KR20220022065A - Sharing Methods for Clustering User Searched Image and Implementation Thereof - Google Patents

Abstract

The present invention provides a method for clustering and sharing a user searched image to classify various images of various sources by attibutes including time, event, and character to cluster an image through a tag explaining the image, and an implementation system thereof. A method for clustering an image of a server operated by at least one processor comprises: extracting a content for explaining at least one image and a corresponding image included in each web document in a plurality of web documents; determining one representative image representing duplication images to connect image explaining contents corresponding to the duplicaiton images with the representative image when the duplication images are included in images extracted from the plurality of web documents; determining image information including an image explianing tag and a time stamp of the representative image from a plurality of image explaining contents connected with the representative image; and extracting images associated with the clustering keyword from the image storage to cluster at least a part of the extracted images based on similarity of the extracted images and to generate at least one clustering event when an image clustering request according to the clustering keyword is generated.

Description

{Sharing Methods for Clustering User Searched Image and Implementation Thereof}

The present invention relates to a method for clustering and sharing images searched by a user and a system for implementing the same.

Various images are posted on web pages such as news and blogs, and photos taken from user terminals are quickly uploaded on various sharing platforms such as social media services. The web, where such various images exist, becomes a huge image repository, and users can search for images they want.

However, the same images are redundantly present, or similar images taken at the same event exist in large quantities. Therefore, in order to obtain a desired result among numerous images that are not properly classified, the user must refine the search term to search, and for this purpose, the user must have prior knowledge of a person or event. In addition, since it is difficult to reflect the freshness of the image, the search result may not change significantly depending on the search period. Recently, an attempt has been made to classify and provide images by event, but since the images are still displayed in an array within the event, there is no difference from the prior art of exposing images in chronological order. Accordingly, there is a need for a method for classifying and sharing images in a way that is meaningful to a user.

An object to be solved by the present invention is to provide a method for classifying various images from various sources by attributes such as time, event, person, and the like, and clustering images through tags that describe images, and a system and application implementing the same. In addition, the problem to be solved by the present invention is to provide a sharing method for generating shareable content based on clustered images, and a system and application implementing the same.

According to an embodiment, there is provided an image clustering and sharing method of a server operated by at least one processor, the method comprising: receiving a sharing request for a plurality of images clustered as a single event; A person included in each image is identified based on the person identification information included in each of the plurality of images, and a change in a person's movement in images including the same person among the plurality of images is estimated to determine the person. aligning the images of and transmitting, to a user terminal, the aligned plurality of images, wherein the aligning includes calculating an optical flow of coordinates for all image pairs in images including the same person, and calculating Based on the results, the images can be arranged in an order that makes the movement of the person continuous.

According to an embodiment of the present invention, various images from various sources may be grouped by attributes such as time, event, person, and the like. According to an embodiment of the present invention, it is possible to create content that can be shared by processing a large amount of images pouring out on the web. According to an embodiment of the present invention, a user can obtain meaningful content from a keyword of interest, and quickly visually check an image search result through sorted images.

1 is a schematic configuration diagram of a system according to an embodiment of the present invention.
2 is a flowchart illustrating a method of storing images in an image storage according to an embodiment of the present invention.
3 is a flowchart of an image clustering method according to an embodiment of the present invention.
4 is a flowchart of a method for identifying a person in an image according to an embodiment of the present invention.
5 is a diagram illustrating a terminal on which a screen is displayed according to an embodiment of the present invention.

Hereinafter, with reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated. In addition, terms such as “…unit”, “…group”, and “module” described in the specification mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software. there is.

1 is a schematic configuration diagram of a system according to an embodiment of the present invention.

Referring to FIG. 1 , a system 10 includes a server 100 in which the functions described in the present invention are implemented and a user terminal 200 communicating with the server 100 . The system 10 includes an image storage 300 in which images processed by the server 100 are stored. The user terminal 200 is equipped with an application programmed to provide the functions described in the present invention, displays information provided from the server 100 through the application, and transmits the information input by the user to the server 100 . do.

The server 100 executes the operations described in the present invention by at least one processor. The server 100 classifies various images from various sources by attributes such as time, event, and person, and groups the images through tags that describe image attributes. The server 100 generates shareable content based on the clustered images, and provides an image search result in response to a search request of the user terminal 200 . An operation method of the server 100 will be described in detail below.

The user terminal 200 includes an application stored in a computer-readable storage medium, and hardware such as a processor, a memory, a display, and a communication module. The application includes instructions for executing the operations described for example in the present invention. The processor runs the application to execute the programmed operation. The display may display a user interface screen provided by an application and receive a user input, for example, a touch input. The communication module communicates with the server 100 through a communication network.

The user terminal 200 may be implemented in various forms, for example, in the form of various types of computers such as a mobile terminal such as a smart phone, a pad type terminal such as a smart pad, a laptop computer, a wearable device, a TV terminal, etc. can be implemented.

2 is a flowchart illustrating a method of storing images in an image storage according to an embodiment of the present invention, and FIG. 3 is an exemplary diagram illustrating an image storage method according to an embodiment of the present invention.

Referring to FIG. 2 , the server 100 extracts at least one image included in each web document and contents describing the image from a plurality of web documents ( S110 ). A web document (or simply referred to as a 'document') is a digital document published on the web, such as news, blogs, and social media services, and includes all documents accessible by the server 100 through a network. A web document is created with at least one image and text, and the same/similar image may be extracted from a plurality of web documents. Since the image and text included in the web document are correlated with each other, the server 100 may extract image-related content or content describing the image from the text. As for the description of the image, a title appearing in the document from which the image is extracted, or words and phrases included in the document may be extracted from the metadata of the document.

The server 100 tags each image with a description of the corresponding image (S120).

The server 100 determines whether the extracted images are duplicated, and extracts the duplicate images (S130). The duplicate image extraction method may be selected from various image processing techniques. For example, the server 100 may determine duplicate images by comparing feature values (eg, 128-bit hash values) representing each image.

The server 100 determines a representative image from among the duplicate images, and connects the image descriptions tagged to each of the duplicate images to the representative image (S140). That is, image information in which a plurality of web document information is linked to a single image is generated. The server 100 may determine the image with the earliest creation date or the best quality among the duplicate images as the representative image, but may select the representative image in various other ways.

The server 100 determines the image description tag of the representative image and the timestamp of the representative image based on the plurality of image description contents, maps the image description tag and the timestamp to the representative image, and stores it in the image storage 300 ( S150). The image description tag may be obtained from words frequently appearing in a plurality of documents describing the same image. The image description tag that appears frequently in the plurality of documents can be viewed as the most representative description of the image. The server 100 may determine the earliest creation date among web documents including duplicate images as the timestamp of the representative image. Alternatively, when a specific event time (eg, record release date, performance date, event schedule, etc.) is described in the web document, the server 100 may determine the timestamp of the representative image based on the document content. Most news about events that occurred on the same day are written on the same day, but since web documents may contain information about events that have already occurred or events that will occur in the future, the actual event occurrence date is set instead of the date of creation of the web document. It can also be used as a timestamp.

Representative image #1, image description tag, and timestamp stored in the image storage 300 may be stored as shown in Table 1. The representative image may be stored as a feature value and/or an image file.

Hereinafter, a method for grouping identical/similar images according to a grouping criterion such as time/person/event type, etc. will be described. FIG. 3 is a flowchart of an image grouping method according to an embodiment of the present invention. Referring to FIG. 3 , the server 100 receives an image clustering request including a clustering keyword ( S210 ). When the server 100 receives a request for an image search for a search keyword from the user terminal 200 , the server 100 may start an image clustering operation by applying the search keyword as a clustering keyword. Alternatively, the server 100 may periodically perform an image grouping operation for a specific keyword or perform an image grouping operation for a specific event in advance whenever a specific event occurs.

The server 100 extracts images related to the clustering keyword from the image storage 300 in which the image description tag and the timestamp are mapped to the image extracted from the web document and stored (S220). At this time, the server 100 sets the timestamp of an image created in a specific search period (eg, today, 3 days ago from today, a week ago from today, a month ago from today, a year ago from today, a specific period in the past, etc.) extract them The search period may be set by the user or the server. On the other hand, before image clustering, the server 100 maps an image description tag and a timestamp to an image extracted from a large amount of web documents and stores it in the image storage 300 , and when clustering the images, the image storage 300 performs clustering. It is assumed that images related to keywords are extracted. However, the server 100 may map an image description tag and a timestamp to an image extracted from a web document while grouping the images, and store it in the image storage 300 .

The server 100 arranges images related to the clustering keyword in timestamp order (S230). Referring to (a) of FIG. 5 , since the images related to the clustering keyword are extracted from the image storage 300 in which duplicate images existing in the web document are organized into a single image, the images extracted from the image storage 300 are It consists of images that are not identical.

The server 100 generates at least one cluster event by tying the images based on the similarity of the images arranged in the timestamp order (S240). The similarity of the images may include a similarity between images or a similarity of an image description tag tagged to the image.

On the other hand, in steps S230 and S240, it has been described that the server 100 arranges the images in a timestamp order in order to group the images in divided time units. However, there is no need to pre-classify images by arranging them in timestamp order, and the server 100 may extract images created in a specific search period and group all of the extracted images based on similarity.

The server 100 maps an event name and a cluster tag to each cluster event (S250). The server 100 creates an event name representing the cluster by analyzing the image description tags of images belonging to the corresponding cluster, and creates a cluster tag representing the cluster by analyzing the image description tags of the images belonging to the corresponding cluster. The cluster tag may include all image description tags of images belonging to the corresponding cluster, or may include a high-frequency tag among image description tags of images belonging to the corresponding cluster. In addition to the image description tag, the server 100 may determine keywords related to the image description tag as the cluster tag, or may determine keywords extracted from information related to the search keyword as the cluster tag. For example, when the search keyword is a person, the server 100 extracts synonyms/similar words for the movie/starring broadcast of the person, and the keyword determined to be highly related to the search keyword or the cluster event from the extracted information. This can be determined by the cluster tag. At least some of the cluster tags may be displayed on the user terminal 200 together with the clustered image. The clustered images, event names, and cluster tags for each cluster event are stored in the image storage 300 .

The server 100 transmits the images grouped by a specific group event or group tag to the user terminal 200 (S260). The clustered images are displayed on the user interface screen of the user terminal 200 .

The user terminal 200 displays images for each group event on the user interface screen 400. If a plurality of cluster events exist, they may be displayed in chronological order. For example, the user interface screen 400a displays an event name 410 , a clustered image 420 , and at least one tag 430 for each clustered event. The tag may be a tag corresponding to the cluster event or a tag associated with the cluster event. The user interface screen 400 may further display a share button 440, a date 450, and the like for each group event. The user interface screen 400 may further display a search keyword name 460 used to search for a group event. When the user selects the tag 430 , the user terminal 200 may display a search result related to the tag 430 on a sharing screen (eg, a chat room screen of a messenger application).

When the user selects the share button 440 , the user terminal 200 may display a group event corresponding to the share button 440 on the sharing screen (eg, a chat room screen of a messenger application) 400b. In this case, the shared clustering event can display the entire clustered image on the shared screen, but the thumbnail form or the clustered images are automatically/manually sequentially or randomly displayed (played) content ( In the future, it may be displayed as 'moving image content' or 'summary content') 470 .

The sharing screen 400b may display tags related to the shared content together with the shared content.

4 is a flowchart of a method for identifying a person in an image according to an embodiment of the present invention.

Referring to FIG. 4 , there are numerous web documents such as news, blogs, social media services, and the like. When images extracted from web documents are duplicated, the server 100 determines a representative image from among the duplicate images and duplicates the representative images. Links the image descriptions tagged to each of the images. However, since the image description is text, the image search result may be inaccurate if there is a person with the same name or an ambiguous expression. Although people can be classified through the image classifier, the number of people continuously increases, so the learning-based image classifier is not highly scalable. Accordingly, the server 100 identifies the person in the image based on the image description extracted together with the image as follows.

The server 100 manages person information for each person (S310). The person information includes a characteristic value of a person image, unique person identification information (ID) assigned to a person, and additional information (eg, occupation, etc.) capable of identifying the person. Meanwhile, the server 100 may use an external person database without directly managing person information.

When the server 100 receives the image extracted from the web document and the image description, it extracts a candidate person from the image description (S320). If, from the description of the image, it is unnecessary to identify a person in the image or it is certain that it is a specific person, the following person identification procedure may be omitted, and the procedure of tagging the image description tag to the extracted image may be performed immediately.

The server 100 evaluates whether the candidate person is a person in the image based on keywords included in the image description and person information of the candidate person (S330). The server 100 may mash-up various APIs such as a person database, a movie database, and a TV program database to evaluate whether the candidate person is a person in the image.

The server 100 identifies the person in the image based on the evaluation score of the candidate person (S340). When there are a plurality of candidate persons, the server 100 may determine a person in the image based on the evaluation score of each candidate person. The server 100 may finally determine the person by comparing the image feature value of the identified person with the feature value of the image extracted from the web document in order to increase accuracy.

The server 100 adds the confirmed person ID to the image description tag of the image (S350).

Through the method of identifying the person in the image, the server 100 may tag and store accurate person information when storing the images extracted from the web document in the image storage described with reference to FIG. 2 . When the server 100 provides the clustered image to the user terminal 200 , the server 100 may cluster the images with accurate person information.

There may be various ways in which the user requests person confirmation. According to one embodiment, when a user views a web document containing an image and wonders who the image contained in the web document is, the user transmits the web document or link information (URL) of the web document to the server 100 to You can request to verify the person of an image included in the document. Then, the server 100 may add the same person identification information to the image of the web document and display it on the user terminal 200 . According to another embodiment, the user may request to confirm the person of the image by transmitting the image to be identified to the server 100 .

When a plurality of people are included in the image, the server 100 may evaluate who each person is, and confirm the person's name based on the evaluation result.

Even if only an image is input, the server 100 searches for a stored image identical to the input image in the image storage 300 . And the server 100 determines a candidate person based on the image description tag or image description contents corresponding to the stored image, and compares the image feature value of the narrowed candidate person with the feature value of the input image to evaluate each of the plurality of people there is.

If there is no stored image identical to the input image in the image storage 300, the server 100 evaluates each of the plurality of people by comparing the characteristic values of the person images stored in the image storage 300 with the characteristic values of each person in the input image. can

The user terminal 200 may further show the evaluation score along with the person's name, as shown in FIG. 8 . Each person name is generated as a tag, and when the user selects the person name or person name tag on the interface screen, the user terminal 200 may display a search result related to the selected person name tag.

The server 100 generates the clustered images as content that users can share and provides them to the user terminal 200 . The server 100 may provide the 'moving image content' or 'summary content' in which the clustered images are continuously reproduced to the user terminal 200 . Although there may be various services for the user to share content, the description will be given here by taking as an example sharing of images clustered with interlocutors on the chat room screen of a messenger application.

First, a method for the server 100 to generate summary content using the clustered images will be described.

The server 100 brings the clustered image included in the clustering event (S410).

The server 100 checks the characters in each of the clustered images, and sorts them by the characters (S420).

The server 100 checks a movement between images of the same person among the images of the same person arranged for each person (S430). The server 100 may find a motion by tracking an optical flow of image coordinates.

The server 100 calculates a continuous motion score for all image pairs from the optical flow of coordinates for all image pairs in the image in which the same person appears (S440). When many coordinates of two images move continuously in the same direction, a higher motion score is calculated. The server 100 may store the relationship of all image pairs obtainable from the N images as an NxN matrix.

The server 100 estimates the movement direction in the image based on the movement scores of all image pairs, and sequentially arranges the images in the order in which the movement is continuous ( S450 ).

The server 100 generates summary content (moving image content) that is displayed while sequentially arranged images are continuously (randomly or sequentially) passed ( S460 ). The images are placed in an order that makes the movement of the person natural based on the optical flow, so if the placed images are passed sequentially (randomly or sequentially), the person appears to move naturally.

The summary content may be selected from among various templates and generated. For example, the summary content may be created as a template in which images of a single character are sequentially followed. When a plurality of characters exist in the group event, the summary content may be generated by connecting the summary content of the plurality of characters.

The server 100 may generate a summary content by selecting a plurality of images from among the clustered images, or the server 100 may select a plurality of images selected from the user terminal 200 or appear selected from the user terminal 200 . Summary content can be created based on a person.

Next, a method for the user terminal 200 to display content related to the swarm event received from the server 100 on the screen will be described.

The user terminal 200 receives a plurality of images clustered as a cluster event from the server 100 and displays them on the search result screen 500a. The user terminal 200 may request a cluster event for the search keyword from the server 100 . In this case, the user may directly input a search keyword to request a cluster event, or may request a cluster event by selecting a search keyword displayed on an arbitrary interface screen. When a search result related to a search keyword exists in other collections in addition to the group event, the user interface screen 500a may further display another collection in the form of a card view.

The search result screen 500a may display representative images 510 of a plurality of images. In this case, the search result screen 500a may display a tag 520 related to the swarm event. In addition, the user interface screen 500a may display a share button 530 . The user interface screen 500a may display an image unfold button 540 .

Referring to FIG. 10( b ), when the image unfold button 540 of the search result screen 500a is selected, the images of the group event hidden in the search result screen 500b are unfolded and displayed. In this case, the images are arranged for each person, and even in the same person image, they are displayed aligned according to the movement direction (movement line).

When the share button 530 is selected, the server 100 may generate a plurality of images as summary content and transmit it to the user terminal 200 . Alternatively, when the user selects a button (not shown) for requesting generation of summary content for images included in the group event on the search result screen 500a or 500b, the server 100 summarizes the plurality of images. It can be generated as type content and transmitted to the user terminal 200 . The search result screen 500a or 500b may further include an image selection button (not shown) so that a user can select images from among the images included in the group event to generate summary content.

The user terminal 200 may receive the summary content 610 of the swarm event from the server 100 and display it on the shared screen (eg, chat room screen) 600 . When the user makes a selection, such as by tapping the summary content 610 , the images included in the summary content 610 are sequentially (randomly or sequentially) displayed in an order. The sharing screen 600 may display a tag 620 related to the summary content together with the summary content 610 .

When a recommendation tag or a representative tag is selected, the user terminal 200 may display a corresponding search result on the sharing screen 600 or a separate interface screen.

It is assumed that the server 100 shares content through the messenger application of the user terminal 200 . The server 100 may be divided into a messaging server 10 , an image analysis server 12 , a scrap server 14 , etc. according to functions provided by the messenger service, and the messaging server 10 and the image analysis server 12 . , and the method of interworking between the scrap server 14 and the method of communicating with the user terminal 200 may be variously changed in design according to interworking rules or service scenarios. On the other hand, the server 100 includes at least one of the messaging server 10, the image analysis server 12, and the scrap server 14, and the server function not included in the server 100 is an external server system (eg, For example, it may be provided from an external server system in conjunction with a system operated by a third party).

When the specific link (URL) information 710 is input to the chat room screen 700, the user terminal 200 transmits the specific link (URL) information to the scrap server 14, and the scrap server 14 sends the specific link ( URL) accesses the content server corresponding to the information and scrapes the content. The scraped content includes an image and image description information (eg, web document title) included in the web document.

The scrap server 14 transmits the scraped content to the image analysis server 12 to request shared content.

The image analysis server 12 generates a thumbnail by analyzing information such as whether a person appears in the scraped image, the location of a face, and the location of an object. Then, the image analysis server 12 extracts the same/similar image as the scraped image from the image storage 300 . Here, as shown in Table 1, the image storage 300 stores image description tags or image description contents included in web documents for each image. Accordingly, the image analysis server 12 generates a tag list associated with the scraped image based on the image description tag mapped to the extracted same/similar image or the image description contents included in web documents in the image storage 300 . can do.

The thumbnail and tag list of the scraped content may be transmitted to the user terminal 200 through the scrap server 14 .

The present invention may include a cutting unit, a first transfer and a second transfer, and a combine unit.

The cutting unit may generate a plurality of pieces by dividing the data, and may assign an address to each of the pieces. Here, the addresses of the pieces may be composed of a combination of a plurality of letters and numbers.

Also, the cutting unit may generate a combination rule in consideration of each address. Here, the combination rule refers to a rule that allows a plurality of data pieces to be combined into data before being divided based on each address.

The first transfer may transmit a plurality of data pieces in an arbitrary order. Here, a plurality of data pieces may be transmitted together with an assigned address, respectively.

The second transfer may transmit a combination rule corresponding to the plurality of data pieces transmitted by the first transfer. Here, it may be preferable that the second transfer transmits the combination rule with a time difference with respect to the transmission of the plurality of data pieces by the first transfer.

The functional operations described in this specification and the embodiments related to the present subject matter can be implemented in a digital electronic circuit, computer software, firmware or hardware, including the structures disclosed herein and structural equivalents thereof, or in a combination of one or more thereof Do.

Embodiments of the subject matter described herein are one or more computer program products, ie one or more modules directed to computer program instructions encoded on a tangible program medium for execution by or for controlling the operation of a data processing device. can be implemented. A tangible program medium may be a radio wave signal or a computer-readable medium. A radio wave signal is an artificially generated signal, eg a machine-generated electrical, optical or electromagnetic signal, that is generated to encode information for transmission to an appropriate receiver device for execution by a computer. The computer-readable medium may be a machine-readable storage device, a machine-readable storage substrate, a memory device, a combination of materials that affect a machine-readable radio wave signal, or a combination of one or more of these.

A computer program (also known as a program, software, software application, script or code) may be written in any form of any programming language, including compiled or interpreted language or a priori or procedural language, and may be written as a stand-alone program or module; It can be deployed in any form, including components, subroutines, or other units suitable for use in a computer environment.

A computer program does not necessarily correspond to a file in a file system. A program may be in a single file provided to the requested program, or in multiple interacting files (eg, files that store one or more modules, subprograms, or portions of code), or portions of files that hold other programs or data. (eg, one or more scripts stored within a markup language document).

The computer program may be deployed to be executed on one computer or multiple computers located at one site or distributed over a plurality of sites and interconnected by a communication network.

Additionally, the logic flows and structural block diagrams described herein describe corresponding acts and/or specific methods supported by corresponding functions and steps supported by the disclosed structural means, and corresponding software. It can also be used to build structures and algorithms and their equivalents.

The processes and logic flows described herein may be performed by one or more programmable processors executing one or more computer programs to perform functions by operating on input data and generating output.

Processors suitable for the execution of computer programs include, for example, both general and special purpose microprocessors and any one or more processors of any kind of digital computer. Typically, the processor will receive instructions and data from read-only memory, random access memory, or both.

A key element of a computer is one or more memory devices for storing instructions and data and a processor for executing instructions. In addition, a computer is generally operably coupled to receive data from, or transmit data to, one or more mass storage devices for storing data, such as, for example, magnetic, magneto-optical disks or optical disks, or to perform both such operations. or will include However, the computer need not have such a device.

The present description sets forth the best mode of the invention, and provides examples to illustrate the invention, and to enable any person skilled in the art to make or use the invention. The specification thus prepared does not limit the present invention to the specific terms presented.

Accordingly, although the present invention has been described in detail with reference to the above-described examples, those skilled in the art can make modifications, changes, and modifications to the examples without departing from the scope of the present invention. In short, in order to achieve the intended effect of the present invention, it is not necessary to separately include all the functional blocks shown in the drawings or follow all the orders shown in the drawings. indicate that it may be within the scope

Claims (7)

An image sharing method of a server operated by at least one processor, comprising:
receiving a request to share a plurality of images clustered in a single event;
A person included in each image is identified based on the person identification information included in each of the plurality of images, and a change in a person's movement is estimated in images including the same person among the plurality of images to determine the corresponding person aligning the images of and
sending, to a user terminal, the aligned plurality of images;
The sorting step is
A user characterized by calculating the optical flow of coordinates for all image pairs in images containing the same character, and arranging the images in an order that makes the character movement successively based on the calculation result How to cluster and share retrieved images. The method of claim 1,
The step of transmitting the plurality of images is
generating content displayed on an interface screen of the user terminal while the plurality of images are passed randomly or sequentially according to a display order; and
A method for grouping and sharing images searched by a user, comprising the step of transmitting the content to the user terminal. The method of claim 1,
The step of transmitting the plurality of images is
The method for grouping and sharing images searched by a user, characterized in that the single event or at least one tag associated with the plurality of images is further transmitted to the user terminal. The method of claim 1,
The sorting step is
When a plurality of people appear in the plurality of images, the method for clustering and sharing images searched by a user, characterized in that, classifying the plurality of images for each person, and arranging the classified images for each person. An image sharing method of a server operated by at least one processor, comprising:
retrieving, in the image repository, at least one stored image identical to or similar to the input image;
generating a tag list associated with the input image by using image description information mapped to the stored image; and
Transmitting, to a user terminal, the sharing information of the input image and the tag list,
wherein the image storage maps and manages each image extracted from a plurality of web documents and image description information describing each image. 6. The method of claim 5,
The information of the input image and the tag list are displayed on the interface screen of the user terminal,
A method for clustering and sharing images searched by a user, characterized in that the sharing information of the input image is content in the form of a thumbnail. 6. The method of claim 5,
The input image is a grouping and sharing method of images searched by a user, characterized in that the image scraped from the link information requested to share from the user terminal.

Images