of the present invention, particular technique details is not disclosed, and refer to embodiment of the present invention cloud photograph album classification side
Method part.The terminal can be to include mobile phone, panel computer, PDA (Personal Digital Assistant, individual digital
Assistant), POS (Point of Sales, point-of-sale terminal), any terminal device such as vehicle-mounted computer, so that terminal is as mobile phone as an example：
Fig. 5 is illustrated that the block diagram of the part-structure of the mobile phone related to terminal provided in an embodiment of the present invention.With reference to figure
5, mobile phone includes：The parts such as touch-sensitive display 0513, processor 0511, memory 0514.It will be understood by those skilled in the art that
The handset structure shown in Fig. 5 does not constitute the restriction to mobile phone, can include than illustrating more or less part, or group
Close some parts, or different part arrangements.
Each component parts of mobile phone is specifically introduced with reference to Fig. 5：
Memory 0514 can be used to store software program and module, and processor 0511 is by running storage in memory
0514 software program and module, so as to perform various function application and the data processing of mobile phone.Memory 0514 can be led
To include storing program area and storage data field, wherein, storing program area can be needed for storage program area, at least one function
Application program (such as sound-playing function, image player function etc.) etc.；Storage data field can store the use institute according to mobile phone
Data (such as voice data, phone directory etc.) of establishment etc..Additionally, memory 0514 can be stored including high random access
Device, can also include nonvolatile memory, and for example, at least one disk memory, flush memory device or other volatibility are consolidated
State memory device.
Touch-sensitive display 0513 may include two parts of touch detecting apparatus and touch controller.Wherein, touch detection dress
The touch orientation of detection user is put, and detects the signal that touch operation brings, transmit a signal to touch controller；Touch control
Device receives touch information from touch detecting apparatus, and is converted into contact coordinate, then gives processor, and can reception processing
Order that device is sent simultaneously is performed.Furthermore, it is possible to using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves
Type realizes touch-sensitive display.
Touch-sensitive display 0513 can be used to showing by user input information or be supplied to the information and mobile phone of user
Various menus, such as information editing interface.Touch-sensitive display 0513 may include display panel, optionally, can use liquid crystal
Show device (Liquid Crystal Display, LCD), Organic Light Emitting Diode (Organic Light-Emitting Diode,
) etc. OLED form configures touch-sensitive display.Further, when touch-sensitive display 0513 is detected thereon or neighbouring touch
After operation, processor is sent to determine the type of touch event, shown touch-sensitive according to the type of touch event with preprocessor
Is provided and corresponding visual output provided on device.
Mobile phone may also include at least one sensor 0912, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor may include ambient light sensor and proximity transducer, wherein, ambient light sensor can be according to ambient light
Light and shade adjust the brightness of display panel, proximity transducer can close display panel and/or the back of the body when mobile phone is moved in one's ear
Light.As one kind of motion sensor, the size of (generally three axles) acceleration in the detectable all directions of accelerometer sensor,
Size and the direction of gravity are can detect that when static, can be used to recognize application (the such as horizontal/vertical screen switching, related trip of mobile phone attitude
Play, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；As for the gyro that mobile phone can also configure
The other sensors such as instrument, barometer, hygrometer, thermometer, infrared ray sensor, will not be repeated here.
Processor 0511 is the control centre of mobile phone, using various interfaces and the various pieces of connection whole mobile phone,
By running or performing software program and/or module of the storage in memory 0514, and storage is called in memory 0514
Interior data, perform the various functions and processing data of mobile phone, so as to carry out integral monitoring to mobile phone.Optionally, processor
0511 may include one or more processing units；Preferably, processor 0511 can integrated application processor and modulation /demodulation treatment
Device, wherein, application processor mainly processes operating system, user interface and application program etc., and modem processor is mainly located
Reason radio communication.It is understood that above-mentioned modem processor can not also be integrated into processor 0511.
Mobile phone also includes the power supply (such as battery) powered to all parts, it is preferred that power supply can be by power management
System is logically contiguous with processor 0511, so as to realize management charging, electric discharge and power managed etc. by power-supply management system
Function.
Although not shown, mobile phone can also will not be repeated here including camera, bluetooth module etc..
In embodiments of the present invention, the processor 0511 included by the terminal also has following functions：
Image similarity identification is carried out to each picture of system photograph album, determines the similarity between image feature data in default phase
Like the multigroup picture in the range of degree, and multigroup picture is stored to the other temporary folder of respective sets respectively；
All pictures in each temporary folder carry out image definition identification, according to described image characteristic difference
Mark the picture less than predetermined definition；
Labeled picture and synchronous updating system photograph album is deleted according to predetermined set or user instruction.
Construction includes the catalogue relation between all pictures that the temporary folder and each temporary folder are included
Index, the index is shown to be visualized in response to user's call instruction.
Receive the triggering command of classification each picture of photograph album of user input.
Decoding Analysis are carried out to the picture, the definition characteristic of the picture is extracted；
When the definition characteristic is less than predetermined threshold value, then the picture is marked automatically.
The characteristic of each picture is extracted, the characteristic is contrasted with the characteristic of reference picture, it is determined that
Similarity between the characteristic of each picture and the characteristic of the reference picture；
Each similarity for determining is contrasted with default minimum similarity degree threshold value, by similarity more than or equal to this most
The picture of small similarity threshold is classified as the same packet of the reference picture, according to the multiple packets of multiple reference pictures packet.
The reference picture is the picture for being randomly selected from album picture or being selected according to certain order, and phase is compared every time
When seemingly spending, it is compared for a reference picture, all pictures close therewith and the reference picture is divided into same group,
It is follow-up that only remaining picture is classified according to similarity, until all picture classifications are finished.
The quantity of the picture according to the described each packet for pre-setting, deletes labeled picture according to similarity automatically,
And the relatively low picture of similarity is preferentially deleted, the quantity is not delete the transformation of picture；
Or receiving the instruction screened to the picture of user input, the picture labeled to each packet is carried out
Delete.
When the picture labeled to each packet is deleted, when the picture number of the temporary folder is less than advance
During the quantity of the picture of the described each packet for setting, terminate the deletion action.
The setting of the setting packet picture number implemented for specific cluster is received, picture number is most in setting the packet
Big value, when picture number exceedes the maximum in temporary folder, is automatically deleted the relatively low picture of wherein similarity to meet
The constraint of the maximum.
It is described with the step of being shown in the form of photograph album folder structure during the visualization display temporary folder
The preview picture of each temporary folder is shown with the preview graph of a wherein pictures.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the corresponding process in foregoing photograph album Classified optimization embodiment of the method, herein
Repeat no more.
In several embodiments provided herein, it should be understood that disclosed system, device and cloud photograph album are classified
Method, can realize by another way.For example, device embodiment described above is only schematical, for example, institute
State the division of unit, only a kind of division of logic function there can be other dividing mode when actually realizing, such as it is multiple single
Unit or component can be combined or be desirably integrated into another system, or some features can be ignored, or not performed.It is another,
Shown or discussed coupling or direct-coupling or communication connection each other can be by some interfaces, device or unit
INDIRECT COUPLING or communication connection, can be electrical, mechanical or other forms.
The unit that is illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be according to the actual needs selected to realize the mesh of this embodiment scheme
's.
In addition, during each functional unit in each embodiment of the invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.Above-mentioned integrated list
Unit can both be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
One of ordinary skill in the art will appreciate that whole or portion in the various cloud photograph album sorting techniques of above-described embodiment
Program be can be by step by step to instruct the hardware of correlation to complete, the program can be stored in a computer-readable storage medium
In matter, storage medium can include：Read-only storage (ROM, Read Only Memory), random access memory (RAM,
Random Access Memory), disk or CD etc..
One of ordinary skill in the art will appreciate that realizing all or part in above-described embodiment cloud photograph album sorting technique
The hardware that step can be by program to instruct correlation is completed, and described program can be stored in a kind of computer-readable storage
In medium, storage medium mentioned above can be read-only storage, disk or CD etc..
A kind of mobile terminal provided by the present invention is described in detail above, for the general technology people of this area
Member, according to the thought of the embodiment of the present invention, will change in specific embodiments and applications, in sum,
This specification content should not be construed as limiting the invention.
Claims (10)
1. a kind of album picture Classified optimization method, it is characterised in that comprise the following steps：
Image similarity identification is carried out to each picture of system photograph album, determines the similarity between image feature data in default similarity
In the range of multigroup picture, and multigroup picture is stored to the other temporary folder of respective sets respectively；
All pictures in each temporary folder carry out image definition identification, are marked respectively according to described image characteristic
Go out the picture less than predetermined definition；
Labeled picture and synchronous updating system photograph album is deleted according to predetermined set or user instruction.
2. album picture Classified optimization method as claimed in claim 1, it is characterised in that the characteristic at least includes following
Any one is any various：
The Hash codes of whole picture file, rotate insensitive data, definition characteristic and overall profile data.
3. album picture Classified optimization method as claimed in claim 4, it is characterised in that the institute in each temporary folder
Having picture carries out image definition identification, and foundation described image characteristic marks the picture less than predetermined definition respectively
In step, specifically include：
Decoding Analysis are carried out to the picture, the definition characteristic of the picture is extracted；
When the definition characteristic is less than predetermined threshold value, then the picture is marked automatically.
4. album picture Classified optimization method as claimed in claim 1, it is characterised in that described to be carried out to each picture of system photograph album
Image similarity identification, determines that multigroup picture of the similarity between image feature data in default similarity dimensions is specifically wrapped
Include：
The characteristic of each picture is extracted, the characteristic is contrasted with the characteristic of reference picture, determine each figure
Similarity between the characteristic of piece and the characteristic of the reference picture；
Each similarity for determining is contrasted with default minimum similarity degree threshold value, similarity is more than or equal to the minimum phase
The same packet of the reference picture is classified as like the picture of degree threshold value, according to the multiple packets of multiple reference pictures packet.
5. album picture Classified optimization method as claimed in claim 4, it is characterised in that the reference picture is from album picture
In randomly select or according to certain order select picture, when comparing similarity every time, be compared for a reference picture,
All pictures close therewith and the reference picture are divided into same group, subsequently only remaining picture is divided according to similarity
Class, until all picture classifications are finished.
6. album picture Classified optimization method as claimed in claim 1, it is characterised in that described to be referred to according to predetermined set or user
In the step of labeled picture and synchronous updating system photograph album is deleted in order, specifically include：
The quantity of the picture according to the described each packet for pre-setting, deletes labeled picture according to similarity automatically, and excellent
The relatively low picture of similarity is first deleted, the quantity is not delete the transformation of picture；
Or receiving the instruction screened to the picture of user input, the picture labeled to each packet is deleted
Remove.
7. album picture Classified optimization method as claimed in claim 6, it is characterised in that the picture labeled to each packet
When being deleted, when the picture number of the temporary folder is less than the quantity of the picture of the described each packet for pre-setting
When, terminate the deletion action.
8. album picture Classified optimization method as claimed in claim 1, it is characterised in that receive for setting that specific cluster is implemented
The setting of the fixed packet picture number, sets the maximum of picture number in the packet, when picture number surpasses in temporary folder
When crossing the maximum, it is automatically deleted the relatively low picture of wherein similarity to meet the constraint of the maximum.
9. a kind of album picture Classified optimization device, it is characterised in that including：
Similarity identification module, for carrying out image similarity identification to each picture of system photograph album, between determining image feature data
Multigroup picture of the similarity in default similarity dimensions, and multigroup picture is stored other interim to respective sets respectively
File；
Definition identification module, carries out image definition identification, according to described for all pictures in each temporary folder
Image feature data marks the picture less than predetermined definition respectively；
Optimization module, for deleting labeled picture and synchronous updating system photograph album according to predetermined set or user instruction.
10. a kind of mobile terminal, it is characterised in that including：
Touch-sensitive display, for showing user interface, realizes man-machine interaction；
One or more processors；
Memory；
One or more application programs, wherein one or more of application programs are stored in the memory and are configured
It is by one or more of computing devices；
One or more of programs are used to drive one or more of processors to be configured to perform claim requirement 1 to right
It is required that the module of the method in 8 described in any one.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116167.XA CN106777007A (en) | 2016-12-07 | 2016-12-07 | Photograph album Classified optimization method, device and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611116167.XA CN106777007A (en) | 2016-12-07 | 2016-12-07 | Photograph album Classified optimization method, device and mobile terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106777007A true CN106777007A (en) | 2017-05-31 |
Family
ID=58877036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611116167.XA Pending CN106777007A (en) | 2016-12-07 | 2016-12-07 | Photograph album Classified optimization method, device and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106777007A (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107454267A (en) * | 2017-08-31 | 2017-12-08 | 维沃移动通信有限公司 | The processing method and mobile terminal of a kind of image |
| CN107730364A (en) * | 2017-10-31 | 2018-02-23 | 北京麒麟合盛网络技术有限公司 | user identification method and device |
| CN108009277A (en) * | 2017-12-20 | 2018-05-08 | 珠海格力电器股份有限公司 | A kind of image-erasing method and terminal device |
| CN108009280A (en) * | 2017-12-21 | 2018-05-08 | 广东欧珀移动通信有限公司 | Image processing method, device, terminal and storage medium |
| CN108228844A (en) * | 2018-01-09 | 2018-06-29 | 美的集团股份有限公司 | A kind of picture screening technique and device, storage medium, computer equipment |
| CN108536753A (en) * | 2018-03-13 | 2018-09-14 | 腾讯科技（深圳）有限公司 | The determination method and relevant apparatus of duplicate message |
| CN108921204A (en) * | 2018-06-14 | 2018-11-30 | 平安科技（深圳）有限公司 | Electronic device, picture sample set creation method and computer readable storage medium |
| CN109063737A (en) * | 2018-07-03 | 2018-12-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and mobile terminal |
| CN109167937A (en) * | 2018-11-05 | 2019-01-08 | 北京达佳互联信息技术有限公司 | Video distribution method, apparatus, terminal and storage medium |
| WO2019051801A1 (en) * | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and apparatus, computer device, and non-volatile readable storage medium |
| CN109543062A (en) * | 2018-09-29 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Image processing method, system, computer installation and readable storage medium storing program for executing |
| CN110012485A (en) * | 2019-04-10 | 2019-07-12 | 惠州Tcl移动通信有限公司 | A kind of base station classification control method, system, storage medium and mobile terminal |
| WO2019137167A1 (en) * | 2018-01-10 | 2019-07-18 | Oppo广东移动通信有限公司 | Photo album management method and apparatus, storage medium, and electronic device |
| CN110795579A (en) * | 2019-10-29 | 2020-02-14 | Oppo广东移动通信有限公司 | Picture cleaning method and device, terminal and storage medium |
| CN110930302A (en) * | 2018-08-30 | 2020-03-27 | 珠海金山办公软件有限公司 | Picture processing method and device, electronic equipment and readable storage medium |
| CN111046933A (en) * | 2019-12-03 | 2020-04-21 | 东软集团股份有限公司 | Image classification method and device, storage medium and electronic equipment |
| CN111488477A (en) * | 2019-01-25 | 2020-08-04 | 中国科学院半导体研究所 | Album processing method, apparatus, electronic device and storage medium |
| CN111666262A (en) * | 2020-05-28 | 2020-09-15 | 重庆渝抗医药科技有限公司 | Working method for extracting feature points of massive medical images in network attached storage NAS state |
| CN112115285A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Picture cleaning method and device |
| CN112395037A (en) * | 2020-12-07 | 2021-02-23 | 深圳云天励飞技术股份有限公司 | Dynamic cover selection method and device, electronic equipment and storage medium |
| CN112712041A (en) * | 2020-12-31 | 2021-04-27 | 北京华安信联通信技术有限公司 | Photo classification method |
| CN113076284A (en) * | 2021-04-08 | 2021-07-06 | 立臻科技(昆山)有限公司 | Image instant management method, device, equipment and storage medium |
| CN113225451A (en) * | 2021-04-28 | 2021-08-06 | 维沃移动通信（杭州）有限公司 | Image processing method and device and electronic equipment |
| CN113392206A (en) * | 2021-06-17 | 2021-09-14 | 李元烈 | Intelligent editing method for popular culture hot content |
| CN113656615A (en) * | 2021-10-21 | 2021-11-16 | 环球数科集团有限公司 | Intelligent sharing method and device of travel information and computer equipment |
| CN113688850A (en) * | 2020-05-14 | 2021-11-23 | 武汉Tcl集团工业研究院有限公司 | Image processing method and terminal |
| WO2022088834A1 (en) * | 2020-10-26 | 2022-05-05 | 深圳市雷鸟网络传媒有限公司 | Dynamic photograph album generation method, server, display terminal and readable storage medium |
| CN115687677A (en) * | 2022-10-18 | 2023-02-03 | 武汉骏信达信息咨询有限公司 | Data storage management method and system based on artificial intelligence |
| CN116069729A (en) * | 2023-04-06 | 2023-05-05 | 深圳市微克科技有限公司 | Intelligent document packaging method, system and medium |
| CN116383427A (en) * | 2023-06-06 | 2023-07-04 | 深圳市微克科技有限公司 | Picture batch analysis method, system and medium based on intelligent wearable device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216976A (en) * | 2014-09-01 | 2014-12-17 | 广东欧珀移动通信有限公司 | Method and system for viewing pictures of mobile terminal by groups |
| CN104408061A (en) * | 2014-10-29 | 2015-03-11 | 深圳市中兴移动通信有限公司 | Photo album management method and device |
| CN105989599A (en) * | 2015-02-15 | 2016-10-05 | 西安酷派软件科技有限公司 | Image processing method and apparatus, and terminal |
-
2016
- 2016-12-07 CN CN201611116167.XA patent/CN106777007A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104216976A (en) * | 2014-09-01 | 2014-12-17 | 广东欧珀移动通信有限公司 | Method and system for viewing pictures of mobile terminal by groups |
| CN104408061A (en) * | 2014-10-29 | 2015-03-11 | 深圳市中兴移动通信有限公司 | Photo album management method and device |
| CN105989599A (en) * | 2015-02-15 | 2016-10-05 | 西安酷派软件科技有限公司 | Image processing method and apparatus, and terminal |
Cited By (42)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107454267A (en) * | 2017-08-31 | 2017-12-08 | 维沃移动通信有限公司 | The processing method and mobile terminal of a kind of image |
| WO2019051801A1 (en) * | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and apparatus, computer device, and non-volatile readable storage medium |
| US11314803B2 (en) | 2017-09-15 | 2022-04-26 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for image-processing and mobile terminal |
| CN107730364A (en) * | 2017-10-31 | 2018-02-23 | 北京麒麟合盛网络技术有限公司 | user identification method and device |
| CN108009277A (en) * | 2017-12-20 | 2018-05-08 | 珠海格力电器股份有限公司 | A kind of image-erasing method and terminal device |
| CN108009280A (en) * | 2017-12-21 | 2018-05-08 | 广东欧珀移动通信有限公司 | Image processing method, device, terminal and storage medium |
| CN108009280B (en) * | 2017-12-21 | 2021-01-01 | Oppo广东移动通信有限公司 | Picture processing method, device, terminal and storage medium |
| CN108228844A (en) * | 2018-01-09 | 2018-06-29 | 美的集团股份有限公司 | A kind of picture screening technique and device, storage medium, computer equipment |
| CN108228844B (en) * | 2018-01-09 | 2020-10-27 | 美的集团股份有限公司 | Picture screening method and device, storage medium and computer equipment |
| WO2019137167A1 (en) * | 2018-01-10 | 2019-07-18 | Oppo广东移动通信有限公司 | Photo album management method and apparatus, storage medium, and electronic device |
| CN110109878A (en) * | 2018-01-10 | 2019-08-09 | 广东欧珀移动通信有限公司 | Photograph album management method, device, storage medium and electronic equipment |
| CN108536753A (en) * | 2018-03-13 | 2018-09-14 | 腾讯科技（深圳）有限公司 | The determination method and relevant apparatus of duplicate message |
| CN108921204B (en) * | 2018-06-14 | 2023-12-26 | 平安科技（深圳）有限公司 | Electronic device, picture sample set generation method, and computer-readable storage medium |
| CN108921204A (en) * | 2018-06-14 | 2018-11-30 | 平安科技（深圳）有限公司 | Electronic device, picture sample set creation method and computer readable storage medium |
| CN109063737A (en) * | 2018-07-03 | 2018-12-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and mobile terminal |
| CN110930302B (en) * | 2018-08-30 | 2024-03-26 | 珠海金山办公软件有限公司 | Picture processing method and device, electronic equipment and readable storage medium |
| CN110930302A (en) * | 2018-08-30 | 2020-03-27 | 珠海金山办公软件有限公司 | Picture processing method and device, electronic equipment and readable storage medium |
| CN109543062A (en) * | 2018-09-29 | 2019-03-29 | 中国平安人寿保险股份有限公司 | Image processing method, system, computer installation and readable storage medium storing program for executing |
| CN109167937A (en) * | 2018-11-05 | 2019-01-08 | 北京达佳互联信息技术有限公司 | Video distribution method, apparatus, terminal and storage medium |
| CN109167937B (en) * | 2018-11-05 | 2022-10-14 | 北京达佳互联信息技术有限公司 | Video distribution method, device, terminal and storage medium |
| CN111488477A (en) * | 2019-01-25 | 2020-08-04 | 中国科学院半导体研究所 | Album processing method, apparatus, electronic device and storage medium |
| CN110012485A (en) * | 2019-04-10 | 2019-07-12 | 惠州Tcl移动通信有限公司 | A kind of base station classification control method, system, storage medium and mobile terminal |
| CN112115285A (en) * | 2019-06-21 | 2020-12-22 | 杭州海康威视数字技术股份有限公司 | Picture cleaning method and device |
| CN110795579A (en) * | 2019-10-29 | 2020-02-14 | Oppo广东移动通信有限公司 | Picture cleaning method and device, terminal and storage medium |
| CN111046933A (en) * | 2019-12-03 | 2020-04-21 | 东软集团股份有限公司 | Image classification method and device, storage medium and electronic equipment |
| CN111046933B (en) * | 2019-12-03 | 2024-03-05 | 东软集团股份有限公司 | Image classification method, device, storage medium and electronic equipment |
| CN113688850A (en) * | 2020-05-14 | 2021-11-23 | 武汉Tcl集团工业研究院有限公司 | Image processing method and terminal |
| CN111666262A (en) * | 2020-05-28 | 2020-09-15 | 重庆渝抗医药科技有限公司 | Working method for extracting feature points of massive medical images in network attached storage NAS state |
| WO2022088834A1 (en) * | 2020-10-26 | 2022-05-05 | 深圳市雷鸟网络传媒有限公司 | Dynamic photograph album generation method, server, display terminal and readable storage medium |
| CN112395037A (en) * | 2020-12-07 | 2021-02-23 | 深圳云天励飞技术股份有限公司 | Dynamic cover selection method and device, electronic equipment and storage medium |
| CN112712041A (en) * | 2020-12-31 | 2021-04-27 | 北京华安信联通信技术有限公司 | Photo classification method |
| CN112712041B (en) * | 2020-12-31 | 2023-12-01 | 北京华安信联通信技术有限公司 | Photo classification method |
| CN113076284A (en) * | 2021-04-08 | 2021-07-06 | 立臻科技(昆山)有限公司 | Image instant management method, device, equipment and storage medium |
| CN113225451A (en) * | 2021-04-28 | 2021-08-06 | 维沃移动通信（杭州）有限公司 | Image processing method and device and electronic equipment |
| CN113392206A (en) * | 2021-06-17 | 2021-09-14 | 李元烈 | Intelligent editing method for popular culture hot content |
| CN113656615B (en) * | 2021-10-21 | 2021-12-21 | 环球数科集团有限公司 | Intelligent sharing method and device of travel information and computer equipment |
| CN113656615A (en) * | 2021-10-21 | 2021-11-16 | 环球数科集团有限公司 | Intelligent sharing method and device of travel information and computer equipment |
| CN115687677A (en) * | 2022-10-18 | 2023-02-03 | 武汉骏信达信息咨询有限公司 | Data storage management method and system based on artificial intelligence |
| CN115687677B (en) * | 2022-10-18 | 2024-03-22 | 浙江丰能医药科技有限公司 | Data storage management method and system based on artificial intelligence |
| CN116069729A (en) * | 2023-04-06 | 2023-05-05 | 深圳市微克科技有限公司 | Intelligent document packaging method, system and medium |
| CN116383427A (en) * | 2023-06-06 | 2023-07-04 | 深圳市微克科技有限公司 | Picture batch analysis method, system and medium based on intelligent wearable device |
| CN116383427B (en) * | 2023-06-06 | 2023-08-11 | 深圳市微克科技有限公司 | Picture batch analysis method, system and medium based on intelligent wearable device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106777007A (en) | Photograph album Classified optimization method, device and mobile terminal | |
| CN104615769B (en) | Picture classification method and device | |
| KR102173123B1 (en) | Method and apparatus for recognizing object of image in electronic device | |
| US20210294429A1 (en) | Apparatus, method and recording medium for controlling user interface using input image | |
| US9172879B2 (en) | Image display control apparatus, image display apparatus, non-transitory computer readable medium, and image display control method | |
| KR20140110584A (en) | Method for providing augmented reality, machine-readable storage medium and portable terminal | |
| US20140267435A1 (en) | Image editing method, machine-readable storage medium, and terminal | |
| CN108886574A (en) | A kind of shooting bootstrap technique, equipment and system | |
| WO2015003606A1 (en) | Method and apparatus for recognizing pornographic image | |
| CN111464716A (en) | Certificate scanning method, device, equipment and storage medium | |
| KR102077677B1 (en) | Mobile terminal and method for controlling the same | |
| US20230336671A1 (en) | Imaging apparatus | |
| CN106096043A (en) | A kind of photographic method and mobile terminal | |
| EP3113047A1 (en) | Search system, server system, and method for controlling search system and server system | |
| KR20180121273A (en) | Method for outputting content corresponding to object and electronic device thereof | |
| CN105468716A (en) | Picture search device and method, and terminal | |
| CN107133361A (en) | Gesture identification method, device and terminal device | |
| KR102303206B1 (en) | Method and apparatus for recognizing object of image in electronic device | |
| KR20150117043A (en) | Method for sorting a media content and electronic device implementing the same | |
| US20160283520A1 (en) | Search device, search method, and computer program product | |
| CN110955788A (en) | Information display method and electronic equipment | |
| KR20150097250A (en) | Sketch retrieval system using tag information, user equipment, service equipment, service method and computer readable medium having computer program recorded therefor | |
| KR20140146884A (en) | Method for editing images captured by portable terminal and the portable terminal therefor | |
| CN113034213B (en) | Cartoon content display method, device, equipment and readable storage medium | |
| JP6321204B2 (en) | Product search device and product search method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170721 Address after: 100102, 18 floor, building 2, Wangjing street, Beijing, Chaoyang District, 1801 Applicant after: BEIJING ANYUN SHIJI SCIENCE AND TECHNOLOGY CO., LTD. Address before: 100088 Beijing city Xicheng District xinjiekouwai Street 28, block D room 112 (Desheng Park) Applicant before: Beijing Qihu Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
| RJ01 | Rejection of invention patent application after publication |