CN101071431A - Method and system for searching image based on key graph as search condition - Google Patents
Method and system for searching image based on key graph as search condition Download PDFInfo
- Publication number
- CN101071431A CN101071431A CNA2007100731897A CN200710073189A CN101071431A CN 101071431 A CN101071431 A CN 101071431A CN A2007100731897 A CNA2007100731897 A CN A2007100731897A CN 200710073189 A CN200710073189 A CN 200710073189A CN 101071431 A CN101071431 A CN 101071431A
- Authority
- CN
- China
- Prior art keywords
- image
- graphic
- key graphic
- key
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
Landscapes
- Engineering & Computer Science (AREA)
- Library & Information Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and system for image searching based on key graphic as searching condition, where the method comprises: a. receiving key graphics; b. analyzing key graphics mode data and recording the analysis result; c. according to the key graphics mode data, finding the same or like graphics and returning the finding result. And the invention can make a user fast and accurately find the required ones among large numbers of images in the network or local harddisk so as to save searching time for users and largely raise searching efficiency.
Description
Technical field
The present invention relates to visual search technique field, relating in particular to a kind of is the method and system that search condition carries out the image search based on key graphic.
Background technology
Image technology is various and the general name of the relevant technology of image in a broad sense.Can be divided into three according to its characteristics not only had been related but also distinguishing level: image processing, image analysis and image understanding.
It also serves as that identification is layed foundation automatically with the visual effect of improving image that image processing is mainly carried out various processing to image, or image is carried out compressed encoding to reduce the requirement of required storage space or transmission time, transmission channel.
Image analysis then mainly is that interested target in the image is detected and measures, thereby sets up description to image with the objective information that obtains them.Image analysis is a process from the image to data, and data can be the results that target signature is measured here, or based on the symbolic representation of measuring.They have described the characteristics and the character of target in the image.
Image understanding then is on the basis of image analysis, further studies the character of each target in the image and connecting each other between them, and draws to the understanding of image content implication and to the explanation of original objective scene, thereby instructs and planning action.
Present search for picture file, a lot of search techniques are arranged, can carry out the image search such as the function of search of the disk file of the WDS engine of google, microsoft windows etc., with windows XP software is example, manual such passage label of attribute key entry " my Mount Lushan tourism photo " of giving file, perhaps change picture file " my Mount Lushan tourism photo " by name, can search for these attributes as key word with " Mount Lushan " by search software then, thereby obtain Target Photo.This class search technique is not to search at the graphical information of picture itself, but need artificial (perhaps machine is automatic) that passage or other information (are comprised text description, camera exif information, aperture, ISO, shutter F value, shooting time, the author is taken in the spot for photography, lens type etc.) append on the figure, by these additional information search are realized.
The shortcoming of prior art is:
These engines mainly with the text key message as matching condition, the information in network or the local computer is searched for.As the matching condition of these search be not image, but the information of text or other types.These informational needs manually add in the image and could be obtained by these search engine searches; Do not have the information of other attached texts or other types if certain image has only image itself, then can't searched engine search obtain.Existing image technology and search engine are separate separately simultaneously, do not realize both technique effects that combination brought.
Summary of the invention
It is the method and system that search condition carries out the image search based on key graphic that the technical problem to be solved in the present invention provides a kind of, makes the user can search required image fast and accurately.
For solving the problems of the technologies described above, the objective of the invention is to be achieved through the following technical solutions.
A kind of is the method that search condition carries out the image search based on key graphic, comprises step:
A: receive key graphic;
B: analysis of key graphic model data, and record analysis result;
C: search the figure identical and/or similar according to the key graphic mode data, and return lookup result with key graphic.
Wherein, the graphic model data comprise described in the step b: rectangle, circle, triangle, polygon, straight line, camber line, direction, quantity, color, size, coordinate, humanoid.
Wherein, described key graphic mode data and searched pictorial data have at least one identical, two figure coupling then.
Wherein, described key graphic is two, and these two key graphic mode datas are when mating with searched pictorial data two figure respectively, and then described key graphic and searched image reach coupling.
Wherein, described key graphic is two, and when any key graphic mode data and searched pictorial data two figure mate in these two key graphic, and then described key graphic and searched image reach coupling.
Wherein, described input key graphic is two, and when only having a key graphic mode data and searched pictorial data two figure to mate in these two key graphic, and then described key graphic and searched image reach coupling.
A kind of is the system that search condition carries out the image search based on key graphic, comprising: receiver module, image analysis logging modle, pattern comparison module;
Receiver module is used to be received in the key graphic of drawing on the software interface drawing area;
The image analysis logging modle is used to analyze the graphic model data of described key image, and the data result after the record analysis;
The pattern comparison module is used for the mode data of the searched image of the key graphic data of user's input and appointment is mated, and extracts satisfactory image as the required image of user according to matching result.
Wherein, described image analysis logging modle specifically comprises: image analysis module, graphic feature logging modle;
The image analysis module is used to analyze the graphic model data of described key graphic;
The graphic feature logging modle is used to deposit in the data result behind the image analysis module analysis.
Above technical scheme as can be seen, the present invention has following beneficial effect:
The present invention carries out picture search by the key graphic mode data of analysis of key figure, can make in a large amount of image of users from networks or local hard drive and search required image fast and accurately, thereby save user's search time, improve the efficient of search greatly, also improved the application of image technology in reality simultaneously.
Description of drawings
Fig. 1 is the inventive method process flow diagram;
Fig. 2 is a system construction drawing of the present invention.
Embodiment
The present invention utilizes existing pattern analysis technology, this graphic model characteristic that the key graphic that the user is imported obtains behind pattern analysis and the searched pictorial data of appointment are mated, and extract satisfactory image as required image according to matching result.
For ease of the present invention is further understood, now in conjunction with the accompanying drawings the inventive method is described in detail.
See also the inventive method process flow diagram shown in Figure 1, comprising:
Step 101: receive key graphic;
Wherein, described key graphic is meant with the condition of certain graphic feature as search matched, and image is searched for, and obtains the high image of matching degree.This graphic feature is exactly a key graphic.
Step 102: the analysis of key figure obtains the graphic model data;
Wherein, described graphic model comprises: rectangle, circle, triangle, polygon, straight line, camber line, direction, quantity, color, size, coordinate, humanoid figures feature.
Step 103: record analysis data result;
Step 104: search according to the key graphic mode data whether the figure identical and/or similar with key graphic is arranged, if enter step 105; Otherwise, return no matched image, finish;
Step 105: extract matched image in the searched image as the required image of user.
It is the system that search condition carries out the image search based on key graphic that corresponding the present invention also provides a kind of, sees also system construction drawing of the present invention shown in Figure 2, and this system comprises: receiver module 201, image analysis logging modle 202, pattern comparison module 203;
Wherein, provide a drawing area on software interface, the user can draw the user with mouse or other input equipments and wish the key graphic of searching on drawing area; Software can also be imported key graphic with other input modes: disk file for example, and peripheral hardware scanning, first-class other modes of making a video recording, the common ground of these modes is exactly can be to the native system input image data;
Image analysis logging modle 202 is used to analyze the graphic model data of described key image, and the data result after the record analysis;
Wherein, image analysis logging modle 202 specifically comprises: image analysis module 2021, graphic feature logging modle 2022;
Graphic feature logging modle 2022 is used to deposit in the data result behind the image analysis module analysis;
Below in conjunction with specific embodiment the inventive method is described further.
For example with the searched visual X1 of appointment, X2 input imagery analysis module, the result after the analysis is as shown in table 1:
Table 1
(connecing table 1)
Behind image analysis module analysis image X1, the X2, analysis result is deposited in the graphic feature logging modle; After the user draws a rectangle and input simultaneously, obtain mode data after this key graphic of image analysis module analysis, as shown in table 2:
Table 2
(connecing table 2)
And table 2 mode data is increased in the image feature logging modle, as shown in table 3:
Table 3
(connecing table 3)
Compare by key graphic Y and the searched visual X1 of appointment, the mode data of X2 of pattern comparison module user's input, there is table 3 to see, user's tablet pattern Y has an identical rectangular pattern that promptly meets with X1, so figure Y and X1 " two figure coupling ".Though both rectangle number, coordinate, color and inequality, have in each pattern feature of X1 and Y one identical, then think X1 and Y coupling, the present invention calls this " two figure coupling ".
If the user imports two key graphic Y1 and Y2, it is as shown in table 4 to draw each graphic model data by top analytical procedure:
Table 4
(connecing table 4)
The present invention require the user must specify between these two search condition Y1 and the Y2 to be " with ", " or " or the relation of "No", if " with " relation, then require Y1 and Y2 to reach " two figure coupling " respectively with X, just think the complete search condition that the user imports (just Y1 and Y2 " with " combination) and X reached coupling, this skill is invented and is referred to as " with combinations matches ".Can see that by data on the table 4 combination of Y1 and Y2 and X1, X2 all do not reach " with combinations matches ";
If " or " relation, then as long as any one among Y1 and the Y2 and X have reached " two figure coupling ", this skill invention just think the complete search condition that the user imports (just Y1 and Y2 " or " combination) and X reached coupling, the technical program is referred to as " or combinations matches ".By data on the table 4 as can be seen, the combination of Y1 and Y2 and X1, X2 have all reached " or combinations matches ";
If the relation of "No", then have only as Y1 and X " two figure coupling ", and Y2 and X it is considered herein that complete search condition ("No" of Y1 and Y2 combination just) and X that the user imports have reached coupling not " two figure coupling " time, and the technical program is referred to as " denying combinations matches ".By data on the table 4 as can be seen, the combination of Y1 and Y2 and X1, X2 all do not reach " not combinations matches ".
If the user imports a plurality of key graphic, then can draw matching result equally by top various matching principles.
More than to provided by the present invention a kind of be that the method and system that search condition carries out image search are described in detail based on key graphic, used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, the part that all can change in specific embodiments and applications, in sum, this description should not be construed as limitation of the present invention.
Claims (8)
1, a kind of is the method that search condition carries out the image search based on key graphic, it is characterized in that, comprises step:
A: receive key graphic;
B: analysis of key graphic model data, and record analysis result;
C: search the figure identical and/or similar according to the key graphic mode data, and return lookup result with key graphic.
2, be the method that search condition carries out the image search based on key graphic according to claim 1, it is characterized in that the data of graphic model described in the step b comprise: rectangle, circle, triangle, polygon, straight line, camber line, direction, quantity, color, size, coordinate, humanoid.
3, be the method that search condition carries out image search based on key graphic as claimed in claim 1 or 2, it is characterized in that, described key graphic mode data and searched pictorial data have at least one identical, then two figure mate.
4, as being the method that search condition carries out the image search as described in the claim 3 based on key graphic, it is characterized in that, described key graphic is two, and when these two key graphic mode datas mated with searched pictorial data two figure respectively, then described key graphic and searched image reached coupling.
5, as being the method that search condition carries out the image search as described in the claim 3 based on key graphic, it is characterized in that, described key graphic is two, and when any key graphic mode data and searched pictorial data two figure mated in these two key graphic, then described key graphic and searched image reached coupling.
6, as being the method that search condition carries out the image search as described in the claim 3 based on key graphic, it is characterized in that, described input key graphic is two, and when only having a key graphic mode data and searched pictorial data two figure to mate in these two key graphic, then described key graphic and searched image reach coupling.
7, a kind of is the system that search condition carries out the image search based on key graphic, it is characterized in that, comprising: receiver module, image analysis logging modle, pattern comparison module;
Receiver module is used to be received in the key graphic of drawing on the software interface drawing area;
The image analysis logging modle is used to analyze the graphic model data of described key graphic, and the data result after the record analysis;
The pattern comparison module is used for the mode data of the searched image of the key graphic data of user's input and appointment is mated, and extracts satisfactory image as the required image of user according to matching result.
8, as being the system that search condition carries out the image search as described in the claim 7, it is characterized in that described image analysis logging modle specifically comprises: image analysis module, graphic feature logging modle based on key graphic;
The image analysis module is used to analyze the graphic model data of described key graphic;
The graphic feature logging modle is used to deposit in the data result behind the image analysis module analysis.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007100731897A CN101071431A (en) | 2007-01-31 | 2007-01-31 | Method and system for searching image based on key graph as search condition |
PCT/CN2008/070225 WO2008101422A1 (en) | 2007-01-31 | 2008-01-31 | Image searching method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNA2007100731897A CN101071431A (en) | 2007-01-31 | 2007-01-31 | Method and system for searching image based on key graph as search condition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101071431A true CN101071431A (en) | 2007-11-14 |
Family
ID=38898655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNA2007100731897A Pending CN101071431A (en) | 2007-01-31 | 2007-01-31 | Method and system for searching image based on key graph as search condition |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN101071431A (en) |
WO (1) | WO2008101422A1 (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008101422A1 (en) * | 2007-01-31 | 2008-08-28 | Tencent Technology (Shenzhen) Company Limited | Image searching method and system |
CN101825989A (en) * | 2010-04-23 | 2010-09-08 | 杭州图酷科技有限公司 | Drag and drop image search input method |
CN101996394A (en) * | 2009-08-27 | 2011-03-30 | 鸿富锦精密工业(深圳)有限公司 | Scanned image noise clearing system and method |
CN103412947A (en) * | 2013-08-26 | 2013-11-27 | 浙江大学 | Polygon search method for big space data |
CN104794139A (en) * | 2014-01-22 | 2015-07-22 | 腾讯科技(北京)有限公司 | Information retrieval method, device and system |
CN104854539A (en) * | 2014-05-15 | 2015-08-19 | 华为技术有限公司 | Object searching method and device |
CN105468590A (en) * | 2014-06-18 | 2016-04-06 | 上海华力微电子有限公司 | Method for improving graph search accuracy |
CN106096669A (en) * | 2016-08-24 | 2016-11-09 | 上海柏楚电子科技有限公司 | A kind of method quickly selecting similar fitgures for CAD |
CN107644105A (en) * | 2017-10-18 | 2018-01-30 | 广东小天才科技有限公司 | One kind searches topic method and device |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103198067B (en) * | 2012-01-06 | 2016-08-10 | 卓望数码技术(深圳)有限公司 | A kind of service search method and system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100397400C (en) * | 2006-02-10 | 2008-06-25 | 华为技术有限公司 | Graphic retrieve method |
CN1851709A (en) * | 2006-05-25 | 2006-10-25 | 浙江大学 | Embedded multimedia content-based inquiry and search realizing method |
CN101071431A (en) * | 2007-01-31 | 2007-11-14 | 腾讯科技(深圳)有限公司 | Method and system for searching image based on key graph as search condition |
-
2007
- 2007-01-31 CN CNA2007100731897A patent/CN101071431A/en active Pending
-
2008
- 2008-01-31 WO PCT/CN2008/070225 patent/WO2008101422A1/en active Application Filing
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008101422A1 (en) * | 2007-01-31 | 2008-08-28 | Tencent Technology (Shenzhen) Company Limited | Image searching method and system |
CN101996394A (en) * | 2009-08-27 | 2011-03-30 | 鸿富锦精密工业(深圳)有限公司 | Scanned image noise clearing system and method |
CN101825989A (en) * | 2010-04-23 | 2010-09-08 | 杭州图酷科技有限公司 | Drag and drop image search input method |
CN103412947A (en) * | 2013-08-26 | 2013-11-27 | 浙江大学 | Polygon search method for big space data |
CN104794139A (en) * | 2014-01-22 | 2015-07-22 | 腾讯科技(北京)有限公司 | Information retrieval method, device and system |
CN104794139B (en) * | 2014-01-22 | 2019-09-20 | 腾讯科技(北京)有限公司 | Information retrieval method, apparatus and system |
CN104854539B (en) * | 2014-05-15 | 2018-08-14 | 华为技术有限公司 | A kind of object search method and device |
US10311115B2 (en) | 2014-05-15 | 2019-06-04 | Huawei Technologies Co., Ltd. | Object search method and apparatus |
CN104854539A (en) * | 2014-05-15 | 2015-08-19 | 华为技术有限公司 | Object searching method and device |
CN105468590A (en) * | 2014-06-18 | 2016-04-06 | 上海华力微电子有限公司 | Method for improving graph search accuracy |
CN105468590B (en) * | 2014-06-18 | 2020-06-30 | 上海华力微电子有限公司 | Method for improving graph search accuracy |
CN106096669A (en) * | 2016-08-24 | 2016-11-09 | 上海柏楚电子科技有限公司 | A kind of method quickly selecting similar fitgures for CAD |
CN107644105A (en) * | 2017-10-18 | 2018-01-30 | 广东小天才科技有限公司 | One kind searches topic method and device |
Also Published As
Publication number | Publication date |
---|---|
WO2008101422A1 (en) | 2008-08-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101071431A (en) | Method and system for searching image based on key graph as search condition | |
US9972108B2 (en) | Mixed media reality recognition with image tracking | |
US8493353B2 (en) | Methods and systems for generating and joining shared experience | |
Philbin et al. | Geometric latent dirichlet allocation on a matching graph for large-scale image datasets | |
US8634603B2 (en) | Automatic media sharing via shutter click | |
Girod et al. | Mobile visual search: Architectures, technologies, and the emerging MPEG standard | |
CN105631051A (en) | Character recognition based mobile augmented reality reading method and reading system thereof | |
US20030126126A1 (en) | Apparatus and method for searching multimedia object | |
CN102214222B (en) | Presorting and interacting system and method for acquiring scene information through mobile phone | |
CN102017661A (en) | Data access based on content of image recorded by a mobile device | |
CN106462728A (en) | Systems and methods for image-feature-based recognition | |
CN104903892A (en) | Searching system and searching method for object-based images | |
CN107292642B (en) | Commodity recommendation method and system based on images | |
CN104021150A (en) | Facial recognition with social network aiding | |
CN103530114A (en) | Picture managing method and device | |
CN103412954A (en) | Virtual dynamic magazine using augmented reality technique | |
CN103533169A (en) | Method for positioning and linking field of electronic business card based on mobile terminal | |
CN101853297A (en) | Method for fast obtaining expected image in electronic equipment | |
Shen et al. | Image-based indoor place-finder using image to plane matching | |
CN104331515A (en) | Method and system for generating travel journal automatically | |
CN104951801A (en) | Photo management method and system | |
CN103327163A (en) | Method for searching contact information and communication terminal thereof | |
CN102231149A (en) | Method for searching visual information of mobile phone based on local characteristics | |
CN110019913A (en) | Picture match method, user equipment, storage medium and device | |
EP3564833B1 (en) | Method and device for identifying main picture in web page |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Open date: 20071114 |