KR20120001847A - System and method for searching image - Google Patents
System and method for searching image Download PDFInfo
- Publication number
- KR20120001847A KR20120001847A KR1020100062437A KR20100062437A KR20120001847A KR 20120001847 A KR20120001847 A KR 20120001847A KR 1020100062437 A KR1020100062437 A KR 1020100062437A KR 20100062437 A KR20100062437 A KR 20100062437A KR 20120001847 A KR20120001847 A KR 20120001847A
- Authority
- KR
- South Korea
- Prior art keywords
- image
- color
- information
- mobile terminal
- extracting
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Abstract
Description
The present invention relates to an image retrieval system and an image retrieval method.
Recently, with the rapid proliferation of computers, the Internet (INTERNET) based on TCP / IP (Transport Control Protocol / Internet Protocol) is established, and various communication networks are being integrated around the Internet. Accordingly, an internet user can search for and obtain a lot of information through the Internet.
The Internet is coupled to a plurality of information providing servers and a plurality of personal computers (PCs), and the personal computers (PCs) are configured to have a predetermined web browser for conducting Internet access, so that a user can use a personal computer (PC). After accessing the Internet, the user can search for various information provided by the web server or transmit or receive various data in real time.
When the Internet user wants to search for a desired image on the Internet, if a user inputs a search word as a keyword, a search engine searches for a search word input as a keyword and outputs an image matching the input keyword.
In the case of a search system with the keyword condition as described above, the keyword is conditioned to find the corresponding image, and thus the image information to be searched cannot be easily and accurately found. That is, the conventional image retrieval system having a keyword condition has a problem in that when there is no keyword that matches the keyword in the title or description of the image including each syllable or word, there is a problem that the corresponding image cannot be searched.
Therefore, in order to solve the above problems, the present invention transmits the image taken by using the mobile terminal to the web server, the web server extracts the image in the order of the highest image and the transmitted image from the pre-stored image It is an object of the present invention to provide an image retrieval system and an image retrieval method capable of easily retrieving an image matching the image by transmitting the display to the mobile terminal.
An image retrieval system according to the present invention includes a mobile terminal for taking an image, transmitting the captured image to a web server, and receiving and displaying image information transmitted from the web server; And a web server which receives the image from the mobile terminal, analyzes the information of the image, and compares the analyzed result value with the identification information of the pre-stored image, and transmits the images having the highest sink rate to the mobile terminal in order. An image retrieval system comprising: a web server comprising: a data receiving unit for receiving an image from the mobile terminal; A color value extracting unit analyzing the information of the image and extracting main color values included in the image in order; A location information extraction unit for extracting location information values in which the main color information is distributed and generating code information according to the location information values; A shape extracting unit which extracts shape information values of the image corresponding to the location information values and generates code information according to the shape information values; A data integration unit for integrating a result value extracted or generated by the color value extraction unit, the location information extraction unit, and the shape extraction unit to match the information of the image; A comparison and analysis unit configured to extract images having a high think rate in order by comparing the result values integrated by the data integration unit with identification information of an image previously stored in a database; And a data transmitter for transmitting the image extracted by the comparison analyzer to the mobile terminal.
A size calculating unit is provided between the shape extracting unit and the data integration unit to calculate a size value of the entire image of the shape of the image.
The color value extracting unit may include: a main color value extracting unit extracting a color most distributed in the image to generate code information according to the distribution of the colors; And an auxiliary color value extracting unit for generating code information according to a distribution of colors other than the maximum color distributed in the image.
The position information extracting unit may include: a position value generating unit generating code information according to color positions of the main colors; A distribution value generator for generating code information according to a ratio of color distribution at a color position of the main color; And an array value generation unit for generating code information according to the arrangement order of the color positions of the main colors.
In addition, the image retrieval method according to the present invention comprises the steps of: (a) taking an image via a mobile terminal, and transmitting the captured image to a web server; (b) receiving an image from the mobile terminal, analyzing information of the received image, and extracting main color values included in the image in order; (c) extracting location information values in which the main color information is distributed and generating code information according to the location information values; (d) extracting shape information values of the image corresponding to the location information values to generate code information according to the shape information values; (e) integrating result values extracted or generated by the steps (b), (c) and (d) to match the information of the image; (f) extracting images having a high think rate in order by comparing the integrated result with identification information of an image previously stored in a database; (g) transmitting the extracted image to the mobile terminal; And (h) receiving the information of the transmitted image and displaying the information on the mobile terminal.
After performing the step (d), (d-1) characterized in that it further comprises the step of calculating the size value for the entire image of the shape of the image.
The step (b) may include: (b-1) generating code information according to the distribution of the color by extracting the color most distributed in the image; And (b-2) generating code information according to a distribution of colors other than the color most maximally distributed in the image.
Step (c) includes: (c-1) generating code information according to the color position of the main color; (c-2) generating code information according to a ratio of color distribution at a color position of the main color; And (c-2) generating code information according to the arrangement order of the color positions of the main colors.
As described above, according to the present invention, the image taken using the mobile terminal is transmitted to the web server, and the web server extracts the images from the pre-stored images in the order of high sync rate to the mobile terminal. By transmitting and displaying, it is possible to search for an image matching the image more easily.
Specific matters other than the problem to be solved, the problem solving means, and the effects of the present invention as described above are included in the following embodiments and the drawings. Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. Like reference numerals refer to like elements throughout.
1 is a block diagram showing the configuration of an image retrieval system according to the present invention;
FIG. 2 is a block diagram illustrating a configuration of a color value extraction unit of FIG. 1. FIG.
3 is a block diagram showing a configuration of a location information extraction unit of FIG. 1;
4 is a flowchart illustrating an image retrieval method according to the present invention.
5 is a flowchart illustrating a color value extraction step of FIG. 4.
FIG. 6 is a flowchart illustrating a location information extraction step of FIG. 4. FIG.
7 is a view showing an image search result displayed on the mobile terminal by FIG.
Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, the accompanying drawings are only described in order to more easily disclose the contents of the present invention, but the scope of the present invention is not limited to the scope of the accompanying drawings that will be readily available to those of ordinary skill in the art. You will know.
1 is a block diagram showing the configuration of an image retrieval system according to the present invention, FIG. 2 is a block diagram showing the configuration of the color value extraction section of FIG. 1, and FIG. 3 is a block diagram showing the configuration of the location information extraction section of FIG. to be.
As shown in FIG. 1, an image retrieval system according to the present invention includes a
The
On the other hand, objects that can be photographed and retrieved from the
As described above, the information of the image transmitted from the
The
Here, the
In addition, a
In addition, as shown in Figure 2, the color
In general, the main color
In order to extract such color values, a preprocessing process, that is, a binarization process using a threshold value, is performed to extract only a specific region where the frequency of color generation is dense. Binary processing, one of the most basic techniques of image processing, is a relatively simple algorithm. This binarization technique is used to extract specific color values.
The location
Here, the position
As shown in FIG. 3, the
The
The
The
On the other hand, although not shown, the database of the
As shown in FIG. 7, the
As described above, according to the present image retrieval system, the image taken using the
4 is a flowchart illustrating an image retrieval method according to the present invention, FIG. 5 is a flowchart illustrating the color value extraction step of FIG. 4, FIG. 6 is a flowchart illustrating the location information extraction step of FIG. 4, and FIG. 7 is FIG. 4. Is a diagram showing an image search result displayed on the mobile terminal.
As shown in FIG. 4, the image scarring method according to the present invention includes: (a) photographing an image through a mobile terminal and transmitting the photographed image to a web server (S100); (b) receiving an image from the mobile terminal, extracting main color values included in the image in order by analyzing the information of the received image information; (c) extracting location information values in which the main color information is distributed and generating code information according to the location information values (S300); (d) extracting shape information values of the image corresponding to the location information values to generate code information according to the shape information values (S400); (e) integrating the result values extracted or generated by the steps (b) (S200), (c) (S300) and (d) (S400) to match the information of the image (S500). ); (f) extracting images having a high sink rate in order by comparing the integrated result with identification information of an image previously stored in a database (S600); (g) transmitting the extracted image to the mobile terminal (S700); And (h) receiving information of the transmitted image and displaying the information on the mobile terminal (S800).
In step (a), when the user takes a picture through the mobile terminal and manipulates a menu to be transmitted to the web server, the captured image is outputted from the mobile terminal and transmitted to the web server through a communication service provider network. .
In addition, after performing step (d) (S400), (d-1) may further include calculating a size value for the entire image of the shape of the image (S450).
As shown in FIG. 5, the step (b) (S200) may include: (b-1) generating code information according to the distribution of the color by extracting the color most distributed in the image (S210); And (b-2) generating code information according to a distribution of colors other than the maximum color distributed in the image (S220).
As shown in FIG. 6, the step (c) (S300) may include (c-1) generating code information according to the color position of the main color (S310); (c-2) generating code information according to a ratio of color distribution at a color position of the main color (S320); And (c-2) generating code information according to the arrangement order of the color positions of the main colors (S330).
The step (e) (S500), the color (a1, a2, ..., al) generated in the step (b) (S200) to (d) (S400), the position (b1, b2,. .., bm), shape (c1, c2, ..., cn), size (d1, d2, ..., do) information value is a vector value (a1, ..., al, b1, ... , bm, c1, ..., cn, d1, ..., do). In addition, the vectors combined in the above-described manner are indexed together with the names of the objects, and the indexed annotations and images are passed to the comparison analysis unit, and then the result value of the image photographed through the similarity function in step (f). And the think rate of the image result of the object stored in the database.
As shown in FIG. 7, the step (h) (S800) is extracted by the web server in the step (f) (S600), and is transmitted to the mobile terminal through the step (g) (S700). And, the think rate corresponding to each image is displayed through the mobile terminal. For example, a rose is photographed using a smartphone, and the photographed image is transmitted to a web server to display the image and the extracted images in the order of high sink rate with the name. In this case, the mobile terminal may search for an image to be searched among the images transmitted from the web server, and if there is no image to be searched, the mobile terminal may request a re-search to the web server.
As described above, according to the present invention, the image taken using the mobile terminal is transmitted to the web server, and the web server extracts the images from the pre-stored images in the order of high sync rate to the mobile terminal. By transmitting and displaying, it is possible to search for an image matching the image more easily.
As described above, it is to be understood that the technical structure of the present invention can be embodied in other specific forms without departing from the spirit and essential characteristics of the present invention.
Therefore, the exemplary embodiments described above are to be understood as illustrative and not restrictive in all respects, and the scope of the present invention is indicated by the following claims rather than the detailed description, and the meaning and scope of the claims and their All changes or modifications derived from equivalent concepts should be construed as being included in the scope of the present invention.
Claims (8)
Receiving an image from the mobile terminal to analyze the information of the image, and compares the analysis result with the identification information of the pre-stored image and transmits the image having a high sink rate in order to the mobile terminal; Is an image search system,
The web server,
A data receiver receiving an image from the mobile terminal;
A color value extracting unit analyzing the information of the image and extracting main color values included in the image in order;
A location information extraction unit for extracting location information values in which the main color information is distributed and generating code information according to the location information values;
A shape extracting unit which extracts shape information values of the image corresponding to the location information values and generates code information according to the shape information values;
A data integration unit for integrating a result value extracted or generated by the color value extraction unit, the location information extraction unit, and the shape extraction unit to match the information of the image;
A comparison and analysis unit configured to extract images having a high think rate in order by comparing the result values integrated by the data integration unit with identification information of an image previously stored in a database; And
And a data transmission unit for transmitting the image extracted by the comparison analysis unit to the mobile terminal.
An image retrieval system is provided between the shape extracting unit and the data integration unit to calculate a size value of the entire image of the shape of the image.
The color value extracting unit may include: a main color value extracting unit extracting a color most distributed in the image to generate code information according to the distribution of the colors; And
And an auxiliary color value extraction unit for generating code information according to a distribution of colors other than the maximum color distributed in the image.
The position information extracting unit may include: a position value generating unit generating code information according to color positions of the main colors;
A distribution value generator for generating code information according to a ratio of color distribution at a color position of the main color; And
And an array value generator for generating code information according to the arrangement order of the color positions of the main colors.
(b) receiving an image from the mobile terminal, analyzing information of the received image, and extracting main color values included in the image in order;
(c) extracting location information values in which the main color information is distributed and generating code information according to the location information values;
(d) extracting shape information values of the image corresponding to the location information values to generate code information according to the shape information values;
(e) integrating result values extracted or generated by the steps (b), (c) and (d) to match the information of the image;
(f) extracting images having a high think rate in order by comparing the integrated result with identification information of an image previously stored in a database;
(g) transmitting the extracted image to the mobile terminal; And
(h) receiving the information of the transmitted image and displaying the information on the mobile terminal.
After performing the step (d), (d-1) further comprising the step of calculating the size value for the entire image of the shape of the image.
The step (b)
(b-1) generating code information according to the distribution of the colors by extracting the color most distributed in the image; And
(b-2) generating code information according to a distribution of colors other than the color most distributed in the image.
The step (c)
(c-1) generating code information according to the color position of the main color;
(c-2) generating code information according to a ratio of color distribution at a color position of the main color; And
(c-2) generating code information according to the arrangement order of the color positions of the main colors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020100062437A KR20120001847A (en) | 2010-06-30 | 2010-06-30 | System and method for searching image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020100062437A KR20120001847A (en) | 2010-06-30 | 2010-06-30 | System and method for searching image |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20120001847A true KR20120001847A (en) | 2012-01-05 |
Family
ID=45609344
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020100062437A KR20120001847A (en) | 2010-06-30 | 2010-06-30 | System and method for searching image |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR20120001847A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014007586A1 (en) * | 2012-07-06 | 2014-01-09 | Samsung Electronics Co., Ltd. | Apparatus and method for performing visual search |
KR101448174B1 (en) * | 2013-04-03 | 2014-10-08 | 주식회사 다음커뮤니케이션 | Method of serching image and server apparatus thereof |
KR20150140392A (en) * | 2013-09-05 | 2015-12-15 | 이베이 인크. | Estimating depth from a single image |
US9292541B2 (en) | 2012-04-17 | 2016-03-22 | Electronics And Telecommunications Research Institute | Method of providing online information using image information |
CN105468772A (en) * | 2015-12-10 | 2016-04-06 | 广东欧珀移动通信有限公司 | Picture searching method applied at mobile terminal and mobile terminal |
WO2016186289A1 (en) * | 2015-05-18 | 2016-11-24 | 김동주 | System and method for providing information using image recognition technique |
WO2018147625A1 (en) * | 2017-02-08 | 2018-08-16 | (주)아모레퍼시픽 | Apparatus and method for searching for make-up product |
KR20200005060A (en) | 2018-07-05 | 2020-01-15 | 십일번가 주식회사 | A method for image searching using an captured image based on guidelines and an apparatus therefor |
KR20200021737A (en) | 2018-08-21 | 2020-03-02 | 십일번가 주식회사 | A method for image searching using real time popular search word and an apparatus therefor |
KR20200023091A (en) | 2018-08-24 | 2020-03-04 | 십일번가 주식회사 | Image search method for providing information about similarity and apparatus therefor |
KR20200024037A (en) | 2018-08-27 | 2020-03-06 | 십일번가 주식회사 | Image search method using filtering and apparatus therefor |
KR20200026373A (en) | 2018-08-30 | 2020-03-11 | 십일번가 주식회사 | Image search method using search history and apparatus therefor |
-
2010
- 2010-06-30 KR KR1020100062437A patent/KR20120001847A/en active IP Right Grant
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9292541B2 (en) | 2012-04-17 | 2016-03-22 | Electronics And Telecommunications Research Institute | Method of providing online information using image information |
WO2014007586A1 (en) * | 2012-07-06 | 2014-01-09 | Samsung Electronics Co., Ltd. | Apparatus and method for performing visual search |
US9256617B2 (en) | 2012-07-06 | 2016-02-09 | Samsung Electronics Co., Ltd. | Apparatus and method for performing visual search |
KR101448174B1 (en) * | 2013-04-03 | 2014-10-08 | 주식회사 다음커뮤니케이션 | Method of serching image and server apparatus thereof |
KR20150140392A (en) * | 2013-09-05 | 2015-12-15 | 이베이 인크. | Estimating depth from a single image |
US10255686B2 (en) | 2013-09-05 | 2019-04-09 | Ebay Inc. | Estimating depth from a single image |
WO2016186289A1 (en) * | 2015-05-18 | 2016-11-24 | 김동주 | System and method for providing information using image recognition technique |
CN105468772A (en) * | 2015-12-10 | 2016-04-06 | 广东欧珀移动通信有限公司 | Picture searching method applied at mobile terminal and mobile terminal |
WO2018147625A1 (en) * | 2017-02-08 | 2018-08-16 | (주)아모레퍼시픽 | Apparatus and method for searching for make-up product |
KR20200005060A (en) | 2018-07-05 | 2020-01-15 | 십일번가 주식회사 | A method for image searching using an captured image based on guidelines and an apparatus therefor |
KR20200021737A (en) | 2018-08-21 | 2020-03-02 | 십일번가 주식회사 | A method for image searching using real time popular search word and an apparatus therefor |
KR20200023091A (en) | 2018-08-24 | 2020-03-04 | 십일번가 주식회사 | Image search method for providing information about similarity and apparatus therefor |
KR20200024037A (en) | 2018-08-27 | 2020-03-06 | 십일번가 주식회사 | Image search method using filtering and apparatus therefor |
KR20200026373A (en) | 2018-08-30 | 2020-03-11 | 십일번가 주식회사 | Image search method using search history and apparatus therefor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR20120001847A (en) | System and method for searching image | |
US10509821B2 (en) | Data capture and identification system and process | |
KR101715036B1 (en) | Method for searching product classification and providing shopping data based on object recognition, server and system thereof | |
US10997788B2 (en) | Context-aware tagging for augmented reality environments | |
US9754183B2 (en) | System and method for providing additional information using image matching | |
US20020090132A1 (en) | Image capture and identification system and process | |
CN107092646A (en) | System and method for carrying out image identification using mobile device | |
KR20110096500A (en) | Location-based communication method and system | |
KR20090106069A (en) | Apparatus and Method for inputing and searching information for augumented reality | |
CN110083762A (en) | Source of houses searching method, device, equipment and computer readable storage medium | |
CN104580300B (en) | The method and system of figure and outdoor scene identification based on cloud operation | |
CN111797266B (en) | Image processing method and apparatus, storage medium, and electronic device | |
CN103369361B (en) | The control method of image data echo, server and terminal | |
KR101873246B1 (en) | Method for searching product classification and providing shopping data based on object recognition, server and system thereof | |
KR101320247B1 (en) | Apparatus and method for image matching in augmented reality service system | |
KR101737619B1 (en) | Apparatus and method for providing face recognition | |
KR20120003587A (en) | Method for providing shopping data service based on object recognition, server and system thereof | |
CN117216308B (en) | Searching method, system, equipment and medium based on large model | |
KR101525223B1 (en) | System for transferring data, method for transferring data and computer-readable recording medium comprising program for performing the same |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
E701 | Decision to grant or registration of patent right | ||
NORF | Unpaid initial registration fee |