CN111382770A - Picture clustering method, device, equipment and storage medium - Google Patents
Picture clustering method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111382770A CN111382770A CN201811643244.6A CN201811643244A CN111382770A CN 111382770 A CN111382770 A CN 111382770A CN 201811643244 A CN201811643244 A CN 201811643244A CN 111382770 A CN111382770 A CN 111382770A
- Authority
- CN
- China
- Prior art keywords
- picture
- pictures
- clustering
- similarity
- attribute information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a picture clustering method, a device, equipment and a storage medium, wherein the method can comprise the steps of determining attribute information of each picture in a plurality of pictures; pre-classifying a plurality of pictures according to the attribute information to obtain a plurality of picture subsets, wherein each picture subset comprises at least one picture; determining the similarity between pictures in each picture subset; and clustering each picture subset according to the similarity between the pictures. The invention can improve the image clustering speed and improve the user experience.
Description
Technical Field
The present invention relates to the field of information processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for clustering pictures.
Background
With the development of networks and electronic technologies, more and more users are familiar with electronic devices for storing or referring to pictures.
When a large number of pictures are stored in the electronic device, clustering is usually performed on a plurality of pictures to facilitate the user to look up the pictures. At present, feature information can be extracted from each graph in all the pictures to determine the similarity between the pictures, and then the pictures are clustered.
However, feature extraction, comparison and the like are performed on all the pictures, so that the picture clustering speed is low, and the user experience is influenced.
Disclosure of Invention
The invention provides a picture clustering method, a picture clustering device, picture clustering equipment and a storage medium, which are used for improving picture clustering speed and improving user experience.
In a first aspect, the present invention provides a method for clustering pictures, including:
determining attribute information of each picture in a plurality of pictures;
pre-classifying the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset comprises at least one picture;
determining the similarity between pictures in each picture subset;
and clustering each picture subset according to the similarity between the pictures.
In a second aspect, the present invention further provides an image clustering device, including:
the first determining module is used for determining the attribute information of each picture in the plurality of pictures;
the first classification module is used for performing pre-classification on the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset comprises at least one picture;
a second determining module, configured to determine similarity between pictures in each of the picture subsets;
and the second classification module is used for clustering each picture subset according to the similarity between the pictures.
In a third aspect, the present invention provides a picture clustering device, including: a memory and a processor; the memory is connected with the processor;
the memory to store program instructions;
the processor is configured to, when the program instructions are executed, implement the picture clustering method according to the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the picture clustering method according to the first aspect.
The invention provides a picture clustering method, a device, equipment and a storage medium, which can obtain a plurality of picture subsets by determining attribute information of each picture in a plurality of pictures and pre-classifying the plurality of pictures according to the attribute information, wherein each picture subset comprises at least one picture, so that the similarity between the pictures in each picture subset is determined, and each picture subset is clustered according to the similarity between the pictures. In the method, the pictures are pre-classified according to the attribute information of the pictures, and the pictures in each picture subset can be clustered only by determining the similarity among the pictures in each picture subset without determining the similarities of all the pictures, so that the processing speed of picture clustering is effectively improved, the processing time of picture clustering is shortened, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, a brief description will be given below of the drawings required for the embodiments or the technical solutions in the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a first flowchart of a picture clustering method according to an embodiment of the present invention;
fig. 2 is a second flowchart of a picture clustering method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a picture clustering device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a picture clustering device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first", "second", third "and the like in the various parts of the embodiments and drawings are used for distinguishing similar objects and not necessarily for describing a particular order or sequence. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The method flow diagrams of the embodiments of the invention described below are merely exemplary and do not necessarily include all of the contents and steps, nor do they necessarily have to be performed in the order described. For example, some steps may be broken down and some steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
The functional blocks in the block diagrams referred to in the embodiments of the present invention described below are only functional entities and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processors and/or microcontrollers.
The following describes a picture clustering method, a picture clustering device, picture clustering equipment and a picture clustering storage medium provided by the embodiments of the present invention with reference to a plurality of examples. The image clustering method can be realized by the terminal equipment and can also be executed by the server. The terminal device is, for example, any one of a desktop computer, a notebook computer, a Personal Digital Assistant (PDA), a smart phone, a tablet computer, and the like having a picture viewing function. The terminal device having the picture viewing function may be installed or integrated with a picture application, for example. The server may be a server of the picture application or a cloud server. The picture application program can be a picture application program carried by an operating system of the terminal equipment, can also be a picture application program downloaded and installed by the terminal equipment, and can also be a picture subprogram of other application programs. The picture application may be referred to as an album application, a photographing application, a picture processing application, and the like. That is to say, the image clustering method according to the embodiment of the present application may be executed by a terminal device, and may also be executed by a server.
In one example, for application on a terminal device, picture clustering is performed by the terminal device. When a plurality of pictures are stored in the terminal equipment, the pictures can be pre-classified and the picture subsets obtained by pre-classification can be clustered by executing the following picture clustering method. Therefore, when the user looks up the pictures through the terminal equipment, the clustered pictures can be looked up, the expected target pictures can be simply and directly found, the browsing among a plurality of pictures is not needed, and the user experience is improved.
In another example, for application on a server, the server performs picture clustering. The server stores a plurality of pictures, and can pre-classify the plurality of pictures and cluster the pre-classified picture subsets by executing the following picture clustering method. In this way, when a user desires to refer to a picture, the server can be accessed through the terminal device, and when the server receives the access of the terminal device, if the access is verified, the server can send the picture list information or preview information after the clustering process to the terminal device; the terminal equipment can access the server according to the picture list information or the preview information, then consult the clustered pictures on the server and simply and directly find the expected target picture.
Fig. 1 is a first flowchart of a picture clustering method according to an embodiment of the present invention. As described below by using an example of the terminal device execution, the specific process executed by the server may refer to the terminal device execution, and details are not described in this application. As shown in fig. 1, the image clustering method in this embodiment may include the following steps:
s101, determining attribute information of each picture in a plurality of pictures.
Taking the terminal device as an example, the multiple pictures may be pictures shot and stored by the terminal device, or may be multiple pictures downloaded and stored from the network.
The attribute information may include: content attributes of the picture, and/or source attributes of the picture, etc. The content attribute of the picture may include, for example: at least one attribute related to the content of the picture, such as figure, landscape, animal, face shape, age group, skin color, gender and the like; the source attributes of the picture may include, for example: at least one of the time of the shot, the place of the shot, the download channel such as an application program, and the like.
If the attribute information includes the content attribute of the picture, in the method, the content attribute of each picture can be determined by performing content analysis on each picture of the plurality of pictures.
If the attribute information includes: the source attribute of the picture, in the method, the source attribute of each picture can be obtained under the condition of obtaining the plurality of pictures.
It should be noted that, if the attribute information includes the content attribute of the picture, only the preliminary analysis is performed on each picture, as long as it is determined that a certain attribute is included in each picture, and specific details are not required to be determined.
For example, the method may analyze each picture to determine whether a person is included in each picture without determining a specific person feature vector. If the picture includes a person, it can be determined that the attribute information of the picture includes the person.
The method can also analyze each picture to determine whether each picture comprises scenery or not without determining a specific scenery feature vector. If the picture includes a landscape, the attribute information of the picture includes the landscape.
The method can also analyze each picture to determine whether the each picture comprises the animal without determining a specific animal feature vector. If the picture comprises an animal, the attribute information of the picture comprises: an animal.
The method can also analyze each picture to determine whether the each picture comprises a person, if so, the face of the person is any face of a face library such as a round face, a square face, a melon seed face and the like, and a specific facial feature vector is not required to be determined. If the face of the person in the picture is a round face, the attribute information of the picture can be determined to include: a round face. If the face of the person in the picture is a square face, the attribute information of the picture can be determined to include: and (5) square face. If the face of the person in the picture is the melon seed face, the attribute information of the picture can be determined to comprise: melon seed and face.
The method can also analyze each picture to determine whether a person is included in each picture, such as a person, and further perform a preliminary analysis on the face of the person to determine the age of the person, such as an infant, a child, an adult, and the like, without determining a specific feature vector. If the person in the picture is an infant, determining that the attribute information of the picture comprises: infants and young children. If the person in the picture is a child, determining that the attribute information of the picture comprises: a child. If the person in the picture is an adult, the attribute information of the picture can be determined to comprise: an adult.
The method can also analyze each picture to determine whether the picture comprises a person, such as a person, and further perform a preliminary analysis on the face of the person to determine the skin color of the person, such as yellow skin, white skin, black skin, and the like, without determining a specific feature vector. If the skin color of the person in the picture is yellow skin, the attribute information of the picture can be determined to comprise: yellow skin. If the skin color of the person in the picture is white skin, the attribute information of the picture can be determined to comprise: the skin is white. If the skin color of the person in the picture is black skin, the attribute information of the picture can be determined to include: and (4) black skin.
The method can also analyze each picture to determine whether a person is included in each picture, such as a person, and further perform a preliminary analysis on the person to determine the gender of the person, such as a male or a female, without determining specific feature vectors. If the person in the picture is a male person, the attribute information of the picture can be determined to include: the male. If the person in the picture is female, the attribute information of the picture can be determined to include: female, the female is provided with a drug.
S102, pre-classifying the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset includes at least one picture.
In the method, the attributes of the multiple pictures can be classified first, the multiple pictures are divided into multiple groups, and the pictures corresponding to the attribute information of each group are divided into one picture subset, so that the multiple picture subsets are obtained. The attribute information in one group is the same, or the similarity of the attribute information is greater than or equal to a preset value. That is to say, in each picture subset, the attribute information of at least one picture belongs to one group, and the attribute information is the same, or the similarity of the attribute information is greater than or equal to a preset value.
For example, as shown above, in S102, pre-classifying the multiple pictures according to the attribute information, obtaining multiple picture subsets may include:
and dividing the pictures with the same attribute information into a picture subset.
That is, the attribute information of at least one picture included in the one picture subset may be the same.
In other examples, the attribute information of at least one picture included in one picture subset may be different, as long as the similarity of the attribute information of the at least one picture is greater than or equal to a preset value, and the similarity of the attribute information is relatively high.
In the method, the plurality of pictures can be pre-classified according to the attribute information to obtain a plurality of picture subsets, so that the pre-classification of the plurality of pictures is realized. The pre-classification is divided based on the attribute information of the pictures, so the pre-classification speed of the pictures is high, and the occupied time is short.
And S103, determining the similarity between the pictures in each picture subset.
In the method, feature extraction may be performed on at least one picture in each picture subset, and a similarity between pictures in each picture subset is determined, where the similarity between pictures may be a feature similarity between pictures.
And S104, clustering each picture subset according to the similarity between the pictures.
In the method, the pictures with the similarity in one range can be divided into one class according to the similarity among the pictures in at least one picture of each picture subset, and the pictures with the similarity in different ranges can be divided into different classes, so that the clustering processing of each picture subset is realized.
Pictures belonging to the same cluster may be stored in the same folder, and pictures belonging to different clusters may be stored in different folders.
According to the picture clustering method provided by the embodiment of the invention, the attribute information of each picture in a plurality of pictures can be determined, the plurality of pictures are pre-classified according to the attribute information to obtain a plurality of picture subsets, each picture subset comprises at least one picture, so that the similarity among the pictures in each picture subset is determined, and the clustering processing is carried out on each picture subset according to the similarity among the pictures. In the method, the pictures are pre-classified according to the attribute information of the pictures, and the pictures in each picture subset can be clustered only by determining the similarity among the pictures in each picture subset without determining the similarities of all the pictures, so that the processing speed of picture clustering is effectively improved, the processing time of picture clustering is shortened, and the user experience is improved.
Optionally, on the basis of the image clustering method shown in fig. 1, an embodiment of the present invention may further provide an image clustering method. Fig. 2 is a second flowchart of a picture clustering method according to an embodiment of the present invention. As shown in fig. 2, determining the similarity between the pictures in each picture subset in S103 may include:
s201, determining a feature vector of each picture in each picture subset.
In the method, the pictures in each picture subset may be processed according to a preset feature model to determine a feature vector of each picture in each picture subset.
Optionally, the feature vector is a facial feature vector.
If the feature vector is a facial feature vector, facial feature recognition may be performed on each picture in each picture subset in the method to determine a facial feature vector in each picture.
Determining the feature vector of each picture according to the face feature vector of each picture and the face feature vectors of other pictures in each picture subset, determining the similarity between the pictures, and then performing picture clustering on each picture subset to divide the pictures with the same face feature vector into one type, namely, dividing the pictures of the same person into one type.
S202, determining the similarity between the pictures according to the feature vector of each picture and the feature vectors of other pictures in each picture subset.
In the method, the similarity between the pictures can be determined by comparing the feature vector of each picture with the feature vectors of other pictures in each picture subset.
The feature vector of each picture in each picture subset and the feature vectors of other pictures are adopted to determine the similarity between the pictures, so that the similarity between the pictures is more accurate, and the accuracy of picture clustering is ensured.
Optionally, the similarity between the pictures may include: the difference between the feature vector of each picture and the feature vectors of the other pictures.
For example, if the difference between the feature vector of each picture and the feature vectors of the other pictures is larger, the similarity between the pictures can be determined to be smaller; on the contrary, if the difference between the feature vector of each picture and the feature vectors of the other pictures is smaller, it is determined that the similarity between the pictures is larger.
In other implementations, the similarity between the pictures may not include: the difference between the feature vector of each picture and the feature vectors of the other pictures is only required if the similarity between the pictures is obtained according to the feature vector of each picture and the feature vectors of the other pictures. In the other implementation manners, the similarity between the pictures can be obtained by using other calculation formulas according to the feature vector of each picture and the feature vectors of the other pictures, which is not limited to the above, and is not described herein again.
And determining the similarity between the pictures in a subtraction mode so as to make the similarity include: the difference value of the characteristic vector of each picture and the characteristic vectors of other pictures reduces the processing mode of similarity between the pictures, thereby improving the picture clustering speed and the clustering time.
Optionally, on the basis of the image clustering method shown in fig. 2, as shown in S104, performing clustering processing on each image subset according to the similarity between the images may include:
and S203, if the difference value between the characteristic vector of the first picture and the characteristic vector of the second picture in each picture subset is within a preset range, clustering the first picture and the second picture into a class of pictures.
That is, in the method, pictures with difference values of the feature vectors within a range can be clustered into one class of pictures, and pictures with difference values of the feature vectors within different ranges can be clustered into different classes.
In the method, the difference value between the characteristic vector of the first picture and the characteristic vector of the second picture in each picture subset is within a preset range, and then the first picture and the second picture are clustered into a class of pictures, so that the picture clustering accuracy is improved, and the clustering effect is improved.
The following is an embodiment of the apparatus of the present invention, which can be used to implement the above-mentioned embodiment of the method of the present invention, and the implementation principle and technical effects are similar.
Fig. 3 is a schematic structural diagram of a picture clustering device according to an embodiment of the present invention. The image clustering device is integrated in a terminal device or a server in a software and/or hardware mode. As shown in fig. 3, the picture clustering device 30 of the present embodiment may include:
the first determining module 31 is configured to determine attribute information of each of the plurality of pictures.
A first classification module 32, configured to perform pre-classification on the multiple pictures according to the attribute information to obtain multiple picture subsets; each picture subset includes at least one picture.
A second determining module 33, configured to determine similarity between pictures in each of the picture subsets;
and the second classification module 34 is configured to perform clustering processing on each of the picture subsets according to the similarity between the pictures.
The picture clustering device can perform picture pre-classification according to the attribute information of the pictures, and can perform clustering processing on the pictures in each picture subset only by determining the similarity among the pictures in each picture subset without determining the similarities of all the pictures, thereby effectively improving the processing speed of picture clustering, shortening the processing time of picture clustering and improving the user experience.
Optionally, the first classification module 32 is specifically configured to classify the pictures with the same attribute information into a picture subset.
Optionally, the second determining module 33 is specifically configured to determine a feature vector of each picture in each picture subset; and determining the similarity between the pictures according to the feature vector of each picture and the feature vectors of other pictures in each picture subset.
Optionally, the similarity between the pictures includes: the difference between the feature vector of each picture and the feature vectors of the other pictures.
Optionally, the second classification module 34 is specifically configured to cluster the first picture and the second picture into a class of pictures if a difference between the feature vector of the first picture and the feature vector of the second picture in each picture subset is within a preset range.
Optionally, the feature vector is a facial feature vector.
Optionally, the attribute information includes at least one of the following: person, landscape, animal, face shape, age group, skin color, sex, photographing time, and photographing place.
The image clustering device provided in this embodiment can perform the image clustering method described in fig. 1 or fig. 2, and specific implementation and effective effects thereof can be found in the above description, which is not described herein again.
Fig. 4 is a schematic structural diagram of a picture clustering device according to an embodiment of the present invention. As shown in fig. 4, the picture clustering device 40 of the present embodiment includes: a memory 41 and a processor 42. The memory 41 is connected to the processor 42 via a bus.
A memory 41 for storing program instructions.
A processor 42 for causing the processor 42 to perform the following steps when the program instructions are executed:
determining attribute information of each picture in a plurality of pictures;
pre-classifying the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset comprises at least one picture;
determining the similarity between pictures in each picture subset;
and clustering each picture subset according to the similarity between the pictures.
Optionally, the processor 42 is specifically configured to divide the pictures with the same attribute information into a picture subset.
Optionally, the processor 42 is specifically configured to determine a feature vector of each picture in each picture subset; and determining the similarity between the pictures according to the feature vector of each picture and the feature vectors of other pictures in each picture subset.
Optionally, the similarity between the pictures includes: the difference between the feature vector of each picture and the feature vectors of the other pictures.
Optionally, the processor 42 is specifically configured to cluster the first picture and the second picture into a class of picture if a difference between the feature vector of the first picture and the feature vector of the second picture in each picture subset is within a preset range.
Optionally, the feature vector is a facial feature vector.
Optionally, the attribute information includes at least one of the following: person, landscape, animal, face shape, age group, skin color, sex, photographing time, and photographing place.
Alternatively, the picture clustering device 40 may be a terminal device or a server.
The image clustering device of this embodiment may perform the image clustering method described in fig. 1 or fig. 2, and specific implementation and effective effects thereof can be referred to above, which is not described herein again.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program can be executed by the processor 42 shown in fig. 4 to implement the image clustering method shown in any of the above embodiments, and specific implementation and effective effects thereof can be seen from the foregoing, and are not described herein again.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media capable of storing program codes, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, and an optical disk.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A picture clustering method is characterized by comprising the following steps:
determining attribute information of each picture in a plurality of pictures;
pre-classifying the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset comprises at least one picture;
determining the similarity between pictures in each picture subset;
and clustering each picture subset according to the similarity between the pictures.
2. The method according to claim 1, wherein the pre-classifying the plurality of pictures according to the attribute information to obtain a plurality of picture subsets comprises:
and dividing the pictures with the same attribute information into a picture subset.
3. The method of claim 1, wherein the determining the similarity between the pictures in each of the picture subsets comprises:
determining a feature vector of each picture in each picture subset;
and determining the similarity between the pictures according to the feature vector of each picture and the feature vectors of other pictures in each picture subset.
4. The method of claim 3, wherein the inter-picture similarity comprises: the difference value of the feature vector of each picture and the feature vectors of other pictures.
5. The method according to claim 4, wherein the clustering the each picture subset according to the similarity between the pictures comprises:
and if the difference value of the characteristic vector of the first picture and the characteristic vector of the second picture in each picture subset is within a preset range, clustering the first picture and the second picture into a class of pictures.
6. The method of any of claims 3-5, wherein the feature vector is a facial feature vector.
7. The method according to any of claims 1-5, wherein the attribute information comprises at least one of: person, landscape, animal, face shape, age group, skin color, sex, photographing time, and photographing place.
8. An image clustering apparatus, comprising:
the first determining module is used for determining the attribute information of each picture in the plurality of pictures;
the first classification module is used for performing pre-classification on the plurality of pictures according to the attribute information to obtain a plurality of picture subsets; each picture subset comprises at least one picture;
a second determining module, configured to determine similarity between pictures in each of the picture subsets;
and the second classification module is used for clustering each picture subset according to the similarity between the pictures.
9. A picture clustering device, comprising: a memory and a processor; the memory is connected with the processor;
the memory to store program instructions;
the processor, configured to implement the picture clustering method according to any one of claims 1 to 7 when the program instructions are executed.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the picture clustering method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643244.6A CN111382770A (en) | 2018-12-29 | 2018-12-29 | Picture clustering method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643244.6A CN111382770A (en) | 2018-12-29 | 2018-12-29 | Picture clustering method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111382770A true CN111382770A (en) | 2020-07-07 |
Family
ID=71219372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811643244.6A Pending CN111382770A (en) | 2018-12-29 | 2018-12-29 | Picture clustering method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111382770A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117009564A (en) * | 2023-09-28 | 2023-11-07 | 荣耀终端有限公司 | Picture processing method and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426497A (en) * | 2015-11-24 | 2016-03-23 | 上海斐讯数据通信技术有限公司 | Automatic classification method and system for photo album in intelligent terminal |
| WO2017000716A2 (en) * | 2015-06-30 | 2017-01-05 | 中兴通讯股份有限公司 | Image management method and device, and terminal device |
| CN106355170A (en) * | 2016-11-22 | 2017-01-25 | Tcl集团股份有限公司 | Photo classifying method and device |
| CN106610983A (en) * | 2015-10-22 | 2017-05-03 | 中兴通讯股份有限公司 | Picture management method and apparatus, and terminal |
| CN107015998A (en) * | 2016-01-28 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of image processing method, device and intelligent terminal |
| CN107609466A (en) * | 2017-07-26 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Face cluster method, apparatus, equipment and storage medium |
| CN108509994A (en) * | 2018-03-30 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | character image clustering method and device |
| CN109063737A (en) * | 2018-07-03 | 2018-12-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and mobile terminal |
-
2018
- 2018-12-29 CN CN201811643244.6A patent/CN111382770A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017000716A2 (en) * | 2015-06-30 | 2017-01-05 | 中兴通讯股份有限公司 | Image management method and device, and terminal device |
| CN106610983A (en) * | 2015-10-22 | 2017-05-03 | 中兴通讯股份有限公司 | Picture management method and apparatus, and terminal |
| CN105426497A (en) * | 2015-11-24 | 2016-03-23 | 上海斐讯数据通信技术有限公司 | Automatic classification method and system for photo album in intelligent terminal |
| CN107015998A (en) * | 2016-01-28 | 2017-08-04 | 阿里巴巴集团控股有限公司 | A kind of image processing method, device and intelligent terminal |
| CN106355170A (en) * | 2016-11-22 | 2017-01-25 | Tcl集团股份有限公司 | Photo classifying method and device |
| CN107609466A (en) * | 2017-07-26 | 2018-01-19 | 百度在线网络技术（北京）有限公司 | Face cluster method, apparatus, equipment and storage medium |
| CN108509994A (en) * | 2018-03-30 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | character image clustering method and device |
| CN109063737A (en) * | 2018-07-03 | 2018-12-21 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and mobile terminal |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117009564A (en) * | 2023-09-28 | 2023-11-07 | 荣耀终端有限公司 | Picture processing method and electronic equipment |
| CN117009564B (en) * | 2023-09-28 | 2024-01-05 | 荣耀终端有限公司 | Picture processing method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3248143B1 (en) | Reducing computational resources utilized for training an image-based classifier | |
| CN107463605B (en) | Method and device for identifying low-quality news resource, computer equipment and readable medium | |
| Ma et al. | Knowledge adaptation for ad hoc multimedia event detection with few exemplars | |
| CN111368893A (en) | Image recognition method and device, electronic equipment and storage medium | |
| EP3540612A1 (en) | Cluster processing method and device for questions in automatic question and answering system | |
| CN109558533B (en) | Personalized content recommendation method and device based on multiple clustering | |
| US10482146B2 (en) | Systems and methods for automatic customization of content filtering | |
| US9747305B2 (en) | Image search device, image search method, program, and computer-readable storage medium | |
| CN108228844B (en) | Picture screening method and device, storage medium and computer equipment | |
| CN110399487B (en) | Text classification method and device, electronic equipment and storage medium | |
| CN109241299B (en) | Multimedia resource searching method, device, storage medium and equipment | |
| CN110765286A (en) | Cross-media retrieval method and device, computer equipment and storage medium | |
| JP2018032340A (en) | Attribute estimation device, attribute estimation method and attribute estimation program | |
| WO2023016087A1 (en) | Method and apparatus for image clustering, computer device, and storage medium | |
| EP2084625B1 (en) | Dominant color descriptors | |
| CN113657087B (en) | Information matching method and device | |
| CN112632280B (en) | Text classification method and device, terminal equipment and storage medium | |
| CN114330584A (en) | Data clustering method and device, storage medium and electronic equipment | |
| CN115935049A (en) | Recommendation processing method and device based on artificial intelligence and electronic equipment | |
| CN111382770A (en) | Picture clustering method, device, equipment and storage medium | |
| CN111667018A (en) | Object clustering method and device, computer readable medium and electronic equipment | |
| JP2014102772A (en) | Program, device, and method for calculating similarity between contents represented by sets of feature vectors | |
| CN111797765B (en) | Image processing method, device, server and storage medium | |
| CN114373088A (en) | Training method of image detection model and related product | |
| CN114461822A (en) | Resource processing method, device, equipment and storage medium |
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 |