CN105913052A - Photograph classification management method and system thereof - Google Patents
Photograph classification management method and system thereof Download PDFInfo
- Publication number
- CN105913052A CN105913052A CN201610400173.1A CN201610400173A CN105913052A CN 105913052 A CN105913052 A CN 105913052A CN 201610400173 A CN201610400173 A CN 201610400173A CN 105913052 A CN105913052 A CN 105913052A
- Authority
- CN
- China
- Prior art keywords
- photo
- face
- folder
- file
- sub
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
- G06V40/173—Classification, e.g. identification face re-identification, e.g. recognising unknown faces across different face tracks
Landscapes
- Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a photograph classification management method and a system thereof. The method is characterized by through carrying out face characteristic identification on a photograph to be processed, storing the photograph whose face characteristic is identified and the photograph whose face characteristic is not identified in a first file and a second file respectively; carrying out face characteristic identification on the photograph stored in the first file; establishing subfiles corresponding to the number of faces under the first file; storing the photographs containing the same face in the same subfile; reading the number of preset face characteristic points in each photograph in each subfile; according to a descending order of the number of the preset face characteristic points, arranging the photographs in each subfile; and according to an arrangement order of the photographs, marking a recommending index or a deletion index of the photograph. By using the method and the system thereof, portrait characteristics are analyzed, a certain arrangement rule is set, the recommending index or the deletion index is given out so that a user can conveniently and rapidly search the required photograph.
Description
Technical field
The present invention relates to information storage tube reason technical field, the method for a kind of photo classification management and system thereof.
Background technology
Increasing terminal use, lives mobile terminal as record, flutters the instrument catching beautiful scenery.The mobile phone persistently releasing big pixel in industry also demonstrate that consumer demand is in sustainable growth for this part of taking pictures.According to mobile Internet design centre 2012
The data survey that year is carried out for mobile phone photograph shows, the people of 44% has been accustomed on mobile phone processing photo.Certainly, this ratio is still going up year by year along with the progress of smart mobile phone technology.
But most user takes pictures for mobile terminal and is only limitted to shooting, and fresh set foot in arrangement less, cause the photo of storage in mobile phone disorderly and unsystematic, occupy mobile phone storage, some problems that mobile phone photo album easily occurs, such as: same place repeats to shoot multiple, wherein comprise many similar photos, general user is to have a full house at mobile phone EMS memory just to arrange photograph album, therefore whenever user is needing to quickly find satisfied photo when, too much owing to wherein storing photo, cause search efficiency low, thus bring inconvenience to the use of user.
Therefore, prior art awaits further improving.
Summary of the invention
In view of above-mentioned weak point of the prior art, it is an object of the invention to provide the user method and the system thereof of the management of a kind of photo classification, overcome terminal in prior art not have the problem of function of automatic arranging storage inside photo.
It is as follows that the present invention solves the technical scheme that technical problem used:
The method of a kind of photo classification management, wherein, said method comprising the steps of:
Step A, pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file；
Step B, under described first file storage photo do face feature identification, identify the number wherein containing different faces, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder；
Step C, read in described sub-folder the number presetting human face characteristic point contained by every photo, successively decrease according to the number of described default human face characteristic point or photo in sub-folder described in descending order.
The method of described photo classification management, wherein, also includes before described step A:
Step A0, reading the information of pending photo, the photo that shooting time is spaced Preset Time is stored in same parent folder, and sets up described first file and described second file under described parent folder.
The method of described photo classification management, wherein, described step C also includes:
Step C1, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
The method of described photo classification management, wherein, described step C1 also includes:
Step C11, read the smiling face's number contained by every photo in described sub-folder, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades；
Step C12, read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level；
Step C13, read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
The method of described photo classification management, wherein, described step C1 also includes:
Step C21, to search face in described sub-folder be front and containing the photo of smiling face, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades；
Step C22, search face in described sub-folder and be front, do not contain the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level；
Step C23, reading the windup-degree remaining side face contained by photo in described sub-folder, successively decrease arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, the photo deletion index that labelling contains side face is two grades.
A kind of system of photo classification management, wherein, described system includes:
First divides module, for pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file；
Second divides module, for the photo of storage under described first file is done face feature identification, identify the number wherein containing different faces, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder；
Order module, for reading in described sub-folder the number presetting human face characteristic point contained by every photo, successively decreases according to the number of described default human face characteristic point or photo in sub-folder described in descending order.
The system of described photo classification management, wherein, described system also includes:
File prestores module, and for reading the information of pending photo, the photo that shooting time is spaced Preset Time is stored in same parent folder, and sets up described first file and described second file under described parent folder.
The system of described photo classification management, wherein, described order module also includes:
LBP value sequencing unit, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
The system of described photo classification management, wherein, described order module also includes:
First presets feature ordering unit, for reading in described sub-folder the smiling face's number contained by every photo, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades；
Second presets feature ordering unit, for read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level；
3rd presets feature ordering unit, for read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
The system of described photo classification management, wherein, described order module also includes:
4th presets feature ordering unit, it is front and the photo containing smiling face for searching face in described sub-folder, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades；
5th presets feature ordering unit, for to search face in described sub-folder be front, does not contains the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level；
6th presets feature ordering unit, for reading, described sub-folder remains the windup-degree of side face contained by photo, successively decreasing arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, index deleted by the photo that labelling contains side face is two grades.
Beneficial effect, the invention provides method and the system thereof of a kind of photo classification management, by pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file, the photo of storage under described first file is done face feature identification, identify the number of different face, and under described first file, set up the sub-folder of corresponding face number, photo containing identical face is stored in same sub-folder, read the number presetting human face characteristic point in described sub-folder in every photo, according to the photo in sub-folder described in the number descending order of described default human face characteristic point, and according to photo put in order the recommendation index to photo or delete index be marked.The method of the invention and system thereof, be analyzed for portrait feature, and arranges certain queueing discipline, is arranged by photo, facilitates user and quickly searches required photo.
Accompanying drawing explanation
Fig. 1 is the flow chart of steps of the method for a kind of photo classification management of the present invention.
Fig. 2 is folder hierarchy block diagram in the method for the invention specific embodiment.
Fig. 3 is the theory structure schematic diagram of the system of a kind of photo classification management of the present invention.
Detailed description of the invention
For making the purpose of the present invention, technical scheme and advantage clearer, clear and definite, the present invention is described in more detail for the embodiment that develops simultaneously referring to the drawings.Should be appreciated that specific embodiment described herein is used only for explaining the present invention, be not intended to limit the present invention.
Owing to user is when using terminal to take pictures, same scene or same scenery, the most all can shoot very multiple pictures, causes the similarity of multiple pictures in internal memory the highest, not only take a large amount of internal memory, when a photo therein found out by needs, generally require and many pieces of browse one by one, and when user carry out photo arrange time, often can only manually delete, the most in use, not there is due to terminal the function of automatic arranging photo, bring inconvenience to user.
The method of the invention is analyzed for portrait feature, and similar portrait photographs is stored in a file；According to personage front, side in file, if smile, if the conditions such as eye closing display photos successively；So photo browses the most succinct, when point opens the file of similar portrait photographs, owing to effect of taking pictures there to be sequence, bad photo recommendation deletion can be shot by automatically prompting user, therefore facilitate user to arrange the photo in terminal efficiently, offer convenience to the use of user.
Concrete, the invention provides a kind of method that photo classification manages, as it is shown in figure 1, said method comprising the steps of:
Step S1, pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file.
The pending photo stored in terminal is carried out face characteristic identification, it may be judged whether containing face, will identify that the photo of face stores the first file, by unidentified go out face photo store the second file.
Step S2, the photo of storage under described first file is done face feature identification, identify the number of different face, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder.
Under first file, the photo of storage all contains face, number to faces different in the photo of storage under the first file the most in this step, then an independent sub-folder is set up respectively according to different people, photo correspondence containing identical face is saved in a single sub-folder, thus establish the file of an exclusive photo for everyone, search photo for user and provide convenient.
Step S3, read in described sub-folder the number presetting human face characteristic point in every photo, successively decrease according to the number of described default human face characteristic point or the order that is incremented by arranges the photo in described sub-folder.
The corresponding storage whole photos containing same face under each sub-folder, the most described whole photo there may be the photo of many people group photo, it is also likely to be the single photo of this people, in this step, the number presetting human face characteristic point in photo is identified, carry out successively decreasing or sort ascending according to the number identified, thus realize the regular storage of photo, and carry out recommending index or deleting the labelling of index to photo according to the order after arrangement.
Described default human face characteristic point is behaved certain characteristic point on the face, and such as: whether contain smiling face in the eyes contained in current photo, in photo, in the position of human eye and the distance of photo center or photo, whether face is front etc..It is envisioned that user can the most self-defined described default human face characteristic point, it is also possible to being configured default human face characteristic point by the way of system default, described default human face characteristic point can be one or more.
It is also preferred that the left in order to preferably photo is ranked up, also include in described step S3:
Step S31, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
In photo under pressing from both sides due to storage to same file, when being ranked up, it is possible that two or multiple pictures contain same number and preset human face characteristic point, therefore when in two or multiple pictures containing identical default human face characteristic point, then the order that photo successively decreases according to LBP value is arranged.
LBP(Local
Binary Patterns), i.e. local binary patterns, is a kind of nonparametric operator describing image local space structure.LBP operator definitions is the texture operator that a kind of grey scale is constant, is that the common definition from local neighborhood texture gets.Basic thought is: with the gray value of center pixel as threshold value, the binary code obtained compared with its neighborhood is to state Local textural feature.
Specifically, the step being ranked up according to default human face characteristic point the photos taken a group photo in sub-folder containing many individuals to photo includes:
S311, read the smiling face's number contained by every photo in described sub-folder, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades.
First smiling face's number contained by every photo in sub-folder is identified by this step, when it specifically identifies, can be identified only for the feature of the feature of eye and face, it is judged that curved degree under the upper curved degree of the corners of the mouth and canthus, if all exceeding predefined curved degree, it is judged that for smiling face.Smiling face's feature of the face characteristic of reading with storage can also be compared, if comparison success, then containing smiling face in the face characteristic in explanation photo.
Every photo in sub-folder is all carried out smiling face's contrast, finds out the photo all containing smiling face, and the order arrangement photo successively decreased according to smiling face's number by the photo finding out smiling face, and the recommendation index of this type of photo of labelling is two grades.
Step S312, read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level.
The eyes number contained in photo to the unidentified smiling face of going out is identified, and according to the descending order photo of eyes number, and the recommendation index mark of this kind of photo is designated as one-level.Same, can be identified according to the eye feature prestored, it is also possible to the feature identified is judged, it is determined whether for the feature of eyes, the most then read the number containing eye feature in photo, and be marked.
Step S313, read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
By in sub-folder unidentified go out eyes every photo contained by face number be identified, and according to the descending order photo of face number, and the deletion index mark of this type of photo is designated as two grades.
The step being ranked up photo according to the default human face characteristic point of the basis preset for the photo of people single in sub-folder includes:
Step S321, to search face in described sub-folder be front and containing the photo of smiling face, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades.
Step S322, search face in described sub-folder and be front, do not contain the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level.
This step also includes: be front to face, can't detect the process step of eyes photo: the deletion index mark that can't detect the photo of eyes is designated as two grades.Due in photo containing face, but but can't detect eyes, illustrate photo be probably be used in eye closing in the case of shoot, therefore can advise that this type of photo is deleted by user.
Step S323, reading the windup-degree remaining side face contained by photo in described sub-folder, successively decrease arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, the photo deletion index that labelling contains side face is two grades.
It is also preferred that the left also include in above-mentioned steps S321 and S322: the step of similarity examination.Described similarity examination includes: if L-value deviation is within 10 pixels, then calculate the LBP value of photo, and LBP value deviation is within 10, then illustrate that the similarity of photo is high, remove the picture that LBP value is maximum, remaining picture is marked, under photo finishing mode, it is recommended that user deletes；And arranging recommendation index is a star；First carrying out judgement with L-value to be because L-value and be easy to get, LBP value calculates to be responsible for, the most long.
Due to different time shooting photo, similarity may ratio relatively low, therefore also included before described step S1:
Step S0, read the information of pending photo, the shooting time interval photo less than a minute is stored in same parent folder, and under described parent folder, sets up described first file and described second file.
In conjunction with file block schematic illustration shown in Fig. 2, the concrete Application Example of processing method of the present invention is described in detail.
The concrete Application Example of the method for the invention comprises the following steps:
Step one: import photo to be classified, reads the shooting time information of photo, first less than one minute, shooting time interval is classified as a parent folder 10.
Step 2: in parent folder 10, carries out Face datection, including positive face and side face, is extracted by the photo having face, is classified as the first file 110, and do not have face classifies as the second file 120.
Step 3: the photo in the first file 110 carries out recognition of face, if different photos, corresponding different people, then sets up sub-folder 1110 and sub-folder 1120 according to personage；(group photo photo, as long as comprising the people of correspondence, all should occur under the sub-folder of correspondence, and i.e. one opening and closing shadow photo comprises two people, then will have this opening and closing shadow photo under the file that two correspondences contain the two people's photo).
Step 4: the photo in sub-folder 1110 is ranked up display；Ordering rule is for first showing many people photo, then shows single photo, and specific implementation method is as follows:
Many people photo
1), first lookup has the photo of smile number；According to smile number sort descending, if smile number is identical, then according to the eyes number sort descending detected, if eyes number is identical, then according to number sort descending, if number is identical, then according to LBP value sort descending；Display two stars recommended in record；
2), residue photo searches the photo that eyes can be detected, according to eyes number sort descending, if eyes number is identical, then according to number sort descending, if number is identical, then according to LBP value sort descending；Display one star recommended in record；
3), remain in photo according to number sort descending, if number is identical, then according to LBP value sort descending；
4), being marked this Part of photos taken, under photo finishing mode, these photos of user to be recommended can be deleted；And arranging deletion index is two stars.
Single photo
5), first search positive face, eyes can be detected, have the photo of smile, according to the human eye coordinate position sort descending successively of distance L from photo center position；Carry out similarity examination again；Display two stars recommended in record.
6) search positive face, again, eyes can be detected, there is no the photo smiled, according to the human eye coordinate position sort descending successively of distance L from photo center position；Carry out similarity examination again；Display one star recommended in record.
7) search positive face again, can't detect the photo of eyes, according to shooting time sequencing display；These photos to be marked, and under photo finishing mode, these photos of user to be recommended can be deleted；And arranging deletion index is two stars.
8), remaining side face photo, show according to the windup-degree sort descending successively of side face；If different photo angular deviations are within about 2 degree, and LBP deviation 10, illustrating that photo is shown in that similarity is high, remove the picture that LBP value is maximum, remaining picture is marked, and under photo finishing mode, these photos of user to be recommended can be deleted；And arranging deletion index is a star.
9), single photo is arranged after, take wherein the arrangement photo of first as Person1 album cover；
10), display: user can define photo under file and all show, or only shows that the photo recommending star shows.
The method provided by the present invention can the most quickly arrange photo, and carries out being classified into file；Whole expansion before Xiang Dui shows, it is possible to neatly a lot, and is to be arranged in order according to effect of taking pictures in file, checks convenient；The when that user arranging photo, it is possible to carry out intelligent recommendation, recommending user one key to delete in bad photo, improve efficiency, the use for user provides convenient.
The present invention, under disclosing the processing method premise that above-mentioned photo arranges, additionally provides the system of a kind of photo classification management, as it is shown on figure 3, described system includes:
First divides module 100, for pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file；Its function is as described in step S1.
Second divides module 200, the photo of storage under described first file is done face feature identification, identify the number of different face, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder；Its function is as described in step S2.
Order module 300, for reading the number presetting human face characteristic point in described sub-folder in every photo, successively decreases according to the number of described default human face characteristic point or incremental order arranges the photo in described sub-folder, and its function is as described in step S3.
Described system also includes:
File prestores module, for reading the information of pending photo, is stored in same parent folder by the shooting time interval photo less than a minute, and sets up described first file and described second file under described parent folder.
Described order module also includes:
LBP value sequencing unit, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
Described order module also includes:
First presets feature ordering unit, for reading in described sub-folder the smiling face's number contained by every photo, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades；
Second presets feature ordering unit, for read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level；
3rd presets feature ordering unit, for read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
Described order module also includes:
4th presets feature ordering unit, it is front and the photo containing smiling face for searching face in described sub-folder, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades；
5th presets feature ordering unit, for to search face in described sub-folder be front, does not contains the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level；
6th presets feature ordering unit, for reading, described sub-folder remains the windup-degree of side face contained by photo, successively decreasing arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, index deleted by the photo that labelling contains side face is two grades.
The invention provides method and the system thereof of a kind of photo classification management, by pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file, the photo of storage under described first file is done face feature identification, identify the number of different face, and under described first file, set up the sub-folder of corresponding face number, photo containing identical face is stored one by one in each sub-folder, read the number presetting human face characteristic point in described sub-folder in every photo, according to the photo in sub-folder described in the number descending order of described default human face characteristic point, and according to photo put in order the recommendation index to photo or delete index be marked.The method of the invention and system thereof, be analyzed for portrait feature, and arranges certain queueing discipline, is arranged by photo, facilitates user and quickly searches required photo.
It is understood that for those of ordinary skills, can be according to technical scheme and inventive concept thereof in addition equivalent or change, and all these change or replace the protection domain that all should belong to appended claims of the invention.
Claims (10)
1. the method for a photo classification management, it is characterised in that said method comprising the steps of:
Step A, pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file；
Step B, under described first file storage photo do face feature identification, identify the number wherein containing different faces, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder；
Step C, read in described sub-folder the number presetting human face characteristic point contained by every photo, successively decrease according to the number of described default human face characteristic point or photo in sub-folder described in descending order.
The method of photo classification the most according to claim 1 management, it is characterised in that also include before described step A:
Step A0, reading the information of pending photo, the photo that shooting time is spaced Preset Time is stored in same parent folder, and sets up described first file and described second file under described parent folder.
The method of photo classification the most according to claim 1 management, it is characterised in that described step C also includes:
Step C1, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
The method of photo classification the most according to claim 3 management, it is characterised in that described step C1 also includes:
Step C11, read the smiling face's number contained by every photo in described sub-folder, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades；
Step C12, read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level；
Step C13, read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
The method of photo classification the most according to claim 3 management, it is characterised in that described step C1 also includes:
Step C21, to search face in described sub-folder be front and containing the photo of smiling face, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades；
Step C22, search face in described sub-folder and be front, do not contain the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level；
Step C23, reading the windup-degree remaining side face contained by photo in described sub-folder, successively decrease arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, the photo deletion index that labelling contains side face is two grades.
6. the system of a photo classification management, it is characterised in that described system includes:
First divides module, for pending photo is carried out face characteristic identification, will identify that face characteristic photo and unidentified go out face characteristic photo be respectively stored into the first file and the second file；
Second divides module, for the photo of storage under described first file is done face feature identification, identify the number wherein containing different faces, and under described first file, set up the sub-folder of described number, the photo containing identical face is stored in same sub-folder；
Order module, for reading in described sub-folder the number presetting human face characteristic point contained by every photo, successively decreases according to the number of described default human face characteristic point or photo in sub-folder described in descending order.
The system of photo classification the most according to claim 6 management, it is characterised in that described system also includes:
File prestores module, and for reading the information of pending photo, the photo that shooting time is spaced Preset Time is stored in same parent folder, and sets up described first file and described second file under described parent folder.
The system of photo classification the most according to claim 6 management, it is characterised in that described order module also includes:
LBP value sequencing unit, when described sub-folder presets the photo of human face characteristic point containing same number, then same number is preset the order that the photo of human face characteristic point successively decreases according to LBP value and arranges.
The system of photo classification the most according to claim 8 management, it is characterised in that described order module also includes:
First presets feature ordering unit, for reading in described sub-folder the smiling face's number contained by every photo, and according to the descending order photo of smiling face's number, and labelling to read the recommendation index containing smiling face's photo be two grades；
Second presets feature ordering unit, for read described sub-folder unidentified go out smiling face the eyes number contained by every photo, and according to the descending order photo of eyes number, and labelling to read the recommendation index of eye feature photo be one-level；
3rd presets feature ordering unit, for read in described sub-folder unidentified go out eyes the face number contained by every photo, and according to the descending order photo of face number, and the deletion index of the photo of face characteristic that labelling reads is two grades.
The system of photo classification the most according to claim 8 management, it is characterised in that described order module also includes:
4th presets feature ordering unit, it is front and the photo containing smiling face for searching face in described sub-folder, read the position of human eye in photo and the distance of photo center, and according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo for smiling face recommends index to be two grades；
5th presets feature ordering unit, for to search face in described sub-folder be front, does not contains the photo of smiling face, read the position of human eye in photo and the distance of photo center, according to the distance of the positional distance photo center of human eye, photo is arranged, and marker detection is front to the feature of face, and the photo not containing smiling face recommends index to be one-level；
6th presets feature ordering unit, for reading, described sub-folder remains the windup-degree of side face contained by photo, successively decreasing arrangement photo according to the size of windup-degree, and delete the LBP value photo less than predetermined threshold of photo, index deleted by the photo that labelling contains side face is two grades.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610400173.1A CN105913052A (en) | 2016-06-08 | 2016-06-08 | Photograph classification management method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610400173.1A CN105913052A (en) | 2016-06-08 | 2016-06-08 | Photograph classification management method and system thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105913052A true CN105913052A (en) | 2016-08-31 |
Family
ID=56750890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610400173.1A Pending CN105913052A (en) | 2016-06-08 | 2016-06-08 | Photograph classification management method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105913052A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679532A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Data transmission method, device, mobile terminal and computer-readable recording medium |
| CN108228852A (en) * | 2018-01-10 | 2018-06-29 | 上海展扬通信技术有限公司 | The method, apparatus and computer readable storage medium of electron album cover generation |
| CN111028251A (en) * | 2019-12-27 | 2020-04-17 | 四川大学 | Dental picture cutting method, system, equipment and storage medium |
| CN112199546A (en) * | 2020-12-04 | 2021-01-08 | 浙江聚欣科技有限公司 | Photo storage management system and method |
| CN112507154A (en) * | 2020-12-22 | 2021-03-16 | 哈尔滨师范大学 | Information processing device |
| 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 |
| CN112733664A (en) * | 2020-12-31 | 2021-04-30 | 北京华安信联通信技术有限公司 | Photo classification method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101379488A (en) * | 2006-02-06 | 2009-03-04 | 联邦印刷有限公司 | Method for evaluating the quality of an image, method for producing a document computer program product, user interface, data file and electronic device |
| CN102132318A (en) * | 2008-08-21 | 2011-07-20 | 惠普开发有限公司 | Automatic creation of a scalable relevance ordered representation of an image collection |
| CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
| CN104331509A (en) * | 2014-11-21 | 2015-02-04 | 深圳市中兴移动通信有限公司 | Picture managing method and device |
-
2016
- 2016-06-08 CN CN201610400173.1A patent/CN105913052A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101379488A (en) * | 2006-02-06 | 2009-03-04 | 联邦印刷有限公司 | Method for evaluating the quality of an image, method for producing a document computer program product, user interface, data file and electronic device |
| CN102132318A (en) * | 2008-08-21 | 2011-07-20 | 惠普开发有限公司 | Automatic creation of a scalable relevance ordered representation of an image collection |
| CN104185981A (en) * | 2013-10-23 | 2014-12-03 | 华为终端有限公司 | Method and terminal selecting image from continuous captured image |
| CN104331509A (en) * | 2014-11-21 | 2015-02-04 | 深圳市中兴移动通信有限公司 | Picture managing method and device |
Non-Patent Citations (3)
| Title |
|---|
| CHARU C. AGGARWAL: "《Social Network Data Analytics》", 31 December 2011 * |
| 丁莹 等著: "《复杂环境运动目标检测技术及应用》", 31 January 2014, 国防工业出版社 * |
| 董春阳著: "《商业摄影后期制作》", 30 April 2016 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679532A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Data transmission method, device, mobile terminal and computer-readable recording medium |
| CN107679532B (en) * | 2017-09-15 | 2019-12-03 | Oppo广东移动通信有限公司 | Data transmission method, device, mobile terminal and computer readable storage medium |
| CN108228852A (en) * | 2018-01-10 | 2018-06-29 | 上海展扬通信技术有限公司 | The method, apparatus and computer readable storage medium of electron album cover generation |
| CN111028251A (en) * | 2019-12-27 | 2020-04-17 | 四川大学 | Dental picture cutting method, system, equipment and storage medium |
| CN112199546A (en) * | 2020-12-04 | 2021-01-08 | 浙江聚欣科技有限公司 | Photo storage management system and method |
| CN112507154A (en) * | 2020-12-22 | 2021-03-16 | 哈尔滨师范大学 | Information processing device |
| CN112507154B (en) * | 2020-12-22 | 2022-02-11 | 哈尔滨师范大学 | Information processing device |
| 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 |
| CN112733664A (en) * | 2020-12-31 | 2021-04-30 | 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 |
| CN112733664B (en) * | 2020-12-31 | 2024-04-16 | 北京华安信联通信技术有限公司 | Photo classification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105913052A (en) | Photograph classification management method and system thereof | |
| CN104822016B (en) | Image processing apparatus and image processing method | |
| CN102387287B (en) | Image processing apparatus, image processing method, and image processing system | |
| CN108241645B (en) | Image processing method and device | |
| CN106777007A (en) | Photograph album Classified optimization method, device and mobile terminal | |
| CN103348381A (en) | Image recognition device, image recognition method, program and integrated circuit | |
| CN101706793A (en) | Method and device for searching picture | |
| JP2002358522A (en) | Device, method and program for supporting image selection | |
| CN105468675A (en) | Picture display system and method combining figure identification and holiday and festival information | |
| JP2007513413A (en) | Content recognition for selecting emphasized images | |
| CN108228114A (en) | Control method and storage medium | |
| CN102033958A (en) | Photo sort management system and method | |
| CN102819726A (en) | System and method for processing photograph of mobile terminal | |
| CN104331515B (en) | A kind of method and system for automatically generating tourism diary | |
| WO2016145844A1 (en) | Picture sorting method and corresponding picture storage and display device | |
| CN101268490A (en) | Information presenting system, information presenting terminal and server | |
| CN106203286A (en) | The content acquisition method of a kind of augmented reality, device and mobile terminal | |
| CN105243084A (en) | Photographed image file storage method and system and photographed image file search method and system | |
| CN104284252A (en) | Method for generating electronic photo album automatically | |
| CN101515271A (en) | Method and system for photo management, photo classification code-storing computer-readable media | |
| CN104063444A (en) | Method and device for generating thumbnail | |
| CN106557549A (en) | Method and device for identifying target object | |
| CN112000024B (en) | Method, device and equipment for controlling household appliance | |
| CN103093213B (en) | Video file classification method and terminal | |
| CN107992540A (en) | A kind of intelligent children's photograph album based on Face recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160831 |