CN110443297B - Image clustering method and device and computer storage medium - Google Patents
Image clustering method and device and computer storage medium Download PDFInfo
- Publication number
- CN110443297B CN110443297B CN201910696640.3A CN201910696640A CN110443297B CN 110443297 B CN110443297 B CN 110443297B CN 201910696640 A CN201910696640 A CN 201910696640A CN 110443297 B CN110443297 B CN 110443297B
- Authority
- CN
- China
- Prior art keywords
- image
- cluster
- image data
- representative
- clustering
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/50—Maintenance of biometric data or enrolment thereof
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method, a device and a computer storage medium for clustering images, wherein the method comprises the steps of acquiring a plurality of pieces of image data; clustering the plurality of pieces of image data to obtain at least one image cluster; acquiring a representative image of the image cluster, wherein the representative image is image data with the highest quality value in the image cluster or a cluster center of the image cluster; confirming a set center matched with the representative image in the image set library; and storing the image clusters to an image collection library according to the confirmation result. Through the mode, the clustering efficiency can be greatly accelerated.
Description
Technical Field
The present invention relates to the field of image clustering, and in particular, to a method and an apparatus for image clustering, and a computer storage medium.
Background
In the existing clustering method, a plurality of cameras correspond to a plurality of image clusters, each image cluster comprises a clustering center, and after the cameras acquire pictures, a single picture is compared with the clustering centers of the plurality of image clusters one by one, and grading is carried out. But the grading efficiency is low, and the method cannot be suitable for a camera system with a camera reaching a certain order of magnitude.
Disclosure of Invention
The invention provides a method and a device for clustering images and a computer storage medium, which aim to solve the problem of low image grading efficiency in the prior art.
In order to solve the above technical problem, one technical solution adopted by the present invention is to provide a method for clustering images, the method including: acquiring a plurality of pieces of image data; clustering the plurality of pieces of image data to obtain at least one image cluster; acquiring a representative image of the image cluster, wherein the representative image is image data with the highest quality value in the image cluster; confirming a set center matched with the representative image in an image set library; and storing the image clusters to the image collection library according to a confirmation result.
In order to solve the above technical problem, another technical solution adopted by the present invention is to provide an image clustering apparatus, including: an acquisition module for acquiring a plurality of pieces of image data; the processing module is used for clustering the plurality of pieces of image data to obtain at least one image cluster and acquiring a representative image of the image cluster, wherein the representative image is the image data with the highest quality value in the image clusters or the cluster center of the image clusters; the confirming module is used for confirming a set center matched with the representative image in an image set library; and the storage module is used for storing the image clusters to the image collection library according to the confirmation result.
In order to solve the above technical problem, another technical solution of the present invention is to provide an image cluster determining apparatus, including a processor and a memory, where the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the image cluster determining method.
In order to solve the above technical problem, another technical solution of the present invention is to provide a computer storage medium, in which a computer program is stored, and the computer program implements the steps of the above method for determining a cluster of images when being executed.
Different from the prior art, the method and the device have the advantages that the clustering processing is carried out on a plurality of pieces of image data, then the image clusters and the representative images are obtained, the representative images are matched with the set center of the image set library, and the image clusters are stored in the image set library according to the matching result. Therefore, the calculation amount is greatly reduced, and the clustering efficiency is increased.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of an embodiment of a clustering method for images according to the present invention;
FIG. 2 is a flow diagram illustrating the sub-steps of step S12 of FIG. 1;
FIG. 3 is a schematic structural diagram of an embodiment of an apparatus for determining clusters of images according to the present invention;
FIG. 4 is a schematic structural diagram of another embodiment of the image cluster determining apparatus according to the present invention;
FIG. 5 is a schematic structural diagram of an embodiment of a computer storage medium according to the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In video monitoring, a large number of face images need to be classified, so that the face images of the same class are classified into the same class. Specifically, the face images of the same person are made to be one single category.
Referring to fig. 1 in detail, fig. 1 is a schematic flow chart of a first embodiment of the image clustering method according to the present invention, and the image clustering method of the present embodiment includes the following steps.
S11, a plurality of pieces of image data are acquired.
In a specific embodiment, the image data may be acquired in real time, specifically, a large number of cameras may capture the image in real time to obtain an image, and the image data is acquired by performing feature processing on the acquired image and stored in a preset database. A preset number of pieces of image data are then periodically retrieved from the database. Specifically, the periodicity may be preset, such as 1h, 12h, 24h, etc., which are not limited herein. The preset number may be specifically preset, and may be set with reference to the calculation amount of the calculation unit, when image data greater than or equal to the preset number exists in the database, the preset number of image data is obtained, and when image data smaller than the preset number exists in the database, all the image data in the database is obtained. And the identification has been obtained for the image data already obtained in the database so that the acquisition will not be repeated the next time.
S12, clustering the image data to obtain at least one image cluster.
And clustering the plurality of pieces of image data to obtain at least one image cluster, specifically, one image cluster is a set of the plurality of pieces of image data with the similarity reaching a certain threshold.
Referring to fig. 2, fig. 2 is a sub-step of step S12 in the first embodiment of the image clustering method according to the present invention. The clustering method of the images comprises the following steps:
s121, calculating the similarity of each piece of image data and other pieces of image data;
and calculating the similarity of the plurality of pieces of image data, specifically calculating the similarity of each piece of image data and other pieces of image data, and taking n pieces of image data as an example, acquiring results of n × n (n-1) pieces of similarity. For example, if five pieces of ABCDE image data exist, the similarity of A-B, A-C, A-D, B-A and B-C is acquired in sequence, and so on until the similarity of E-D. Thereby determining the results of the 20 pieces of similarity.
And S122, using other image data with the similarity larger than the similarity threshold value as a similar image set of each image data.
And taking other image data with the similarity larger than the similarity threshold value as a similar image set of each image data. Specifically, similarity judgment is performed on each piece of image data, and if the similarity between the other pieces of image data and the piece of image data is greater than a similarity threshold, the other pieces of image data are used as a similar image set of the piece of image data.
For example, in the ABCDE five pieces of image data, if the similarity of A-B, B-A, B-C, C-B, D-E and E-D is larger than the threshold value of the similarity. The similar image set of the image data a is (B), the similar image set of the image data B is (a, C), and so on, the similar image set of the image data E is (D).
And S123, sequentially determining whether each piece of image data belongs to the image cluster.
And then sequentially determining each piece of image data, and judging whether the image data are classified into image clusters. For example, a sequence identification may be performed on the plurality of pieces of image data, and the plurality of pieces of image data may be determined sequentially in the sequence of the sequence identification. For example, 1-5 are sequentially marked on the five pieces of ABCDE data, and then the ABCDE is sequentially determined according to the sequence of 1-5. Or other traversal methods are adopted for determination, so as to ensure that each piece of image data in the plurality of pieces of image data is determined and is not repeated.
And S124, if the image data is not classified into the image cluster, taking the image data and the similar image set as a new image cluster.
And if the image data is not classified into the image cluster, taking the image data and the similar image set of the image data as a new image cluster.
Taking five pieces of image data of ABCDE as an example, when determining the ABCDE in sequence, firstly determining A, and taking the similar image sets of A and A as an image cluster if A does not belong to any image cluster because the images are not clustered. Namely, A and B are clustered as an image.
When D is determined, D (E) is taken as a new image cluster because D is not classified into the existing image clusters.
And S125, if the image data is classified into the image cluster, classifying the similar image set into the image cluster.
If the image data has been classified into an image cluster, a similar image set of the image data is also classified into the image cluster.
Taking ABCDE five pieces of image data as an example, when the image cluster (a, (B)) already exists, when B is determined, since B is already included in the image cluster (a, (B)), the similarity image set of B is further included in the image cluster (a, (B)), that is, (a, C) is included in the image cluster (a, (B)), and the image cluster (a, (B), (a, C)) is acquired.
In a particular embodiment, the deduplication process is performed on each image cluster, such that only one per identical image data is stored in each image cluster. If the image clusters (A, (B), (A, C)) are subjected to the deduplication processing, the image clusters become (A, B, C).
By the above manner, each image data is determined in turn, so that each image data is classified into an image cluster.
And S13, acquiring a representative image of the image cluster, wherein the representative image is the image data with the highest quality value in the image cluster.
And in the acquisition of at least one image cluster, further acquiring a representative image of the image cluster, wherein the representative image of one image cluster is the image data with the highest quality value in the image cluster.
In another embodiment, the representative image may also be a cluster center of the image cluster, in particular the image data of the first belonging image cluster. In the image cluster (a, (B)) as in step S124, a is the cluster center of the image cluster (a, (B)), or the representative image set.
Specifically, the representative image may be one image data or a set of a plurality of image data, which is not limited herein.
Specifically, the quality value is a weighted sum of the occlusion coefficient, the blur coefficient, the illumination coefficient, and the three-dimensional angle in the image data. Specifically, the calculation can be performed as follows:
f＝occlusion*k1+blur*k2+illumination*k3+Pitch*k4+Roll*k5+Yaw*k6；
wherein f is the quality value of the image data, oclusion is the occlusion coefficient, blu is the blur coefficient, illumination is the illumination coefficient, Pitch is the Pitch angle [ -90 (up), 90 (down) ] in the three-dimensional angle, the in-plane rotation angle [ -180 (counterclockwise), 180 (clockwise) ] in the Roll three-dimensional angle, and Yaw is the left and right rotation angle [ -90 (left), 90 (right) ] in the three-dimensional angle. k1-k6 are different weighting coefficients. The weighting factors of k1-k6 may be preset according to specific situations.
And S14, confirming the collection center matched with the representative image in the image collection library.
And determining whether a set center in the image set library is matched with the representative image, specifically, calculating the similarity between the representative image and the set center in the image set library, and determining whether the set center is matched with the representative image according to whether the similarity is greater than a similarity threshold. If the similarity is greater than the threshold, it is determined that the set center matches the representative image.
And S15, storing the image cluster to an image collection library according to the confirmation result.
In one embodiment, if the image set library does not have a set center matched with the representative image, the image cluster is saved to the image set library as a new image set;
in particular, the image collection library may specifically be a collection of a plurality of image collections.
In a specific embodiment, the image collection library is originally an empty library, and then the representative images of the image clusters obtained in the first batch of steps S11-S13 are compared with the collection center of the image collection library, because the image collection library is an empty library at this time, the same collection center as the representative image cannot be found in the image collection library, and the image clusters are used as a new image collection in the image collection library, and the representative images are used as the collection center.
When determining the image clusters acquired through S11-S13 in the subsequent batch operation, there are partial image collections and collection centers already in the image collection library. Then, the representative images of the image clusters are sequentially compared with the set centers in the image set library, and whether the similarity is greater than a similarity threshold is calculated, where the similarity threshold may be the same as or different from the similarity threshold of the above embodiment, and this is not limited here.
If the similarity is smaller than a certain threshold value, the fact that the set center matched with the representative image does not exist in the image set library is proved, the image cluster is used as a new image set in the image set library, and the representative image is used as the set center.
In another embodiment, if there is a set center matching the representative image in the image set library, the image cluster is saved to the image set corresponding to the matching set center.
If the image set inventory is in the set center matched with the representative image, namely an image set exists in the image set inventory, and the similarity between the set center of the image set and the representative image of the image cluster is greater than a certain similarity threshold, the image cluster is stored in the image set corresponding to the set center.
Specifically, when the image cluster is stored in the image set corresponding to the matched set center, the quality value of the set center of the image cluster representative image and the image set to be stored are compared, and the above steps of calculating the quality value have already been described, and are not described herein again.
And if the quality value of the representative image is larger than that of the set center, taking the representative image as the set center of the image set after the image cluster is added. So that the center of the image collection is the image data of the best quality in the whole image collection.
In the above embodiment, the acquired image data is periodically processed, and primary clustering and secondary clustering are sequentially performed on the image data. And pre-clustering the image data in a primary cluster, so that the image data with the similarity larger than a certain similarity threshold value is used as an image cluster, and determining the image data with the best quality value in the image cluster as a representative image. And because in one clustering, similarity calculation is performed on each image data in sequence, taking five image data ABCDE as an example, the similarity between the image data A and the image data B is greater than a similarity threshold, the similarity between the image data B and the image data C is greater than the similarity threshold, but the image data A and the image data C are properly compared, and the similarity is smaller than the similarity threshold, but through the above manner, the image data C and the image data A can still be stored in the same clustering. By the method, similar image data can be stored in one cluster as much as possible. The error is greatly reduced.
And in secondary clustering, comparing the representative image with a collection center of the image collection library. Thereby further saving the image data. So that the image data with the similarity reaching a certain threshold value is stored in an image set in the image set library. Because the number of image sets in the image set library is generally large, only the representative images are compared after one-time clustering. Therefore, the calculation amount is greatly reduced, and the batch image data can be rapidly classified so as to be stored in the image collection library.
Furthermore, compared with the prior art, the method provided by the application can be suitable for a large number of camera systems, and the classification and storage of image data are optimized by establishing an image collection library to be interconnected with each camera.
As shown in fig. 3, the present application further provides an apparatus 300 for determining clusters of images, where the apparatus 300 for determining clusters of images includes an obtaining module 31, a processing module 32, a confirming module 33, and a storing module 34. The acquiring module 31 is configured to acquire a plurality of pieces of image data; the processing module 32 is configured to perform clustering processing on the plurality of pieces of image data to obtain at least one image cluster, and obtain a representative image of the image clusters, where the representative image is image data with the highest quality value in the image clusters; the confirming module 34 is used for confirming a collection center matched with the representative image in the image collection library; the storage module 35 is configured to store the image clusters to the image collection library according to the confirmation result. The specific steps of the method have already been described in the above embodiments, and are not described herein again.
The image clustering determination method is generally realized by an image clustering determination device, so the invention also provides an image clustering determination device. Referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of the image cluster determining device of the present invention. The cluster determining apparatus 100 of the image of the present embodiment includes a processor 12 and a memory 11; the memory 11 has stored therein a computer program for execution by the processor 12 for implementing the steps of the method for cluster determination of images as described above.
The logical processes of the above-described clustering determination method of images are presented as a computer program, and on the computer program side, if it is sold or used as a stand-alone software product, it may be stored in a computer storage medium, and thus the present invention proposes a computer storage medium. Referring to fig. 5, fig. 5 is a schematic structural diagram of a computer storage medium 200 according to an embodiment of the present invention, in which a computer program 21 is stored, and the computer program is executed by a processor to implement the distribution network method or the control method.
The computer storage medium 200 may be a medium that can store a computer program, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, or may be a server that stores the computer program, and the server may send the stored computer program to another device for running or may run the stored computer program by itself. The computer storage medium 200 may be a combination of a plurality of entities from a physical point of view, for example, a plurality of servers, a server plus a memory, or a memory plus a removable hard disk.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (8)
1. A method of clustering images, the method comprising:
acquiring a plurality of pieces of image data;
clustering the plurality of pieces of image data to obtain at least one image cluster;
acquiring a representative image of the image cluster, wherein the representative image is image data with the highest quality value in the image cluster or a cluster center of the image cluster;
confirming a set center matched with the representative image in an image set library;
storing the image clusters to the image collection library according to a confirmation result;
wherein the storing the image clusters to the image collection library according to the confirmation result comprises:
if the image set library does not have a set center matched with the representative image, clustering the images and storing the clustered images into the image set library in a new image set;
if the image set library has a set center matched with the representative image, storing the image cluster into an image set corresponding to the matched set center;
wherein, the storing the image cluster to the image set corresponding to the matched set center comprises:
comparing the quality value of the representative image to the quality value of the set center;
and if the quality value of the representative image is greater than that of the set center, taking the representative image as the set center of the image set after the image clusters are added.
2. The clustering method according to claim 1, characterized in that the quality value is a weighted sum of occlusion coefficients, blur coefficients, illumination coefficients and three-dimensional angles in the image data.
3. The clustering method according to claim 1, wherein confirming the set center matching the representative image in the image set library comprises:
calculating the similarity between the representative image and a set center in the image set library;
and confirming that the set center with the similarity larger than a similarity threshold is matched with the representative image.
4. The clustering method according to claim 1, wherein the clustering the plurality of pieces of image data to obtain at least one image cluster comprises:
calculating the similarity of each image data and other image data;
taking other image data with the similarity larger than the similarity threshold value as a similar image set of each image data;
sequentially determining whether each piece of image data is classified into an image cluster;
if the image data is classified into the image cluster, classifying the similar image set into the image cluster;
and if the image data is not classified into the image cluster, taking the image data and the similar image set thereof as a new image cluster.
5. The clustering method according to claim 1, wherein the acquiring the plurality of pieces of image data includes:
acquiring image data in real time;
a preset number of pieces of image data are periodically acquired.
6. An image clustering apparatus, characterized in that the image clustering apparatus comprises:
an acquisition module for acquiring a plurality of pieces of image data;
the processing module is used for clustering the plurality of pieces of image data to obtain at least one image cluster and acquiring a representative image of the image cluster, wherein the representative image is the image data with the highest quality value in the image clusters or the cluster center of the image clusters;
the confirming module is used for confirming a set center matched with the representative image in an image set library;
the storage module is used for storing the image clusters to the image collection library according to the confirmation result;
wherein the storing the image clusters to the image collection library according to the confirmation result comprises:
if the image set library does not have a set center matched with the representative image, clustering the images and storing the clustered images into the image set library in a new image set;
if the image set library has a set center matched with the representative image, storing the image cluster into an image set corresponding to the matched set center;
wherein, the storing the image cluster to the image set corresponding to the matched set center comprises:
comparing the quality value of the representative image to the quality value of the set center;
and if the quality value of the representative image is greater than that of the set center, taking the representative image as the set center of the image set after the image clusters are added.
7. An apparatus for clustering images, the apparatus comprising a processor and a memory; the memory has stored therein a computer program for execution by the processor to implement the steps of the method according to any one of claims 1-5.
8. A computer storage medium, characterized in that the computer storage medium stores a computer program which, when executed, implements the steps of the method according to any one of claims 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910696640.3A CN110443297B (en) | 2019-07-30 | 2019-07-30 | Image clustering method and device and computer storage medium |
| PCT/CN2019/117421 WO2021017282A1 (en) | 2019-07-30 | 2019-11-12 | Systems and methods for image clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910696640.3A CN110443297B (en) | 2019-07-30 | 2019-07-30 | Image clustering method and device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110443297A CN110443297A (en) | 2019-11-12 |
| CN110443297B true CN110443297B (en) | 2022-06-07 |
Family
ID=68432386
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910696640.3A Active CN110443297B (en) | 2019-07-30 | 2019-07-30 | Image clustering method and device and computer storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110443297B (en) |
| WO (1) | WO2021017282A1 (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104970B (en) * | 2019-12-04 | 2023-04-18 | 浙江大华技术股份有限公司 | Face clustering method and device |
| CN111061899B (en) * | 2019-12-18 | 2022-04-26 | 深圳云天励飞技术股份有限公司 | Archive representative picture generation method and device and electronic equipment |
| WO2021128883A1 (en) * | 2019-12-23 | 2021-07-01 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for managing portrait data |
| CN111091106B (en) * | 2019-12-23 | 2023-10-10 | 浙江大华技术股份有限公司 | Image clustering method and device, storage medium and electronic device |
| CN113240092A (en) * | 2021-05-31 | 2021-08-10 | 深圳市商汤科技有限公司 | Neural network training and face recognition method, device, equipment and storage medium |
| CN114329023A (en) * | 2021-12-28 | 2022-04-12 | 北京市商汤科技开发有限公司 | File processing method and device, electronic equipment and computer storage medium |
| CN115687249B (en) * | 2022-12-30 | 2023-03-28 | 浙江大华技术股份有限公司 | Image gathering method and device, terminal and computer readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875834A (en) * | 2018-06-22 | 2018-11-23 | 北京达佳互联信息技术有限公司 | Image clustering method, device, computer equipment and storage medium |
| CN109213732A (en) * | 2018-06-28 | 2019-01-15 | 努比亚技术有限公司 | A kind of method, mobile terminal and computer readable storage medium improving photograph album classification |
| CN109242045A (en) * | 2018-09-30 | 2019-01-18 | 北京达佳互联信息技术有限公司 | Image clustering processing method, device, electronic equipment and storage medium |
| CN110069989A (en) * | 2019-03-15 | 2019-07-30 | 上海拍拍贷金融信息服务有限公司 | Face image processing process and device, computer readable storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7831599B2 (en) * | 2005-03-04 | 2010-11-09 | Eastman Kodak Company | Addition of new images to an image database by clustering according to date/time and image content and representative image comparison |
| US8542950B2 (en) * | 2009-06-02 | 2013-09-24 | Yahoo! Inc. | Finding iconic images |
| US8351661B2 (en) * | 2009-12-02 | 2013-01-08 | At&T Intellectual Property I, L.P. | System and method to assign a digital image to a face cluster |
| US8983210B2 (en) * | 2010-03-01 | 2015-03-17 | Microsoft Corporation | Social network system and method for identifying cluster image matches |
| US9411829B2 (en) * | 2013-06-10 | 2016-08-09 | Yahoo! Inc. | Image-based faceted system and method |
| US9613455B1 (en) * | 2014-11-02 | 2017-04-04 | Google Inc. | Local georeferenced data |
-
2019
- 2019-07-30 CN CN201910696640.3A patent/CN110443297B/en active Active
- 2019-11-12 WO PCT/CN2019/117421 patent/WO2021017282A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875834A (en) * | 2018-06-22 | 2018-11-23 | 北京达佳互联信息技术有限公司 | Image clustering method, device, computer equipment and storage medium |
| CN109213732A (en) * | 2018-06-28 | 2019-01-15 | 努比亚技术有限公司 | A kind of method, mobile terminal and computer readable storage medium improving photograph album classification |
| CN109242045A (en) * | 2018-09-30 | 2019-01-18 | 北京达佳互联信息技术有限公司 | Image clustering processing method, device, electronic equipment and storage medium |
| CN110069989A (en) * | 2019-03-15 | 2019-07-30 | 上海拍拍贷金融信息服务有限公司 | Face image processing process and device, computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021017282A1 (en) | 2021-02-04 |
| CN110443297A (en) | 2019-11-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110443297B (en) | Image clustering method and device and computer storage medium | |
| EP2396749B1 (en) | Methods for identifying imaging devices and classifying images acquired by unknown imaging devices | |
| EP2742442B1 (en) | A method for detecting a copy of a reference video, corresponding apparatus for extracting a spatio-temporal signature from video data and corresponding computer readable storage medium | |
| WO2023184918A1 (en) | Image anomaly detection method, apparatus and system, and readable storage medium | |
| CN113052245B (en) | Image clustering method and device, electronic equipment and storage medium | |
| CN115578585A (en) | Industrial image anomaly detection method, system, computer device and storage medium | |
| CN111814820A (en) | Image processing method and device | |
| CN113661497A (en) | Matching method, matching device, electronic equipment and computer-readable storage medium | |
| CN109241316B (en) | Image retrieval method, image retrieval device, electronic equipment and storage medium | |
| JP2004030694A (en) | Digital video texture analytic method | |
| CN112015935B (en) | Image searching method and device, electronic equipment and storage medium | |
| CN113918744A (en) | Similar image retrieval method, similar image retrieval device, storage medium and computer program product | |
| CN112836759B (en) | Machine-selected picture evaluation method and device, storage medium and electronic equipment | |
| CN113743533B (en) | Picture clustering method and device and storage medium | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN111695526B (en) | Network model generation method, pedestrian re-recognition method and device | |
| CN113840135A (en) | Color cast detection method, device, equipment and storage medium | |
| CN111767757B (en) | Identity information determining method and device | |
| GB2486987A (en) | Classifying images using enhanced sensor noise patterns | |
| CN115619698A (en) | Method and device for detecting defects of circuit board and model training method | |
| CN112487943A (en) | Method and device for removing duplicate of key frame and electronic equipment | |
| CN114201999A (en) | Abnormal account identification method, system, computing device and storage medium | |
| Su et al. | Exposing digital video logo-removal forgery by inconsistency of blur | |
| CN115439938B (en) | Anti-splitting face archive data merging processing method and system | |
| CN116561372B (en) | Personnel gear gathering method and device based on multiple algorithm engines and readable 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |