CN108073948A - A kind of photo sort management, server, apparatus and system - Google Patents
A kind of photo sort management, server, apparatus and system Download PDFInfo
- Publication number
- CN108073948A CN108073948A CN201711384927.XA CN201711384927A CN108073948A CN 108073948 A CN108073948 A CN 108073948A CN 201711384927 A CN201711384927 A CN 201711384927A CN 108073948 A CN108073948 A CN 108073948A
- Authority
- CN
- China
- Prior art keywords
- photo
- classification
- sorted
- server
- face
- 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
Landscapes
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses a kind of photo sort management, server, apparatus and system, the described method includes:Obtain the image content features of photo to be sorted;The photo classification of the photo to be sorted is determined according to the image content features of the photo to be sorted;The photo classification of the definite photo to be sorted is sent to user terminal, so that user terminal is managed the photo to be sorted according to the definite photo classification.Using the present invention, it may be such that user need not carry out hand labeled or manual classification to photo, realizing, which to the operation of the mechanized classification of photograph image content, preferably realizes the classification of the picture material according to photo, carrys out organization and management to photo, greatly facilitates user.
Description
Technical field
The present invention relates to photo management field more particularly to a kind of photo sort management, server, device and it is
System.
Background technology
With advances in technology and the improvement of people's living standards, camera have mobile phone, the palm PC of camera function
Electronic equipments is waited to come into huge numbers of families.More and more users are keen to take pictures, and get substantial amounts of photo.At present, for
Classification is marked to these photos in the photo taken pictures, the mode that user can only be manually, to realize to these photos
Management, such as:After photo hand labeled, it is stored under a certain sort file catalogue.The prior art carries out manual mark
The operation of note is cumbersome, and every photo of shooting is marked classification also than relatively time-consuming in user, if without marking again
Cannot Classification Management be carried out to photo well, this causes user using burden.
The content of the invention
Technical problem to be solved of the embodiment of the present invention is, provides a kind of photo sort management, server, dress
It puts and system, Classification Management can be carried out automatically to the photo got by the modes such as shooting.
In order to solve the above-mentioned technical problem, an embodiment of the present invention provides a kind of photo sort management, including:
Server obtains the image content features of photo to be sorted;
The server determines the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not;
The photo classification of the definite photo to be sorted is sent to user terminal by the server, so that user terminal
According to the definite photo classification, Classification Management is carried out to the photo to be sorted.
Correspondingly, the embodiment of the present invention additionally provides a kind of server, including:
Acquisition module, for obtaining the image content features of photo to be sorted;
Sort module, described in the image content features of the photo to be sorted for being got according to the acquisition module determine
The classification of photo to be sorted;
Communication module, the classification of the photo to be sorted for the sort module to be determined are sent to user terminal,
So that classification of the user terminal according to the definite photo to be sorted, Classification Management is carried out to the photo to be sorted.
Correspondingly, the embodiment of the present invention additionally provides a kind of photo classification managing device, including:
Photo acquisition module, for obtaining photo to be sorted;
Communication module, for the contracting of the photo to be sorted or the photo to be sorted that obtain the photo acquisition module
Sketch map is sent to server, and the photo classification for receiving the photo to be sorted determined by server;
Classification Management module, for the photo classification of the photo to be sorted received according to the communication module, to described
Photo to be sorted carries out Classification Management;
Wherein, the server determines the photograph to be sorted according to the image content features for obtaining the photo to be sorted
The photo classification of piece.
Correspondingly, the embodiment of the present invention additionally provides a kind of photo sort management system, including:Photo classification managing device
And server, wherein,
The photo classification managing device for obtaining photo to be sorted, and by the photo to be sorted or described is treated
The thumbnail of classification photo is sent to the server;
The server, it is to be sorted for being obtained according to the thumbnail of the photo to be sorted or the photo to be sorted
The image content features of photo determine the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not, and by the photo classification of the definite photo to be sorted it is sent to the photo classification managing device;
The photo classification managing device is additionally operable to receive the photo classification of the photo to be sorted determined by server,
And according to photo classification, Classification Management is carried out to the photo to be sorted.
Implement the embodiment of the present invention, have the advantages that:
The photo that the present invention can be got user by the modes such as take pictures carries out the identification of feature and photo is divided
Class so that user need not carry out hand labeled or manual classification to photo, realize the mechanized classification to photo content
Operation, the classification for preferably realizing the content according to photo come the tissue to photo and Classification Management, greatly facilitate use
Family.
Description of the drawings
It in order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the structure composition schematic diagram of the photo sort management system of the embodiment of the present invention;
Fig. 2 is the structure composition schematic diagram of the photo classification managing device in Fig. 1;
Fig. 3 is the structure composition schematic diagram of the server in Fig. 1;
Fig. 4 is the first embodiment flow diagram of the photo sort management of the present invention;
Fig. 5 is the second embodiment flow diagram of the photo sort management of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment belongs to the scope of protection of the invention.
Fig. 1 is referred to, is the structure composition schematic diagram of the photo sort management system of the embodiment of the present invention, the present embodiment
In, the photo sort management system includes:Photo classification managing device 1 and server 2.The photo classification managing device 1
With the server 2 data transfer can be carried out by wired or be wirelessly connected.
The photo classification managing device 1 includes user terminal, for obtaining photo to be sorted, and by the photograph to be sorted
The thumbnail of piece or the photo to be sorted is sent to the server 2.
The server 2 is used to be obtained according to the thumbnail of the photo to be sorted or the photo to be sorted to be sorted
The image content features of photo determine the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not, and by the photo classification of the definite photo to be sorted it is sent to the photo classification managing device 1.
The photo classification managing device 1 is additionally operable to receive the photo class of the photo to be sorted determined by server 2
Not, and according to photo classification to the photo to be sorted Classification Management is carried out.
The photo classification managing device 1 can be the camera with communication function, mobile phone/electricity with camera function
Brain, user by taking pictures, copying, transmitting etc. after modes get photo to be sorted, by the photo classification managing device 1 to
The server 2 sends the photo to be sorted or only sends the thumbnail of the photo to be sorted.
After the server 2 determines the photo classification of the photo to be sorted, the photo classification of the photo to be sorted is sent out
The photo classification managing device 1 is given, the photo to be sorted is managed by the photo classification managing device 1, for example,
The photo to be sorted is stored the mesh to respective classes by the photo classification managing device 1 according to the classification of the photo to be sorted
Under record, and display of classifying.
In addition, the server 2 photo to be sorted is carried out classification determine after, can also be by the photo and its photograph to be sorted
Piece classification is sent in the picture server specified by the photo classification managing device 1, is such as sent to the use that user specifies
In the photo spatial server of family, so that the user picture spatial server stores the photo to be sorted according to photo classification
Into respective memory, institute can be shown according to photo classification in the space of the user (such as QQ space) at any time when the user desires
State photo to be sorted.
It, as needed also can be by it should be noted that the photo classification managing device 1 is after photo to be sorted is got
Its own carries out the Classification and Identification of photo, and is managed operation, i.e., described photo classification managing device 1 obtains described to be sorted
The image content features of photo determine the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not, and according to photo classification, Classification Management is carried out to the photo to be sorted.
Further, Fig. 2 is referred to, is the structure composition schematic diagram of the photo classification managing device 1 in Fig. 1, the photograph
Piece Classification Management device 1 can include:Photo acquisition module 11, communication module 12 and Classification Management module 13.
The photo acquisition module 11, for obtaining photo to be sorted.
The photo acquisition module 11 can get photo by way of taking pictures, and certainly, can also pass through data transmission
Mode photo is got from other equipment, the photo acquisition module 11 is after photo to be sorted is got, additionally it is possible to
The thumbnail of the photo to be sorted is extracted as needed.
The communication module 12 for the photo to be sorted that gets the photo acquisition module 11 or described is treated point
The thumbnail of class photo is sent to server 2, and the photo class for receiving the photo to be sorted determined by server 2
Not.
Specifically, the sending method of the communication module 12 can by user according to situations such as communication speed, campus network and
It needs to be determined that such as:When communication carrier is on the fast wireless network of cable network or WIFI uniform velocity, user is not concerned with flow production
Raw expense and it is desirable that when managed in time all photos, while photo to be sorted is got, i.e., sends photo to be sorted
To server 2;And work as communication carrier on the general wireless network of speed, and user pays close attention to flow and generates expense it may be desirable to working as
When preceding shooting photo manages in time, its thumbnail can be sent to server 2 when getting photo to be sorted;Work as user
It only needs to be managed Part of photos taken, and when regulatory requirement promptness is not strong, manual sending method can be used, treated getting
Classify after photo, decided whether to be uploaded to the server 2 manually by user.
It is to be sorted that this also can be transmitted while the photo to be sorted or its thumbnail is sent in the communication module 12
The name identification of photo, in order to which the server 2 returns to the corresponding name identification of photo to be sorted and its photo classification, so as to
The photo classification managing device 1 divides the photo to be sorted corresponding to name identification according to its photo classification
Class management.Photo classification managing device 1 and server 2 by message carry name identification to ensure classification and photo to be sorted
It is corresponding, so as to support more message concurrent requests.
The Classification Management module 13, for the photo class of the photo to be sorted received according to the communication module 12
Not, the photo to be sorted is managed.Classification Management can include classification storage management, classification display management etc..
Further, the communication module 12 is additionally operable to send the setting request of photo classification to the server, with toilet
It states server 2 and the photo classification that request carries is set to the photo to be sorted or described to be sorted according to the photo classification
The thumbnail classification of photo.
Specifically, user can send photo to be sorted or photograph to be sorted by the communication module 12 to server 2
While piece thumbnail, send individual photo classification and request is set, for asking the server 2 according to the individual photo
Classification sets the photo classification carried in request to classify the thumbnail of the photo to be sorted or photo to be sorted;
It can also be taken in the message for sending the thumbnail for carrying photo to be sorted or photo to be sorted to the server 2
Band photo classification sets request, to ask the photo classification pair that the server 2 sets request to carry according to the photo classification
The photo to be sorted is classified.
Further, the photo classification managing device 1 can also include:Extraction module 14.
The extraction module 14, the photo to be sorted for being obtained to the photo acquisition module 11 carry out Face datection,
And it extracts and obtains facial image;
The communication module 12 is additionally operable to send the facial image to the server 2, for the server 2 to the people
Face image is classified.
Specifically, when user needs to classify to photo by face cluster, such as all photos of same person are returned one
During class, user can detect photo executor face by the extraction module 14 and operate, and extract the facial image in photo, and lead to
It crosses the communication module 12 and is sent to the server 2.
In addition, the communication module 12 while the facial image is sent, can also send face to the server 2
Facial image feature of the identification request in order to the server 2 in the request extraction facial image, and according to people
Face image feature classifies to the photo to be sorted.User can take in the communication module 12 to what server 2 was sent
In message with facial image, asked with specific field value instruction recognition of face in the message;Communication module can also be passed through
12 send individual instruction message instruction to server needs to carry out recognition of face to facial image.So enable server 2
The enough identification for needing to carry out human face photo classification according to user, the knowledge without carrying out other such as indoor and outdoor photo types
Not.And the recognition of face of the identification for being exclusively used in carrying out human face photo classification clusters server, it may not be necessary to additional
Assignor's face identification request in message.
Further, the communication module 12 is sending the photo to be sorted either its thumbnail or facial image
When, the name identification of the photo to be sorted can be also sent simultaneously so that the server 2 returns to the title of corresponding photo to be sorted
Mark and classification, so that the Classification Management module 13 can be to the photo to be sorted corresponding to name identification according to it
Classification is managed.Here name identification is carried by message to ensure the correspondence of classification and photo to be sorted, so as to prop up
More message are held concurrently to classify request.
The photo to be sorted directly can be put into its generic by the Classification Management module 13 according to photo classification
It is organized and managed in photo group, including:According to the definite photo classification, classification is carried out to the photo to be sorted and is deposited
Storage shows to carry out classification, in this case, the Classification Management module 13 may include a classification display unit, for according to institute
Definite photo classification is stated, carrying out classification to the photo to be sorted shows;File (classification group) is established on mobile phone, photograph
Piece hard copy or soft copy are put under corresponding file;The logic association of classification group and photo is established, such as:It is tieed up for classification group
A document is protected, including all photos for belonging to the category.
Further classification logotype addition can also be such as added in metadata on photo, to ensure holding for classification results
It is continuous effective, even if the photo classification of the photo can be still determined after software reinstallation or system refitting according to the classification logotype of photo.
In such cases, the Classification Management module 13 can include:Indexing unit and administrative unit.
The indexing unit, for the photo classification of the photo to be sorted received according to the communication module 12, for institute
State the classification logotype that photo to be sorted adds the photo classification.
The administrative unit, for being managed to the photo to be sorted for being with the addition of classification logotype.
Further, the photo classification managing device 1 can be additionally used according to the Classification Management module 13 to photo
Organization and management shows photo.Such as:User opens some corresponding file of classification group, then this document is presented and presss from both sides following photo
Thumbnail;For another example, user chooses a certain classification, then reads its corresponding document, and the photo according to listed by document extracts its breviary
Figure is shown.If by classification logotype mark on photo, what the photo classification managing device 1 can also be shown according to user
The demand of generic directly reads the classification logotype of photo, and the photo of the category is found and shows photo.
Fig. 3 is referred to again, is the structure composition schematic diagram of the server 2 in Fig. 1.The server 2 specifically includes:It obtains
Module 21, sort module 22 and communication module 23.
The acquisition module 21, for obtaining the image content features of photo to be sorted.
The sort module 22, for the image content features of the photo to be sorted got according to the acquisition module 21
Determine the photo classification of the photo to be sorted.
The to be sorted of the upload of photo classification managing device 1 is being got by modes such as active request, passive receptions
Photo either after the thumbnail of photo to be sorted the acquisition module 21 according to photo to be sorted or the breviary of photo to be sorted
Figure obtains the image content features of photo to be sorted.
The acquisition module 21 can be according to image recognition technology, to the photo to be sorted that receives or photo to be sorted
Thumbnail carries out image identification, reads image content information therein (main scape information and/or background information) as picture material
Feature or image content information (main scape information and/or background information) and metadata information are as image content features.Then by
The sort module 22 is classified.For example, identify head portrait of the main scape information in photo to be sorted for one or more people
Feature can then be determined as personage according to classification;It such as identifies feature of the main scape information for a colored feature, then can be determined as
Plant shines classification;It is outdoor characteristics such as to identify background information, it is determined that shines classification to be outdoor;If it is big to identify background information
The feature in sea, it is determined that shine classification for ocean.If identify the head portrait feature including one or more people, and background information is sea
Foreign feature then can be identified as ocean personage's classification.Specifically it is identified by the similarity meter of photo and photo classification to be sorted
It calculates.The server 2 can specifically be carried by single classified service device, can also be by classified service device cloud (multiple classification clothes
The cloud that business device is formed) it carries, to ensure the quick responses of the classification demand for meeting plurality of classes and more classification requests.
The communication module 23, the classification of the photo to be sorted for the sort module 22 to be determined are sent to use
Family terminal, so that user terminal is managed the photo to be sorted according to the classification of the definite photo to be sorted.
Wherein, the user terminal is above-mentioned photo classification managing device 1, and the communication module 23 can be by existing
Wired/wireless communication network etc. the photo classification of the photo to be sorted is sent to the photo classification managing device 1.
Further, Fig. 3 is referred to, the server 2 may also include:Setup module 24.
The setup module 24, for carrying out classification based training to the photo stored in preset photo library, according in image
Hold feature and obtain the characteristics of image under one or more photo classification and the photo classification.
The server 2 is by setup module 24 to the photo in built-in or peripheral hardware the photo library including a large amount of photos
Classification based training is carried out, characteristics of image under one or more photo classifications and the photo classification is obtained simultaneously according to image content features
It preserves, so that the acquisition module 21 and sort module 22 complete the classification of photo to be sorted.
Specifically, as shown in figure 3, the acquisition module 21 can include:
First receiving unit 211, for receiving the thumbnail of the photo to be sorted or the photo to be sorted.
Fisrt feature acquiring unit 212, for reading the thumbnail of the photo to be sorted or the photo to be sorted
Image content features, wherein, by image content information (main scape information and/or background information) or image content information (main scape
Information and/or background information) and image content features of the metadata information as the photo to be sorted.
Specifically, as shown in figure 3, the sort module 22 can include:
First computing unit, for calculating the image content features of the photo to be sorted and the image under each photo classification
The similarity of feature;Such as based on piecemeal Optimum Matching image similarity calculation method (first to image carry out piecemeal processing, and
Using Optimum Matching it is one-to-one it is matched under the premise of, calculate the attainable maximum similarities of whole piecemeals institute of two images).
First determination unit, in the image for the photo to be sorted being calculated according to first computing unit
Hold the similarity of the characteristics of image under feature and each photo classification, similarity highest and similarity are higher than to the photo classification of threshold value
Photo classification as the photo to be sorted.
Further, as shown in figure 3, the server 2 may also include:
Judgment module 25 when being asked for being set in the photo classification for receiving user's transmission, judges whether local terminal is supported
Identification to requested photo classification;
The setup module 24 is then additionally operable to when the judging result of the judgment module 25 is supports, for user setting institute
The photo classification of request, so as to the sort module 22 according to set photo classification to photo classification to be sorted;If judge
As a result not support, the photo corresponding to requested photo classification is collected, and the photo to being collected into carries out classification based training, obtains
To the mobile phone to the image content features of photo and create requested photo classification and its characteristics of image.
The photo to be sorted is received in first receiving unit 211 of the acquisition module 21 or described is treated point
During the thumbnail of class photo, the judgment module 25 judges whether to receive simultaneously and the photo to be sorted or described treat point
The photo classification that the thumbnail of class photo is synchronously sent sets request, if receiving, the judgment module 25 judges the service
Whether photo classification and the photo classification corresponding picture material that the photo classification set request carry are preserved in device 2
Feature, if in the presence of, the setup module 24 directly sets its requested photo classification for the user, and with the photograph of the setting
Photo classification of the piece classification as photo to be sorted;If being not present, photograph of the setup module 24 to the request being collected into
Photo corresponding to piece classification is trained, and is created the photo classification and is set the photo classification of request carrying and its picture material special
Sign, so that the sort module 22 determines the photo classification of photo to be sorted.For example, when user requires snow mountain to shine classification, if
Server 2 judges not preserve snow mountain according to classification and its image content features by judgment module 25, then can using the words such as snow mountain as
Keyword scans on the internet, and the picture searched is stored in photo library, and is compareed by the setup module 24
The photo corresponding to the photo classification classification collected in valut is trained, and creates the photo classification and its characteristics of image.
Specifically, the identification for human face photo, the setup module 24 of the server 2 can be also used for preset
Photo library in the photo that stores carry out Face datection, recognition of face, face cluster training, obtain one according to facial image feature
A or multiple photo classifications and face characteristic under the photo classification and facial image (preserve corresponding facial image, can use
In subsequently according to the new facial image of the photo classification and it is all before facial image update the face of the photo classification together
Feature) for subsequently carrying out the photo array of face classification.
User is needed when being classified according to face, can pass through the photo classification according to their needs and network request
Managing device 1 sends facial image to server 2, and the acquisition module 21 of the server 2 can also include:
Second receiving unit 213, for receiving facial image;
Second feature acquiring unit 214, for extracting the people in the facial image that second receiving unit 213 receives
Face image feature, and the facial image feature is denoted as to the image content features of the photo to be sorted;Wherein, the face
Image is to be carried out Face datection to the photo to be sorted by the i.e. described photo classification managing device 1 of the user terminal and extracted
It obtains.
It, also can according to their needs and network request, by described specifically, user is needed when being classified according to face
Photo classification managing device 1 directly transmits photo to be sorted to server 2, and the acquisition module 21 can also include:
3rd receiving unit 215, for receiving photo to be sorted;
Third feature acquiring unit 216 for carrying out Face datection to the photo to be sorted, extracts facial image, and
The facial image feature in facial image is extracted, the picture material that the facial image feature is denoted as to the photo to be sorted is special
Sign.
Acquisition for the image content features of the facial image of above-mentioned progress, the sort module 22 can specifically include
Classification and Identification is carried out with lower unit:
Second computing unit, for calculating the facial image feature of the photo to be sorted and each photo class of local terminal storage
The similarity of face characteristic in not;
Second determination unit, for the similarity being calculated according to second computing unit, by similarity highest and
Photo kind judging higher than threshold value is the photo classification of the photo to be sorted;
The setup module 24 is then additionally operable to for the facial image to be associated with the photo having determined that as the photo to be sorted
Classification, and according to the face characteristic of its associated photo classification of facial image update, if there is no similarity higher than threshold value
The facial image according to the new photo classification of the facial image feature-modeling and is associated with the photo classification by photo classification.
Wherein, second computing unit 223 is specifically each photo class by the facial image feature and local terminal storage
Face characteristic in not is compared, and calculates similarity, such as:Based on the human face similarity degree for improving Ha u s d o r f f distances
Face (is divided into several feature point sets such as shape of face, eyes, nose, mouth first, calculates the improvement of each several part respectively by matched method
Ha u s d o r f f distances, are then weighted similarity).If in the presence of with the facial image feature received
Matched facial image, i.e. similarity highest and the photo classification for being higher than threshold value, then by the photo classification where the facial image
The photo classification of the photo to be sorted is denoted as, afterwards, the face figure of its associated photo classification is updated according to the facial image
As feature, facilitate the identification of the human face photo of the follow-up category;If there is no similarity be higher than threshold value photo classification when, institute
Setup module 24 is stated to be additionally operable to according to the new photo classification of the facial image feature-modeling and the facial image is associated with the photograph
Piece classification.Whole facial image features of photo classification can be specifically regenerated, it can also be according to the difference of similarity calculation
Degree update part facial image feature.
Further, for the identification of above-mentioned human face photo, the server 2 can also include:
Notification module 26, for receiving the face of the i.e. described transmission of photo classification managing device 1 of the user terminal
During identification request, the acquisition module 21 is notified to extract the facial image feature in facial image, so that the sort module 22
Classify according to facial image feature to the photo to be sorted.
It is treated point that is, determining to receive the photo classification managing device 1 in the notification module 26 having sent
While class photo or facial image, when also receiving the recognition of face request of user's instruction, that is, determine user in this time
The photo or facial image to be sorted passed needs to carry out the identification of face type, and the acquisition module 21 is notified to carry out face again
Image characteristics extraction and the sort module 22 is made to carry out the identification sort operation of photo or facial image to be sorted.
In the specific implementation, the acquisition module 21 can also set the photo classification of photo to be sorted according to user and ask
Seek to obtain the image content features of photo to be sorted.Such as:
User is by the photo classification managing device 1 in carrying photo to be sorted, photo thumbnail to be sorted or people
Which kind of in the message of face image, needed with a certain field value instruction server 2 in the message according to photo classification to be sorted
Photo, photo thumbnail to be sorted or facial image are classified;Alternatively, user carries photo to be sorted, treats point sending
While the message of class photo thumbnail or facial image, an instruction message is sent, and in a certain field of the instruction message
In value instruction by face classification, instruction according to interior, landscape, one etc. classifications classify, the acquisition module 21 is by corresponding
Unit or the image content features that obtain in photo to be sorted, thumbnail or facial image of unit combination it is subsequent to carry out
Judge identification.
And the recognition of face of the identification for being exclusively used in carrying out human face photo classification clusters server, it may not be necessary in volume
Assignor's face identification request in outer message.
Specifically, the first above-mentioned receiving unit 211, the second receiving unit 213 and the 3rd receiving unit 215 can be
One receiving unit realizes that the fisrt feature acquiring unit 212, second feature acquiring unit 213 and third feature obtain
Unit 216 can be that a feature acquiring unit is realized.
By the description of above-described embodiment, the embodiment of the present invention has the following advantages:
The embodiment of the present invention can carry out image content features to user by the photo that modes are got such as taking pictures, transmitting
Identification and classification to photo so that user need not carry out hand labeled or manual classification to photo, realize pair
The mechanized classification operation of photograph image content, the classification for preferably realizing the picture material according to photo carry out group to photo
It knits and manages, greatly facilitate user.Particularly it can realize the organization and management to photo automatically according to face characteristic,
The photo of same people is organized together, facilitates looking into for the photo that user dresss up to same people's different time different location difference
It sees.It additionally supports the establishment of new photo classification and new face, can effectively expand.
A kind of photo sort management of the present invention is described in detail below.
Refer to Fig. 4, be the present invention photo sort management first embodiment flow diagram, the present embodiment
In, the photo sort management includes:
S101:Server obtains the image content features of photo to be sorted.
Server by receive etc. modes get photo to be sorted that the photo classification managing device uploads or
After the thumbnail of photo to be sorted, the S101 is obtained to be sorted according to photo to be sorted or the thumbnail of photo to be sorted
The image content features of photo.
The S101 can be according to image recognition technology, to the photo to be sorted or the thumbnail of photo to be sorted received
Carry out image identification, read image content information therein (main scape information and/or background information) as image content features or
Image content information therein (main scape information and/or not into information) and metadata information are read as image content features.
User is needed to such as personage according to when particular photos are classified, and the photo classification managing device of user terminal can basis
User needs to perform particular photos Face datection operation, extracts the facial image in photo, and is sent to the server, institute
State image content features of the S101 using the facial image as the particular photos photo i.e. to be sorted for needing to classify, Huo Zheyong
The photo classification managing device at family end can also directly be sent to server needs such as personage to classify according to particular photos to clothes
Business device, the Face datection that photo is carried out by the server extracts facial image, and extracts the facial image feature in photo, institute
State image content features of the S101 using the facial image feature as the particular photos photo i.e. to be sorted for needing to classify.
S102:Server determines the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not.
Specifically, the S102 identifies head portrait feature of the main scape information in photo to be sorted for one or more people,
Personage can be then determined as according to classification;It such as identifies feature of the main scape information for a colored feature, then can be determined as plant
According to classification;It is outdoor characteristics such as to identify background information, it is determined that shines classification to be outdoor;If identify background information for sea
Feature, it is determined that shine classification for ocean.If identify the head portrait feature including one or more people, and background information is special for ocean
Sign, then can be identified as ocean personage's classification.Specifically it is identified by the similarity calculation of photo and photo classification to be sorted.Point
The service implement body of class can be carried by single classified service device, can also be by classified service device cloud (multiple classified service devices
The cloud of composition) it carries, to ensure the quick responses of the classification demand for meeting plurality of classes and more classification requests.
S103:The photo classification of the definite photo to be sorted is sent to user terminal by server.
It can be carried out data transmission between user terminal and server by existing communication network.
It is specified in addition, photo and its photo classification to be sorted can be also sent to by the server by S103 by user
Picture server in, be such as sent in the user picture spatial server that user specifies, so that the user picture space
Server stores the photo to be sorted into respective memory according to photo classification, when the user desires can be at any time in the use
(such as QQ space) shows the photo to be sorted according to photo classification in the space at family.
S104:User terminal carries out Classification Management according to the definite photo classification to the photo to be sorted.It is described
S104 is specifically included:The user terminal carries out classification to the photo to be sorted and shows according to the definite photo classification;
Or including:According to the photo classification of the photo to be sorted determined, the user terminal is the photo to be sorted
The classification logotype of the category is added, and the photo to be sorted to being with the addition of classification logotype carries out Classification Management.
The S104 can directly according to photo classification by the photo to be sorted be put into the photo group of its generic into
Row organization and management, including:File (classification group) is established on mobile phone, photographic hardcopy or soft copy are put into corresponding
Under file;The logic association of classification group and photo is established, such as:For one document of classification group maintenance, belong to such including all
Other photo.
Further photo classification logotype (can also be added in metadata) on photo, to ensure holding for classification results
It is continuous effective, even if the photo classification of the photo can be still determined after software reinstallation or system refitting according to the classification logotype of photo.
Further, the user terminal can also show photo by the organization and management to photo.Such as:User opens
The thumbnail that this document presss from both sides following photo is then presented in some corresponding file of classification group;For another example, user chooses a certain classification,
Its corresponding document is then read, the photo according to listed by document extracts its thumbnail to show.If classification logotype mark is being shone
On piece, the user terminal according to the demand for the generic that user to be shown, can also directly read the classification logotype of photo, will
The photo of the category finds and shows photo.
By the description of above-described embodiment, the embodiment of the present invention has the following advantages:
The embodiment of the present invention can carry out image content features to user by the photo that modes are got such as taking pictures, transmitting
Identification and classification to photo so that user need not carry out hand labeled or manual classification to photo, realize pair
The mechanized classification operation of photograph image content, the classification for preferably realizing the picture material according to photo carry out group to photo
It knits and manages, greatly facilitate user.Particularly it can realize the organization and management to photo automatically according to face characteristic,
The photo of same people is organized together, facilitates looking into for the photo that user dresss up to same people's different time different location difference
It sees.It additionally supports the establishment of new photo classification and new face, can effectively expand.
Refer to Fig. 5 again, be the present invention photo sort management second embodiment flow diagram, the present embodiment
The described method includes:
S201:Server carries out classification based training to the photo that is stored in preset photo library, determines photo classification and its right
The characteristics of image answered.
Wherein, the photo library includes the multiple pictures being collected into.The server is by S201 to being received in photo library
The substantial amounts of photo collected carries out classification based training, one or more photo classification and the photo are obtained according to image content features
Characteristics of image under classification.
In addition, server carries out Face datection, recognition of face, face cluster to the photo stored in preset photo library
Training, the face characteristic under one or more photo classification and the photo classification is obtained according to the facial image feature of each photo
With facial image (preserve corresponding facial image, available for subsequently according to the new facial image of the photo classification and it is all before
Facial image update the face characteristic of the photo classification together).
S202:Server obtains the image content features of photo to be sorted.
Specifically, the S202 can get the image content features of photo to be sorted in the following manner:
Mode one:
The server receives the thumbnail of photo to be sorted or the photo to be sorted, wherein, the photograph to be sorted
The thumbnail of piece is obtained after the photo obtained by photo acquisition device to it performs thumbnail extraction operation;
The server reads the image content features of the thumbnail of the photo to be sorted or the photo to be sorted,
Wherein, by image content information (main scape information and/or background information) or image content information, (main scape information and/or background are believed
Breath) and image content features of the metadata information as the photo to be sorted.
Mode two:
The server receives facial image, extracts the facial image feature in facial image, and by the facial image
Feature is denoted as the image content features of the photo to be sorted;
Wherein, the facial image is to be carried out Face datection to the photo to be sorted by the user terminal and extracted
It arrives.
Mode three:
The photo to be sorted that the server reception is sent by the user terminal;
The server carries out the photo to be sorted Face datection extraction facial image, and extracts in facial image
The facial image feature is denoted as the image content features of the photo to be sorted by facial image feature.
Further, for the thumbnail of common photo to be sorted or photo to be sorted, before the S202, go back
Including step:
The server judges receiving user terminal in transmission photo to be sorted or the thumbnail of photo to be sorted
While, if receive the photo classification of the thumbnail of photo to be sorted that user sent on this or photo to be sorted
Request is set.The photo classification set request can be an individual instruction message or carrying it is described to be sorted
The content of certain field instruction in the message of the thumbnail of photo or photo to be sorted.
If the photo classification that the server receives user terminal transmission sets request, whether local terminal is determined whether
Support determines the identification of requested photo classification;
If supporting, the server is the requested photo classification of user setting, and performs the S202;
If not supporting, the server collects the photo corresponding to requested photo classification, and the photo to being collected into
Classification based training is carried out, obtains the image content features of the photo being collected into, and according to the image of the photo being collected into
Content characteristic creates the characteristics of image under requested photo classification and the photo classification.For example, when user requires snow mountain to shine class
It, can be by with words such as snow mountains if server determines that not preserving snow mountain shines classification and its image content features by judging when other
It is scanned for as keyword, the picture searched is stored in photo library, and by the S304 to collecting in photo library
Photo corresponding to the photo classification classification carries out classification based training, obtains the image content features and wound of requested photo classification
Build the photo classification.
And for needing the photo or facial image to be sorted of progress recognition of face, before the S202, further include
Step:
The server judges receiving user terminal while photo or facial image to be sorted is sent, if
Receive the recognition of face request of user terminal transmission;
If so, perform the S202.
It can specifically be set and asked according to the photo classification of user, corresponding mode is selected to carry out obtaining for image content features
It takes.Such as:User's request by face classification, then extracts facial image feature, user is asked photograph to be sorted to photo to be sorted
Piece landscape is classified, then extracts the content in background as image content features.
S203:Server determines the photo class of the photo to be sorted according to the image content features of the photo to be sorted
Not.
Specifically, for the image content features obtained in the mode one in the S202, the S203 can pass through:It calculates
The image content features of the photo to be sorted and the similarity of the characteristics of image under each photo classification;According to the phase being calculated
Like degree, using similarity highest and similarity higher than threshold value photo classification as the photo to be sorted photo classification
For the image content features obtained in mode two in the S202 or mode three, described in the S203 will be calculated
The facial image feature of photo to be sorted and the similarity of the face characteristic in each photo classification of local terminal storage;By similarity most
High and higher than threshold value photo kind judging is the photo classification of the photo to be sorted, and the facial image has been associated with this
It is determined as the photo classification of the photo to be sorted, and the facial image of its associated photo classification is updated according to the facial image
Feature;If there is no the photo classifications that similarity is higher than threshold value, the server is according to the new photograph of the facial image feature-modeling
The facial image is simultaneously associated with the photo classification by piece classification.
S204:The photo classification of the definite photo to be sorted is sent to user terminal by server.
S205:The user terminal carries out Classification Management according to the definite photo classification to the photo to be sorted.
Specifically it may include:The user terminal divides the photo to be sorted according to the definite photo classification
Class is shown.Or it may include:User terminal is described to be sorted according to the photo classification of the photo to be sorted determined
Photo adds the classification logotype of the category, can specifically mark classification logotype on photo, such as:It is added in metadata, with
Ensure the continuous and effective of classification results, even if still can determine this according to the classification logotype of photo after software reinstallation or system refitting
The photo classification of photo.Then Classification Management is carried out to the photo to be sorted for being with the addition of classification logotype, it specifically can direct root
The photo to be sorted is put into the photo group of its generic according to photo classification and is organized and managed, including:In mobile phone
On establish file (classification group), photographic hardcopy or soft copy are put under corresponding file;Establish classification group and photograph
The logic association of piece, such as:For one document of classification group maintenance, including all photos for belonging to the category.
By the description of above-described embodiment, the embodiment of the present invention has the following advantages:
The embodiment of the present invention can carry out image content features to user by the photo that modes are got such as taking pictures, transmitting
Identification and classification to photo so that user need not carry out hand labeled or manual classification to photo, realize pair
The mechanized classification operation of photograph image content, the classification for preferably realizing the picture material according to photo carry out group to photo
It knits and manages, greatly facilitate user.Particularly it can realize the organization and management to photo automatically according to face characteristic,
The photo of same people is organized together, facilitates looking into for the photo that user dresss up to same people's different time different location difference
It sees.It additionally supports the establishment of new photo classification and new face, can effectively expand.
One of ordinary skill in the art will appreciate that realizing all or part of flow in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer read/write memory medium
In, the program is upon execution, it may include such as the flow of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above disclosure is only the preferred embodiments of the present invention, cannot limit the right model of the present invention with this certainly
It encloses, therefore equivalent variations made according to the claims of the present invention, it is still within the scope of the present invention.
Claims (20)
1. a kind of photo sort management, which is characterized in that including:
Server receives photo to be sorted from user terminal;
The server reads the image content information of the photo to be sorted, and/or the content member number of the photo to be sorted
It is believed that breath, special as the picture material of the photo to be sorted using described image content information and/or content metadata information
Sign;
The server carries out the photo stored in preset photo library face cluster training and non-face cluster is trained, according to
The image content features of each photo obtain the characteristics of image under one or more photo classification and the photo classification, photo classification
Including the photo classification on face and on non-face photo classification;
The server according to the user terminal classification indicate, by the image content features of the photo to be sorted on
Characteristics of image under the photo classification of face and the photo classification be compared or on non-face photo classification and should
Characteristics of image under photo classification is compared, and the photo classification of the photo to be sorted is determined according to comparative result;
The photo classification of the definite photo to be sorted is sent to user terminal by the server, the user terminal according to
The definite photo classification carries out classification to the photo to be sorted and shows.
2. the method as described in claim 1, which is characterized in that the photograph that the photo to be sorted is determined according to comparative result
It the step of piece classification, specifically includes:
The server obtains the figure under the image content features and each photo classification of the photo to be sorted according to comparative result
As the similarity of feature;
According to obtained similarity, using similarity highest and higher than threshold value photo classification as the photo to be sorted photo
Classification.
3. method as claimed in claim 2, which is characterized in that further include:
It receives the photo classification that user terminal is sent and request is set, judge whether local terminal supports the knowledge to requested photo classification
Que Ding not;
If supporting, the server is the requested photo classification of user setting, so that the server is according to set photograph
Piece classification is to photo classification to be sorted;
If not supporting, the server collects the photo corresponding to requested photo classification, and the photo to being collected into carries out
Classification based training obtains the image content features of the photo being collected into, and according to the picture material of the photo being collected into
Characteristics of image under the requested photo classification of feature-modeling and the photo classification.
4. the method as described in claim 1, which is characterized in that the server obtains the image content features of photo to be sorted
The step of before, further include:
The server carries out the photo stored in preset photo library Face datection, recognition of face, face cluster training, root
The face characteristic under one or more photo classification and the photo classification is obtained according to the facial image feature of each photo.
5. method as claimed in claim 4, which is characterized in that the server obtains the image content features of photo to be sorted
The step of, including:
The server receives facial image, extracts the facial image feature in facial image, and by the facial image feature
It is denoted as the image content features of the photo to be sorted;
Wherein, the facial image is that the photo to be sorted is carried out Face datection and extracted to obtain by the user terminal
's.
6. method as claimed in claim 4, which is characterized in that the server obtains the image content features of photo to be sorted
The step of, including:
The server receives photo to be sorted;
The server carries out Face datection to the photo to be sorted, extracts facial image, and extracts the people in facial image
The facial image feature is denoted as the image content features of the photo to be sorted by face image feature.
7. such as claim 4 to 6 any one of them method, which is characterized in that the server is according to the photo to be sorted
Image content features the step of determining the photo classification of the photo to be sorted include:
The server calculates the face in the facial image feature of the photo to be sorted and each photo classification of local terminal storage
The similarity of feature;
By similarity highest and higher than the photo classification that the photo kind judging of threshold value is the photo to be sorted, and by the face
Image is associated with this and has determined that as the photo classification of the photo to be sorted, and updates its associated photo according to the facial image
The face characteristic of classification;
If there is no the photo classifications that similarity is higher than threshold value, the server is according to the new photo of the facial image feature-modeling
The facial image is simultaneously associated with the photo classification by classification.
8. the method for claim 7, which is characterized in that the server is sent receiving the user terminal
When recognition of face is asked, the facial image feature in extraction facial image is performed, to be treated according to facial image feature to described
Classification photo is classified.
9. such as claim 1 to 6 any one of them method, which is characterized in that further include:
The user terminal, should for the photo addition to be sorted according to the photo classification of the photo to be sorted determined
The classification logotype of classification, and the photo to be sorted to being with the addition of classification logotype is managed.
10. a kind of server, which is characterized in that including:
Acquisition module, for receiving photo to be sorted from user terminal, read the photo to be sorted image content information,
And/or the content metadata information of the photo to be sorted, described image content information and/or content metadata information are made
For the image content features of the photo to be sorted;
Setup module is trained for carrying out face cluster training and non-face cluster to the photo stored in preset photo library,
The characteristics of image under one or more photo classification and the photo classification, photo are obtained according to the image content features of each photo
Classification is included on the photo classification of face and on non-face photo classification;
Sort module, for according to the classification of the user terminal indicate, by the image content features of the photo to be sorted with
Be compared on the characteristics of image under the photo classification and the photo classification of face or on non-face photo classification
And the characteristics of image under the photo classification is compared, and the photo classification of the photo to be sorted is determined according to comparative result;
Communication module, the classification of the photo to be sorted for the sort module to be determined is sent to user terminal, described
It is aobvious to carry out the photo to be sorted classification according to the definite photo classification for user terminal.
11. server as claimed in claim 10, which is characterized in that the sort module includes:
First computing unit, for calculating the image content features of the photo to be sorted and the characteristics of image under each photo classification
Similarity;
First determination unit, the picture material of the photo to be sorted for being calculated according to first computing unit are special
Sign and the similarity of the characteristics of image under each photo classification, using similarity highest and similarity higher than threshold value photo classification as
The photo classification of the photo to be sorted.
12. server as claimed in claim 11, which is characterized in that further include:
Judgment module during for setting request in the photo classification for receiving user terminal transmission, judges whether local terminal is supported pair
The identification of requested photo classification;
The setup module is additionally operable to when the judging result of the judgment module is supports, is the requested photo of user setting
Classification, so as to the sort module according to set photo classification to photo classification to be sorted;If judging result is not support,
The photo corresponding to requested photo classification is collected, and the photo to being collected into carries out classification based training, obtains described be collected into
Photo image content features, and create requested photo classification according to the image content features of the photo being collected into
And the characteristics of image under the photo classification.
13. server as claimed in claim 10, which is characterized in that
The setup module is additionally operable to gather the photo progress Face datection, recognition of face, the face that store in preset photo library
Class is trained, and the face obtained according to the facial image feature of each photo under one or more photo classification and the photo classification is special
Sign.
14. server as claimed in claim 13, which is characterized in that the acquisition module includes:
Second receiving unit, for receiving facial image;
Second feature acquiring unit, it is special for extracting the facial image in the facial image that second receiving unit receives
It levies, and the facial image feature is denoted as to the image content features of the photo to be sorted;
Wherein, the facial image is that the photo to be sorted is carried out Face datection and extracted to obtain by the user terminal
's.
15. server as claimed in claim 13, which is characterized in that the acquisition module includes:
3rd receiving unit, for receiving photo to be sorted;
Third feature acquiring unit for carrying out Face datection to the photo to be sorted, extracts facial image, and extracts face
The facial image feature is denoted as the image content features of the photo to be sorted by the facial image feature in image.
16. such as claim 13 to 15 any one of them server, which is characterized in that the sort module includes:
Second computing unit, for calculating in each photo classification that the facial image feature of the photo to be sorted is stored with local terminal
Face characteristic similarity;
Second determination unit for the similarity being calculated according to second computing unit, by similarity highest and is higher than
The photo kind judging of threshold value is the photo classification of the photo to be sorted;
The setup module is additionally operable to for the facial image to be associated with the photo classification having determined that as the photo to be sorted, and root
The face characteristic of its associated photo classification is updated according to the facial image, if there is no the photo classification that similarity is higher than threshold value,
According to the new photo classification of the facial image feature-modeling and the facial image is associated with the photo classification.
17. a kind of photo classification managing device, which is characterized in that including:
Photo acquisition module, for obtaining photo to be sorted;
Communication module, the photo to be sorted for the photo acquisition module to be obtained are sent to server, and for receive by
The photo classification for the photo to be sorted that server determines;
The method of determination of the photo classification includes:The server read the photo to be sorted image content information and/
Or the content metadata information of the photo to be sorted, using described image content information and/or content metadata information as institute
State the image content features of photo to be sorted;The server carries out face cluster instruction to the photo stored in preset photo library
Practice with after non-face cluster training, one or more photo classification and the photo are obtained according to the image content features of each photo
Characteristics of image under classification, wherein photo classification are included on the photo classification of face and on non-face photo classification;Institute
It states server to indicate according to the classification of the photo classification managing device, by the image content features of the photo to be sorted and pass
Characteristics of image under the photo classification and the photo classification of face be compared or on non-face photo classification and
Characteristics of image under the photo classification is compared, the photo classification that the server is determined according to comparative result;
Classification Management module, for according to the definite photo classification, carrying out classification to the photo to be sorted and showing.
18. photo classification managing device as claimed in claim 17, which is characterized in that
The communication module is additionally operable to send the setting request of photo classification to the server, so that the server is according to described in
Photo classification sets the photo classification that request carries to classify the thumbnail of the photo to be sorted or the photo to be sorted;
Alternatively, it is additionally operable to send recognition of face request to the server in order to which the server extracts the face figure in facial image
As feature, to classify according to facial image feature to the photo to be sorted or facial image.
19. the photo classification managing device as described in claim 17 or 18, which is characterized in that the Classification Management module bag
It includes:
Classification display unit, for according to the definite photo classification, carrying out classification to the photo to be sorted and showing;
And/or:
Indexing unit is the photograph to be sorted for the photo classification of the photo to be sorted received according to the communication module
Piece adds the classification logotype of the photo classification;
Administrative unit, for carrying out Classification Management to the photo to be sorted for being with the addition of classification logotype.
20. a kind of photo sort management system, which is characterized in that including:Photo classification managing device and server, wherein,
The photo classification managing device, for obtaining photo to be sorted, and by the photo to be sorted or described to be sorted
The thumbnail of photo is sent to the server;
The server for receiving photo to be sorted from photo classification managing device, reads the image of the photo to be sorted
The content metadata information of content information, and/or the photo to be sorted, by described image content information and/or content member number
It is believed that image content features of the breath as the photo to be sorted, face cluster is carried out to the photo stored in preset photo library
Training and non-face cluster are trained, one or more photo classification and the photo are obtained according to the image content features of each photo
Characteristics of image under classification, photo classification is included on the photo classification of face and on non-face photo classification, according to institute
The classification instruction of photo classification managing device is stated, by the image content features of the photo to be sorted and the photo class on face
Not and the photo classification under characteristics of image be compared or under non-face photo classification and the photo classification
Characteristics of image is compared, and the photo classification of the photo to be sorted is determined according to comparative result, described to be sorted by what is determined
The photo classification of photo is sent to photo classification managing device;
The photo classification managing device is additionally operable to receive the photo classification of the photo to be sorted determined by server, and
According to the definite photo classification, classification is carried out to the photo to be sorted and is shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711384927.XA CN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210013824.3A CN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
CN201711384927.XA CN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210013824.3A Division CN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108073948A true CN108073948A (en) | 2018-05-25 |
Family
ID=48755095
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711384927.XA Pending CN108073948A (en) | 2012-01-17 | 2012-01-17 | A kind of photo sort management, server, apparatus and system |
CN201210013824.3A Active CN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210013824.3A Active CN103207870B (en) | 2012-01-17 | 2012-01-17 | Photo classification management method, server, device and system |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN108073948A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109948734A (en) * | 2019-04-02 | 2019-06-28 | 北京旷视科技有限公司 | Image clustering method, device and electronic equipment |
WO2020020226A1 (en) * | 2018-07-27 | 2020-01-30 | 中兴通讯股份有限公司 | Photo classification method, device, computer-readable medium, and system |
WO2020192736A1 (en) * | 2019-03-26 | 2020-10-01 | 华为技术有限公司 | Object recognition method and device |
WO2022193232A1 (en) * | 2021-03-18 | 2022-09-22 | 京东方科技集团股份有限公司 | Face clustering method and apparatus, classification storage method, medium, and electronic device |
Families Citing this family (74)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103559236A (en) * | 2013-10-25 | 2014-02-05 | 华为终端有限公司 | Image displaying method and terminal |
CN104750688A (en) * | 2013-12-25 | 2015-07-01 | 鸿富锦精密工业(深圳)有限公司 | Photo management method and system |
CN103744996A (en) * | 2014-01-23 | 2014-04-23 | 惠州Tcl移动通信有限公司 | Mobile terminal album classifying method and system |
CN104915344B (en) * | 2014-03-10 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
WO2015139204A1 (en) * | 2014-03-18 | 2015-09-24 | 华为终端有限公司 | Picture management method and device |
CN104951426A (en) * | 2014-03-26 | 2015-09-30 | 联想移动通信软件(武汉)有限公司 | Taken photo classified processing method and device and terminal equipment |
CN104980641B (en) * | 2014-04-04 | 2019-01-08 | 宏碁股份有限公司 | Electronic device and its image inspection method |
CN103995889B (en) * | 2014-06-03 | 2017-11-03 | 广东欧珀移动通信有限公司 | Picture classification method and device |
US20180107660A1 (en) * | 2014-06-27 | 2018-04-19 | Amazon Technologies, Inc. | System, method and apparatus for organizing photographs stored on a mobile computing device |
US9479672B2 (en) * | 2014-07-18 | 2016-10-25 | Sony Mobile Communications Inc. | Method and system for efficient transfer of digital images captured by a lifelog camera |
CN104168378B (en) * | 2014-08-19 | 2018-06-05 | 上海卓易科技股份有限公司 | A kind of picture group technology and device based on recognition of face |
CN104216976B (en) * | 2014-09-01 | 2018-09-04 | 广东欧珀移动通信有限公司 | A kind of mobile terminal picture grouping inspection method and system |
CN105654101B (en) * | 2014-11-11 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
CN104408428B (en) * | 2014-11-28 | 2018-05-15 | 东莞宇龙通信科技有限公司 | A kind of processing method and processing device of same scene photo |
CN104572905B (en) * | 2014-12-26 | 2018-09-04 | 小米科技有限责任公司 | Print reference creation method, photo searching method and device |
WO2016134506A1 (en) * | 2015-02-26 | 2016-09-01 | 刘一佳 | Method for feature reminder when screening photographs and mobile terminal |
US10185894B2 (en) | 2015-03-26 | 2019-01-22 | Beijing Kuangshi Technology Co., Ltd. | Picture management method and device, picture synchronization method and device |
CN104731979A (en) * | 2015-04-16 | 2015-06-24 | 广东欧珀移动通信有限公司 | Method and device for storing all exclusive information resources of specific user |
CN106156247B (en) * | 2015-04-28 | 2020-09-15 | 中兴通讯股份有限公司 | Image management method and device |
CN104933102A (en) * | 2015-05-29 | 2015-09-23 | 努比亚技术有限公司 | Picturing storage method and device |
CN106412213A (en) * | 2015-07-27 | 2017-02-15 | 中兴通讯股份有限公司 | Contact person information processing method and device and mobile terminal |
CN105205093B (en) * | 2015-07-28 | 2019-04-23 | 小米科技有限责任公司 | The method and device that picture is handled in picture library |
CN105243098B (en) * | 2015-09-16 | 2018-10-26 | 小米科技有限责任公司 | The clustering method and device of facial image |
CN105824862A (en) * | 2015-10-20 | 2016-08-03 | 维沃移动通信有限公司 | Image classification method based on electronic equipment and electronic equipment |
EP3361423B1 (en) | 2015-10-30 | 2022-12-14 | Morpho, Inc. | Learning system, learning device, learning method, learning program, teacher data creation device, teacher data creation method, teacher data creation program, terminal device, and threshold value changing device |
CN105512255A (en) * | 2015-12-01 | 2016-04-20 | 上海斐讯数据通信技术有限公司 | Picture screening method and device and mobile terminal |
CN105426515B (en) | 2015-12-01 | 2018-12-18 | 小米科技有限责任公司 | video classifying method and device |
CN105554340A (en) * | 2015-12-09 | 2016-05-04 | 深圳市华德安科技有限公司 | Image processing method and device based on law enforcement recorder |
CN105574155A (en) * | 2015-12-16 | 2016-05-11 | 广东欧珀移动通信有限公司 | Photo search method and device |
CN105608425B (en) * | 2015-12-17 | 2019-02-15 | 小米科技有限责任公司 | The method and device of classification storage is carried out to photo |
CN105608189B (en) * | 2015-12-23 | 2019-10-11 | 北京金山安全软件有限公司 | Picture classification method and device and electronic equipment |
CN105653152A (en) * | 2015-12-23 | 2016-06-08 | 北京金山安全软件有限公司 | Picture processing method and device and electronic equipment |
CN106919604A (en) * | 2015-12-25 | 2017-07-04 | 北京奇虎科技有限公司 | Electron album management method and device |
CN105740379A (en) * | 2016-01-27 | 2016-07-06 | 北京汇图科技有限责任公司 | Photo classification management method and apparatus |
WO2017128266A1 (en) * | 2016-01-28 | 2017-08-03 | 杨钰 | Method of sorting images and mobile terminal |
WO2017128265A1 (en) * | 2016-01-28 | 2017-08-03 | 杨钰 | Method of notifying information when sorting images and a mobile terminal |
WO2017128264A1 (en) * | 2016-01-28 | 2017-08-03 | 杨钰 | Method of acquiring data relating to using image sorting technology on the basis of facial recognition and mobile terminal |
CN107133629B (en) * | 2016-02-29 | 2020-09-04 | 百度在线网络技术(北京)有限公司 | Picture classification method and device and mobile terminal |
CN105740850A (en) * | 2016-03-04 | 2016-07-06 | 北京小米移动软件有限公司 | Method and device for classifying photos |
CN105912590A (en) * | 2016-04-01 | 2016-08-31 | 乐视控股(北京)有限公司 | Classified storage method and device for pictures and mobile terminal |
CN106407369A (en) * | 2016-09-09 | 2017-02-15 | 华南理工大学 | Photo management method and system based on deep learning face recognition |
CN106385502B (en) * | 2016-09-19 | 2020-07-17 | 珠海大横琴科技发展有限公司 | Photo arrangement method and mobile terminal |
CN106446955A (en) * | 2016-09-29 | 2017-02-22 | 宇龙计算机通信科技(深圳)有限公司 | Picture processing method and apparatus |
CN106528094A (en) * | 2016-10-20 | 2017-03-22 | 惠州Tcl移动通信有限公司 | A similarity-based application icon classifying method and system |
CN106874918A (en) * | 2017-02-23 | 2017-06-20 | 上海与德信息技术有限公司 | A kind of photo store method and device |
CN106980658A (en) * | 2017-03-15 | 2017-07-25 | 北京旷视科技有限公司 | Video labeling method and device |
CN108805148B (en) * | 2017-04-28 | 2022-01-11 | 富士通株式会社 | Method of processing image and apparatus for processing image |
CN107292749A (en) * | 2017-08-04 | 2017-10-24 | 平安科技(深圳)有限公司 | Car damages sorting technique, system and the readable storage medium storing program for executing of certificate photograph |
CN107832765A (en) * | 2017-09-13 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | Picture recognition to including word content and picture material |
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 |
CN107729815B (en) * | 2017-09-15 | 2020-01-14 | Oppo广东移动通信有限公司 | Image processing method, image processing device, mobile terminal and computer readable storage medium |
CN107679559B (en) * | 2017-09-15 | 2020-01-10 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and mobile terminal |
WO2019051797A1 (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 computer-readable storage medium |
WO2019051795A1 (en) * | 2017-09-15 | 2019-03-21 | 广东欧珀移动通信有限公司 | Image processing method and device, terminal, server, and computer-readable storage medium |
EP3680785A4 (en) * | 2017-09-15 | 2020-09-23 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Image processing method and apparatus, computer device, and non-volatile readable storage medium |
CN107679560B (en) * | 2017-09-15 | 2021-07-09 | Oppo广东移动通信有限公司 | Data transmission method and device, mobile terminal and computer readable storage medium |
CN107679561A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Image processing method and device, system, computer equipment |
CN107679563A (en) * | 2017-09-15 | 2018-02-09 | 广东欧珀移动通信有限公司 | Image processing method and device, system, computer equipment |
CN107729384A (en) * | 2017-09-18 | 2018-02-23 | 维沃移动通信有限公司 | Image ranking method and mobile terminal |
CN108121762A (en) * | 2017-11-24 | 2018-06-05 | 努比亚技术有限公司 | A kind of image processing method, mobile terminal and computer storage media |
CN107992822B (en) | 2017-11-30 | 2020-04-10 | Oppo广东移动通信有限公司 | Image processing method and apparatus, computer device, computer-readable storage medium |
CN107958069B (en) * | 2017-12-05 | 2020-05-26 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
CN108304882B (en) * | 2018-02-07 | 2022-03-04 | 腾讯科技(深圳)有限公司 | Image classification method and device, server, user terminal and storage medium |
CN110489594A (en) * | 2018-05-14 | 2019-11-22 | 北京松果电子有限公司 | Image vision mask method, device, storage medium and equipment |
CN108830235B (en) * | 2018-06-21 | 2020-11-24 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating information |
CN109934214A (en) * | 2019-02-22 | 2019-06-25 | 深兰科技(上海)有限公司 | A kind of training of object type, detection method and device |
CN110598032B (en) * | 2019-09-25 | 2022-06-14 | 京东方艺云(杭州)科技有限公司 | Image tag generation method, server and terminal equipment |
CN110703972B (en) * | 2019-09-29 | 2021-04-06 | 维沃移动通信有限公司 | File control method and electronic equipment |
CN110956680A (en) * | 2019-10-28 | 2020-04-03 | 恒大智慧科技有限公司 | Postcard making method and device and storage medium |
CN110909368B (en) * | 2019-11-07 | 2023-09-05 | 腾讯科技(深圳)有限公司 | Data encryption method, device and computer readable storage medium |
CN110874420A (en) * | 2019-11-09 | 2020-03-10 | 上海光数信息科技有限公司 | Picture information processing system and method |
CN111666441A (en) * | 2020-04-24 | 2020-09-15 | 北京旷视科技有限公司 | Method, device and electronic system for determining personnel identity type |
CN111666262B (en) * | 2020-05-28 | 2021-06-22 | 重庆中联信息产业有限责任公司 | Working method for extracting feature points of massive medical images in network attached storage NAS state |
CN111857478B (en) * | 2020-07-17 | 2022-02-11 | 北京百度网讯科技有限公司 | Image layout method and device, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050271352A1 (en) * | 2002-09-26 | 2005-12-08 | Kouji Yokouchi | Apparatus and program for image classification |
CN101510205A (en) * | 2009-03-16 | 2009-08-19 | 广州市有福数码科技有限公司 | Method for implementing automatically clustering photographs, apparatus and system |
CN101894147A (en) * | 2010-06-29 | 2010-11-24 | 深圳桑菲消费通信有限公司 | Electronic photo album clustering management method |
CN101990667A (en) * | 2008-04-02 | 2011-03-23 | 谷歌公司 | Method and apparatus to incorporate automatic face recognition in digital image collections |
CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9075808B2 (en) * | 2007-03-29 | 2015-07-07 | Sony Corporation | Digital photograph content information service |
US8254684B2 (en) * | 2008-01-02 | 2012-08-28 | Yahoo! Inc. | Method and system for managing digital photos |
US9639780B2 (en) * | 2008-12-22 | 2017-05-02 | Excalibur Ip, Llc | System and method for improved classification |
CN102033958B (en) * | 2010-12-28 | 2013-04-17 | Tcl商用信息科技(惠州)股份有限公司 | Photo sort management system and method |
-
2012
- 2012-01-17 CN CN201711384927.XA patent/CN108073948A/en active Pending
- 2012-01-17 CN CN201210013824.3A patent/CN103207870B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050271352A1 (en) * | 2002-09-26 | 2005-12-08 | Kouji Yokouchi | Apparatus and program for image classification |
CN101990667A (en) * | 2008-04-02 | 2011-03-23 | 谷歌公司 | Method and apparatus to incorporate automatic face recognition in digital image collections |
CN101510205A (en) * | 2009-03-16 | 2009-08-19 | 广州市有福数码科技有限公司 | Method for implementing automatically clustering photographs, apparatus and system |
CN101894147A (en) * | 2010-06-29 | 2010-11-24 | 深圳桑菲消费通信有限公司 | Electronic photo album clustering management method |
CN102129451A (en) * | 2011-02-17 | 2011-07-20 | 上海交通大学 | Method for clustering data in image retrieval system |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020020226A1 (en) * | 2018-07-27 | 2020-01-30 | 中兴通讯股份有限公司 | Photo classification method, device, computer-readable medium, and system |
WO2020192736A1 (en) * | 2019-03-26 | 2020-10-01 | 华为技术有限公司 | Object recognition method and device |
CN109948734A (en) * | 2019-04-02 | 2019-06-28 | 北京旷视科技有限公司 | Image clustering method, device and electronic equipment |
WO2022193232A1 (en) * | 2021-03-18 | 2022-09-22 | 京东方科技集团股份有限公司 | Face clustering method and apparatus, classification storage method, medium, and electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN103207870B (en) | 2020-06-02 |
CN103207870A (en) | 2013-07-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108073948A (en) | A kind of photo sort management, server, apparatus and system | |
CN104462738B (en) | A kind of methods, devices and systems of mark medical image | |
WO2017197959A1 (en) | Image processing method, apparatus, and device | |
CN103155477B (en) | Data syn-chronization in DCE | |
CN103870485B (en) | Method and device for achieving augmented reality application | |
CN103412951B (en) | Human connection association analysis based on portrait photographs management System and method for | |
CN102741882B (en) | Image classification device, image classification method, integrated circuit, modeling apparatus | |
CN104750737B (en) | A kind of photograph album management method and device | |
CN106165386A (en) | For photo upload and the automatic technology of selection | |
CN108463814A (en) | A kind of medical image mask method and system | |
CN109213882A (en) | Picture sort method and terminal | |
CN108228844A (en) | A kind of picture screening technique and device, storage medium, computer equipment | |
CN108198130A (en) | Image processing method, device, storage medium and electronic equipment | |
CN106777905A (en) | The method that many image center service systems of tele-medicine and its terminal obtain data | |
CN107392238A (en) | Outdoor knowledge of plants based on moving-vision search expands learning system | |
CN108764051A (en) | Image processing method, device and mobile terminal | |
CN106485220A (en) | Face identification method, the intelligent glasses with face identification functions and server | |
CN110049180A (en) | Shoot posture method for pushing and device, intelligent terminal | |
CN107360366A (en) | Photographic method, device, storage medium and electronic equipment | |
CN107729534A (en) | Caste identifying system and method based on big data Cloud Server | |
CN110084267A (en) | Portrait clustering method, device, electronic equipment and readable storage medium storing program for executing | |
CN201751901U (en) | Large-scale database portrait search comparison system based on biometric portrait identification technology | |
CN105426925B (en) | Image labeling method and electronic equipment | |
CN106156247A (en) | Image management method and device | |
CN105917703A (en) | Advertising storage capabilities accessible via a wireless local area network |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180525 |
|
RJ01 | Rejection of invention patent application after publication |