CN102262670A - Cross-media information retrieval system and method based on mobile visual equipment - Google Patents
Cross-media information retrieval system and method based on mobile visual equipment Download PDFInfo
- Publication number
- CN102262670A CN102262670A CN2011102151426A CN201110215142A CN102262670A CN 102262670 A CN102262670 A CN 102262670A CN 2011102151426 A CN2011102151426 A CN 2011102151426A CN 201110215142 A CN201110215142 A CN 201110215142A CN 102262670 A CN102262670 A CN 102262670A
- Authority
- CN
- China
- Prior art keywords
- image
- retrieval
- text
- module
- relevant
- 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
Abstract
The invention discloses a cross-media information retrieval system based on mobile visual equipment. The system provided by the invention comprises an image input module, a text input module, a text-based Internet image retrieval module, a content-based image retrieval module and a retrieval processing module, wherein the image input module is used for inputting an image into the mobile visual equipment; the text input module is used for inputting literal information relevant to the image; the text-based Internet image retrieval module is used for retrieving an image set relevant to the input literal information and setting up and generating a text-relevant image set; the content-based image retrieval module is used for retrieving an image matched with the input image in the text-relevant image set and setting up and generating a vision-relevant image set; and the retrieval processing module is used for extracting key words from a web page at which the image in the finally-found vision-relevant image set is located and then extracting relevant online contents and displaying a retrieved result. By retrieving through combining a text with the image, the cross-media information retrieval system based on the mobile visual equipment can be used for realizing accurate and fast cross-media and visual retrieval. The invention further discloses a cross-media information retrieval method based on the mobile visual equipment simultaneously.
Description
Technical field
The present invention relates to information retrieval field, particularly a kind ofly stride the media information retrieval system and method based on mobile visible equipment.
Background technology
Along with retrieval technique becomes more and more popular, retrieval also becomes an industry that commercial promise is arranged very much gradually.For example, search engine supplier gets a profit by the mode of subsidiary paid advertisement in the result who returns, and the technology so that research is upgraded provides the service of renewal, attracts more user and obtains more advertising income.Now, this competition has turned to wireless domain.Comprise traditional information retrieval, the local information retrieval of contiguous shop and article, or even the retrieval of background image.
Based on the mobile search of mobile visible equipment is a brand-new research topic that is expedited the emergence of by practical application request.Raising day by day along with people's living standard, the continuous development of science and technology, mobile visible equipment for example mobile phone, notebook computer etc. is widely applied in people's the life, and the system of the mobile search that forms gradually will change people's searching and buy daily commodity, mobile content and local information service manner.
Traditional information retrieval adopts the text retrieval technology mainly towards text, and related text document in localization of text and the database is retrieved in the inquiry that normally utilizes a set of keyword or speech to form.If comprise the more text relevant in certain document, so just think that the document is more relevant than the document that other comprise less query term with query term.Utilize the user of multi-medium data resource for hope, generally require them to possess certain knowledge background, could submit to and meet IR (Information Retrieval, information retrieval) the understandable inquiry of system requirements or IR system. still, in actual applications, a large number of users is not sufficient to clearly narrate its inquiry wish for the degree of being proficient in of some notion semanteme, if this moment, the IR system allowed the user to come describing mode input inquiry wish with multiple media information, will retrieve the more Query Result of multiple coincidence wish so.
Concerning multimedia messages collection such as image and video, present most searching system is still taked the text retrieval technology, for example the image of Google and video frequency searching function still are based on text key word, these keywords may derive from the text around the picture, filenames etc. wherein a spot ofly also may derive from artificial mark.So in the last few years, many researchists attempted to realize content-based multimedia information inquiry technology, to remedy the defective of above-mentioned multimedia information retrieval technology.The many researchists of newspaper are arranged in the content-based multimedia information retrieval technology of active research both at home and abroad, comprising to the contents processing of multimedia messagess such as image, video and audio frequency and analysis (parsing), mark (annotation) automatically, index building (indexing) and similar to search (retrieval) etc.Yet, in actual applications, a large number of users is not sufficient to clearly narrate its inquiry wish for the degree of being proficient in of some notion semanteme, if this moment, the IR system allowed the user to come describing mode input inquiry wish with multiple media information, will retrieve the more Query Result of multiple coincidence wish so.Can not be with the user inquiring of a certain or multiple medium expression way description, between the media information that dissimilar medium expression waies are described, search and relevant matches, only retrieve from single medium, make the correctness of user search reduce greatly, the information retrieval of failing to realize to stride medium is the information retrieval technique subject matter that need solve instantly.
Summary of the invention
The object of the present invention is to provide a kind of based on mobile visible equipment stride the media information retrieval system and method, can realize striding the information retrieval of medium, thereby get access to more accurate result for retrieval in conjunction with text and image retrieval.
For achieving the above object, the invention provides a kind of system of striding media information retrieval based on mobile visible equipment, comprise: image input module, text load module, text based the Internet images retrieval module, CBIR module and retrieval process module, described image input module are used for image is input in the described mobile visible equipment; Described text load module is used to import the Word message relevant with image; Described text based the Internet images retrieval module is used to retrieve the image collection related with the Word message of importing, and sets up the relevant image set of generation text; Described CBIR module is used for passing through at the relevant image set of text the image of retrieval and institute's input picture coupling, and sets up the image set of generation visual correlation; Described retrieval process module is used for extracting keyword from the webpage at the image place of the image set of the visual correlation that finally finds, and then extracts relevant online content, and shows result for retrieval.
Preferably, described mobile visible equipment is built-in with camera, and described image is by camera collection and be sent in the image input module.
Preferably, described mobile visible equipment is mobile phone.
Preferably, described system also comprises the query expansion module, described query expansion module is used for the Word message of being imported is expanded and will be generated text set with other literal of described Word message synonym, and described text based the Internet images retrieval module carries out the retrieval of associated images with described text set.
Correspondingly, the present invention also provides a kind of media information retrieval method of striding based on mobile visible equipment,, may further comprise the steps: step 1: obtain image; Step 2: import the Word message related with described image; Step 3: the retrieval of text based the Internet images is that index is retrieved in internet database with the Word message of being imported promptly; Step 4: extract and generate the relevant image set of text; Step 5: CBIR, the image of retrieval and described images match in the relevant image set of text; Step 6: the image set that extracts and generate visual correlation; Step 7: extract the keyword in the webpage of image place; Step 8: extract online content; Step 9: show result for retrieval.
Preferably, before the step of text based the Internet images retrieval, also comprise the query expansion step, described query expansion step is expanded the Word message of being imported and will be generated text set with other literal of described Word message synonym, and described text based the Internet images searching step carries out the retrieval of associated images with described text set.
Of the present inventionly stride the media information retrieval system and method based on mobile visible equipment, be to measure the similarity degree of the image in the inquiry picture image set relevant by the CBIR method, thereby find both visually similar pictures of the relevant justice of text with text.The descriptor that general pattern is commonly used mainly contains: features such as color, texture, shape.Because textural characteristics is not enough to differentiate the image that obtains on the mobile device.Information retrieval work on some mobile devices in the past only uses the CBIR method to inquire about similar image mostly, to excavate the more information of deep layer.Yet, in native system, consider calculation consumption and the degree of accuracy of on great amount of images, searching for, utilize the relevant Word message of input picture, obtain generation text correlogram image set earlier by the retrieval of text based the Internet images, and CBIR coupling task is just carried out on the text correlogram image set of smallest number, by this multi-modal input retrieval scheme of striding medium, realizes the more information retrieval of pin-point accuracy and faster speed.
Beneficial effect of the present invention mainly embodies as follows:
The first, the inquiry input of native system can be multi-modal, for example, and the more subsidiary prompting words of piece image;
The second, native system can use the relevant image set of a dynamic text rather than use a specific database;
The 3rd, in native system, at using widely and large-scale data.Therefore, except accuracy, the raising of search efficiency also is a key factor of this system high efficiency;
The 4th, traditional CBIR (Content Based Image Retrieval, the be called for short CBIR) effect of method under big data quantity is generally not good, and the result's of the vision-mix matching process that the native system scheme adopts accuracy wants high many.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, to do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art below, apparently, accompanying drawing in describing below only is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is a system architecture synoptic diagram of the present invention;
Fig. 2 is a method flow diagram of the present invention;
Fig. 3 is an embodiment of the invention figure.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the invention, the technical scheme in the embodiment of the invention is clearly and completely described, obviously, described embodiment only is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills belong to the scope of protection of the invention not making all other embodiment that obtained under the creative work prerequisite.
The present invention applies to the technology of striding the medium retrieval in the mobile search by in conjunction with text based internet retrieval technique and CBIR technology.Proposed one and be enclosed within and carry out visual search method under the big demand data, supported that the multi-user carries out multi-modal inquiry, realized striding easily intuitively on the mobile device medium, visual retrieval in order to realize the mobile search scheme of mobile device.
With reference to figure 1, a kind of system of striding media information retrieval provided by the invention based on mobile visible equipment, comprise: image input module 100, text load module 200, text based the Internet images retrieval module 400, CBIR module 500 and retrieval process module 600, described image input module 100 are used for image is input in the described mobile visible equipment; Described text load module 200 is used to import the Word message relevant with image; Described text based the Internet images retrieval module 400 is used to retrieve the image collection related with the Word message of importing, and sets up the relevant image set of generation text; Described CBIR module 500 is used for passing through at the relevant image set of text the image of retrieval and institute's input picture coupling, and sets up the image set of generation visual correlation; Described retrieval process module 600 is used for extracting keyword from the webpage at the image place of the image set of the visual correlation that finally finds, and then extracts relevant online content, and shows result for retrieval.Preferably, described system also comprises query expansion module 300, described query expansion module 300 is used for the Word message of being imported is expanded and will be generated text set with other literal of described Word message synonym, and described text based the Internet images retrieval module 400 carries out the retrieval of associated images with described text set.
Preferably, described mobile visible equipment is mobile phone.Preferably, described mobile visible equipment is built-in with camera, and described image is by camera collection and be sent in the image input module 100.Be appreciated that ground, described image also can be sent in the mobile phone by the form of mail or multimedia message mms, and described mobile visible equipment also can be notebook computer or other similar intelligent movable equipment.The common problem of striding media information retrieval based on mobile visible equipment is to be difficult to obtain query image sample (query image), obtains image by being built-in with the shooting of camera mobile phone, and is practical, easy to operate, but range of search is increased.A few thing in the past also utilizes camera built-in on these mobile phones to search the similar image of visual signature.Yet great majority are based on a limited and established data storehouse, and can only carry out simple image querying.Though more the Internet images can be added into into by the text based image search engine.Remain specific and initial pictures storehouse that scale is very limited but retrieval is adopted, be not suitable on large-scale data, carrying out general search.Native system obtains text correlogram image set by the retrieval of text based internet, concentrates from this limited text associated picture and carries out CBIR, improves the speed and the accuracy of retrieval.
With reference to figure 2, correspondingly, the present invention also provides a kind of media information retrieval method of striding based on mobile visible equipment,, may further comprise the steps: step 1: obtain image; Step 2: import the Word message related with described image; Step 3: the retrieval of text based the Internet images is that index is retrieved in internet database with the Word message of being imported promptly; Step 4: extract and generate the relevant image set of text; Step 5: CBIR, the image of retrieval and described images match in the relevant image set of text; Step 6: the image set that extracts and generate visual correlation; Step 7: extract the keyword in the webpage of image place; Step 8: extract online content; Step 9: show result for retrieval.
Preferably, before the step of text based the Internet images retrieval, also comprise the query expansion step, described query expansion step is expanded the Word message of being imported and will be generated text set with other literal of described Word message synonym, and described text based the Internet images searching step carries out the retrieval of associated images with described text set.
Cooperation is with reference to figure 3, and the media information retrieval system of striding based on mobile visible equipment of the present invention supports multi-modal input of striding medium.I.e. inquiry input can be image and the suggestive word of taking.At first add the relevant indicative speech of input, generate the relevant image collection of a text by the retrieval of text based image search engine according to image.Use the CBIR method in this set, to find out the very similar image of vision then.From the webpage at the image place finally found, extract key phrase (key phrase), and from these key phrases, extract the key phrase of the overall situation, thereby at online encyclopedia or other technical search engines obtain relevant information.
When submitting the text based query word to, the user usually is difficult to provide the complete description of the information of will searching.On mobile device, the user can only express the information that they want with one or two speech usually especially.These do not have the query word of fine definition that fuzzy description can only be provided, and therefore, it is not enough and cause poor Search Results information to occur.For the information beyond the query word that addresses this problem and disclose minority, the present invention has adopted the method for expanding query input speech, thereby obtains a series of new query word.Here, the expansion of query word is to use the correlativity semantically of vocabulary to carry out basically, and the basic query extender is based on the busy system of a large-scale general term.It covers small cup and has covered noun, verb, adjective and adverbial word in a large amount of English.These speech organize together with the synonym form basically, are called the synonym collection.These synonym collection are organized in together according to the vocabulary correlativity that is defined on them.If in initial input speech, there is the predefined no sincere word in the word of forbidding, as preposition " " (of), article " this " (the) and pronoun " " (one) or the like, these words will be deleted earlier. and remaining word is changed by algorithm, and is represented by their stem (stems).According to the relation of speech, being added in the newly-generated text set at synonym and the adopted down and concentrated word of listing.Except method, can also use enquiry expanding method based on certain aspect knowledge based on vocabulary.For example replenish the word relevant with special scenes by the knowledge base of some specific areas and the method for artificial intelligence.
The text set of this expansion is regarded as a text feature vector, in text based the Internet images retrieving, just can carry out the coupling of proper vector by word index.Promptly be all words in the superset with " or " relation deliver in the searching system.Like this, can be given higher grade with query text collection more approaching image on the text degree of correlation.According to this grade, the picture of some is selected to come out, and constitutes the relevant image set of a text, thereby continues to find out from this image set visually relevant image.
The Content-Based Image Retrieval method is also having very big tomography aspect the characteristics of image of Treated Base and the high-rise semantic concept, correct image may be not in the front of result for retrieval tabulation.In addition, because the restriction of low bandwidth and the small screen on the mobile device can not provide too many result images to the mobile subscriber.In order to solve above-mentioned difficulty and to excavate useful information implicit in the web content, in native system, the webpage relevant with image carried out keyword abstraction, and this keyword and image be stored in one and index simultaneously, as the index II among Fig. 2, the content of index comprises the identification code of image (ID), visual signature, image content and number of pages.The analysis that keyword is based on the statistical property of word in the webpage and architectural characteristic carries out that off line extracts.Before selecting keyword, extract the text context information of certain image according to the topology layout that proposes in HTML DOM (the Document Object Model) tree.Wherein, the content of asking of the obvious separator of image is as the contextual information of text.All text fragment (surrounding text segments) on every side that obtain are counted as taking in the solid pieces of chapter (article).Subsequent, therefrom extract the keyword of this image based on this chapter.
The media information retrieval system of striding based on mobile visible equipment of the present invention, be to measure the similarity degree of the image in the inquiry picture image set relevant by the CBIR method, thereby find both visually similar pictures of the relevant justice of text with text.The descriptor that general pattern is commonly used mainly contains: features such as color, texture, shape.Because textural characteristics is not enough to differentiate the image that obtains on the mobile device.Information retrieval work on some mobile devices in the past only uses the CBIR method to inquire about similar image mostly, to excavate the more information of deep layer.Yet, in native system, consider calculation consumption and the degree of accuracy of on great amount of images, searching for, utilize the relevant Word message of input picture, obtain generation text correlogram image set earlier by the retrieval of text based the Internet images, and CBIR coupling task is just carried out on the text correlogram image set of smallest number, by this multi-modal input retrieval scheme of striding medium, realizes the more information retrieval of pin-point accuracy and faster speed.
Beneficial effect of the present invention mainly embodies as follows:
The first, the inquiry input of native system can be multi-modal, for example, and the more subsidiary prompting words of piece image;
The second, native system can use the relevant image set of a dynamic text rather than use a specific database;
The 3rd, in native system, at using widely and large-scale data.Therefore, except accuracy, the raising of search efficiency also is a key factor of this system high efficiency;
The 4th, traditional CBIR (Content Based Image Retrieval, the be called for short CBIR) effect of method under big data quantity is generally not good, and the result's of the vision-mix matching process that the native system scheme adopts accuracy wants high many.
The technical scheme that the purpose of this invention is to provide mobile search system in illustrates how to use the technology of striding the medium retrieval to carry out mobile search.Proposed one with regard to two kinds of common customer information requirements and be enclosed within the algorithm that carries out visual search under the big data quantity, thereby realized having on the mobile device of built-in camera the user of support carry out multi-modal, as to stride Media Inquiries mobile search scheme.Need to prove that the technical scheme that the present invention mentioned is the research that utilizes the built-in camera of mobile device to retrieve, all is the method round retrieval of text based the Internet images and CBIR.Return be to the query image global characteristics on more similar image.Therefore specifically being well known to those skilled in the art of text based search engine and CBIR no longer described in detail.Information requirements for the first kind. the matching scheme that then needs to carry out more meticulous (fine-grain) goes to search and comprises and the same obvious object or the scene of inquiry picture, and call duplicate image (identical image) to this class image here.Discern the same object or the method for scene by the partial descriptions symbol, can realize satisfactory results aspect Target Recognition and the duplicate image detection.Utilize local feature to detect sub-detected characteristics point or zone, extract unique point feature on every side simultaneously, and it is showed with the partial descriptions symbol.Partial descriptions symbols is obtained good effect aspect the image that changes because of convergent-divergent, cutting, shearing, rotation, local deepening or operations such as blast and contrast variation handling.Simultaneously, they also have unchangeability for to a certain degree visual angle and illumination variation.
More than to a kind of system and method for striding media information retrieval that the embodiment of the invention provided based on mobile visible equipment, be described in detail, 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. the media information retrieval system of striding based on mobile visible equipment is characterized in that, comprising:
Image input module is used for image is input in the described mobile visible equipment;
The text load module is used to import the Word message relevant with image;
Text based the Internet images retrieval module is used to retrieve the image collection related with the Word message of importing, and sets up the relevant image set of generation text;
The CBIR module, the image that in the relevant image set of text, mates by retrieval and institute's input picture, and set up the image set that generates visual correlation;
The retrieval process module is used for extracting keyword from the webpage at the image place of the image set of the visual correlation that finally finds, and then extracts relevant online content, and shows result for retrieval.
2. the system as claimed in claim 1 is characterized in that, described mobile visible equipment is built-in with camera, and described image is by camera collection and be sent in the image input module.
3. system as claimed in claim 1 or 2 is characterized in that, described mobile visible equipment is mobile phone.
4. the system as claimed in claim 1, it is characterized in that, also comprise the query expansion module, described query expansion module is used for the Word message of being imported is expanded and will be generated text set with other literal of described Word message synonym, and described text based the Internet images retrieval module carries out the retrieval of associated images with described text set.
5. the media information retrieval method of striding based on mobile visible equipment is characterized in that, may further comprise the steps:
Step 1: obtain image;
Step 2: import the Word message related with described image;
Step 3: the retrieval of text based the Internet images is that index is retrieved in internet database with the Word message of being imported promptly;
Step 4: extract and generate the relevant image set of text;
Step 5: CBIR, the image of retrieval and described images match in the relevant image set of text;
Step 6: the image set that extracts and generate visual correlation;
Step 7: extract the keyword in the webpage of image place;
Step 8: extract online content;
Step 9: show result for retrieval.
6. method as claimed in claim 5 is characterized in that, described mobile visible equipment is built-in with camera, and the image in the described step 1 obtains by described camera.
7. as claim 5 or 6 described methods, it is characterized in that described mobile visible equipment is mobile phone.
8. method as claimed in claim 5, it is characterized in that, before the step of text based the Internet images retrieval, also comprise the query expansion step, described query expansion step is expanded the Word message of being imported and will be generated text set with other literal of described Word message synonym, and described text based the Internet images searching step carries out the retrieval of associated images with described text set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102151426A CN102262670A (en) | 2011-07-29 | 2011-07-29 | Cross-media information retrieval system and method based on mobile visual equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011102151426A CN102262670A (en) | 2011-07-29 | 2011-07-29 | Cross-media information retrieval system and method based on mobile visual equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102262670A true CN102262670A (en) | 2011-11-30 |
Family
ID=45009299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011102151426A Pending CN102262670A (en) | 2011-07-29 | 2011-07-29 | Cross-media information retrieval system and method based on mobile visual equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102262670A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855298A (en) * | 2012-08-16 | 2013-01-02 | 熊兵 | Image retrieval method and system |
| CN103064903A (en) * | 2012-12-18 | 2013-04-24 | 厦门市美亚柏科信息股份有限公司 | Method and device for searching images |
| CN103389849A (en) * | 2012-05-07 | 2013-11-13 | 腾讯科技（北京）有限公司 | Image presentation method and system based on mobile terminal and mobile terminal |
| CN103425757A (en) * | 2013-07-31 | 2013-12-04 | 复旦大学 | Cross-medial personage news searching method and system capable of fusing multi-mode information |
| WO2013177751A1 (en) * | 2012-05-29 | 2013-12-05 | 中国科学院自动化研究所 | Cross-media retrieval method based on generalized linear regression model |
| CN104008146A (en) * | 2014-05-09 | 2014-08-27 | 中国科学院信息工程研究所 | Image query expansion method and system based on common visual patterns |
| WO2014166196A1 (en) * | 2013-04-10 | 2014-10-16 | 中兴通讯股份有限公司 | Picture displaying and managing method and system with character introduction function |
| CN105320703A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Query expansion method and device in retrieval of similar vehicle |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN106485196A (en) * | 2015-08-28 | 2017-03-08 | 意法半导体股份有限公司 | Visual search method, corresponding system, equipment and computer program |
| CN103870500B (en) * | 2012-12-14 | 2017-05-24 | 联想(北京)有限公司 | Searching method and searching device |
| CN109117435A (en) * | 2017-06-22 | 2019-01-01 | 索意互动（北京）信息技术有限公司 | A kind of client, server, search method and its system |
| US10339146B2 (en) | 2014-11-25 | 2019-07-02 | Samsung Electronics Co., Ltd. | Device and method for providing media resource |
| CN112861944A (en) * | 2021-01-28 | 2021-05-28 | 中山大学 | Image retrieval method and device based on mixed modal input |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1881212A (en) * | 2006-05-10 | 2006-12-20 | 南京大学 | Graphic and text cooperation method in web search |
| CN1920818A (en) * | 2006-09-14 | 2007-02-28 | 浙江大学 | Transmedia search method based on multi-mode information convergence analysis |
| CN101021849A (en) * | 2006-09-14 | 2007-08-22 | 浙江大学 | Transmedia searching method based on content correlation |
| WO2008020891A2 (en) * | 2006-08-10 | 2008-02-21 | Cisco Technology, Inc. | Method and system for improving timing position estimation in wireless communications networks |
| CN101236567A (en) * | 2008-02-04 | 2008-08-06 | 上海升岳电子科技有限公司 | Method and terminal apparatus for accomplishing on-line network multimedia application |
| CN101458695A (en) * | 2008-12-18 | 2009-06-17 | 西交利物浦大学 | Mixed picture index construct and enquiry method based on key word and content characteristic and use thereof |
| CN101853297A (en) * | 2010-05-28 | 2010-10-06 | 英华达(南昌)科技有限公司 | Method for fast obtaining expected image in electronic equipment |
| CN101877007A (en) * | 2010-05-18 | 2010-11-03 | 南京师范大学 | Remote sensing image retrieval method with integration of spatial direction relation semanteme |
| CN101901249A (en) * | 2009-05-26 | 2010-12-01 | 复旦大学 | Text-based query expansion and sort method in image retrieval |
| CN101945327A (en) * | 2010-09-02 | 2011-01-12 | 郑茂 | Wireless positioning method and system based on digital image identification and retrieve |
| CN101996191A (en) * | 2009-08-14 | 2011-03-30 | 北京大学 | Method and system for searching for two-dimensional cross-media element |
-
2011
- 2011-07-29 CN CN2011102151426A patent/CN102262670A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1881212A (en) * | 2006-05-10 | 2006-12-20 | 南京大学 | Graphic and text cooperation method in web search |
| WO2008020891A2 (en) * | 2006-08-10 | 2008-02-21 | Cisco Technology, Inc. | Method and system for improving timing position estimation in wireless communications networks |
| CN1920818A (en) * | 2006-09-14 | 2007-02-28 | 浙江大学 | Transmedia search method based on multi-mode information convergence analysis |
| CN101021849A (en) * | 2006-09-14 | 2007-08-22 | 浙江大学 | Transmedia searching method based on content correlation |
| CN101236567A (en) * | 2008-02-04 | 2008-08-06 | 上海升岳电子科技有限公司 | Method and terminal apparatus for accomplishing on-line network multimedia application |
| CN101458695A (en) * | 2008-12-18 | 2009-06-17 | 西交利物浦大学 | Mixed picture index construct and enquiry method based on key word and content characteristic and use thereof |
| CN101901249A (en) * | 2009-05-26 | 2010-12-01 | 复旦大学 | Text-based query expansion and sort method in image retrieval |
| CN101996191A (en) * | 2009-08-14 | 2011-03-30 | 北京大学 | Method and system for searching for two-dimensional cross-media element |
| CN101877007A (en) * | 2010-05-18 | 2010-11-03 | 南京师范大学 | Remote sensing image retrieval method with integration of spatial direction relation semanteme |
| CN101853297A (en) * | 2010-05-28 | 2010-10-06 | 英华达(南昌)科技有限公司 | Method for fast obtaining expected image in electronic equipment |
| CN101945327A (en) * | 2010-09-02 | 2011-01-12 | 郑茂 | Wireless positioning method and system based on digital image identification and retrieve |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389849A (en) * | 2012-05-07 | 2013-11-13 | 腾讯科技（北京）有限公司 | Image presentation method and system based on mobile terminal and mobile terminal |
| WO2013177751A1 (en) * | 2012-05-29 | 2013-12-05 | 中国科学院自动化研究所 | Cross-media retrieval method based on generalized linear regression model |
| CN102855298A (en) * | 2012-08-16 | 2013-01-02 | 熊兵 | Image retrieval method and system |
| CN102855298B (en) * | 2012-08-16 | 2016-08-03 | 熊兵 | Image search method and system |
| CN103870500B (en) * | 2012-12-14 | 2017-05-24 | 联想(北京)有限公司 | Searching method and searching device |
| CN103064903A (en) * | 2012-12-18 | 2013-04-24 | 厦门市美亚柏科信息股份有限公司 | Method and device for searching images |
| CN103064903B (en) * | 2012-12-18 | 2017-08-01 | 厦门市美亚柏科信息股份有限公司 | Picture retrieval method and device |
| WO2014166196A1 (en) * | 2013-04-10 | 2014-10-16 | 中兴通讯股份有限公司 | Picture displaying and managing method and system with character introduction function |
| CN103425757A (en) * | 2013-07-31 | 2013-12-04 | 复旦大学 | Cross-medial personage news searching method and system capable of fusing multi-mode information |
| CN104008146B (en) * | 2014-05-09 | 2017-02-15 | 中国科学院信息工程研究所 | Image query expansion method and system based on common visual patterns |
| CN104008146A (en) * | 2014-05-09 | 2014-08-27 | 中国科学院信息工程研究所 | Image query expansion method and system based on common visual patterns |
| CN105320703A (en) * | 2014-08-05 | 2016-02-10 | 北京大学 | Query expansion method and device in retrieval of similar vehicle |
| CN105320703B (en) * | 2014-08-05 | 2018-07-24 | 北京大学 | Enquiry expanding method and device in similar vehicle retrieval |
| US10339146B2 (en) | 2014-11-25 | 2019-07-02 | Samsung Electronics Co., Ltd. | Device and method for providing media resource |
| CN106485196A (en) * | 2015-08-28 | 2017-03-08 | 意法半导体股份有限公司 | Visual search method, corresponding system, equipment and computer program |
| US10585937B2 (en) | 2015-08-28 | 2020-03-10 | Stmicroelectronics S.R.L. | Method for visual search, corresponding system, apparatus and computer program product |
| CN106202514A (en) * | 2016-07-21 | 2016-12-07 | 北京邮电大学 | Accident based on Agent is across the search method of media information and system |
| CN109117435A (en) * | 2017-06-22 | 2019-01-01 | 索意互动（北京）信息技术有限公司 | A kind of client, server, search method and its system |
| CN112861944A (en) * | 2021-01-28 | 2021-05-28 | 中山大学 | Image retrieval method and device based on mixed modal input |
| CN112861944B (en) * | 2021-01-28 | 2022-09-23 | 中山大学 | Image retrieval method and device based on mixed modal input |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102262670A (en) | Cross-media information retrieval system and method based on mobile visual equipment | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| JP6416150B2 (en) | Search method, search system, and computer program | |
| US8554854B2 (en) | Systems and methods for identifying terms relevant to web pages using social network messages | |
| Silva et al. | Adding geographic scopes to web resources | |
| CN105824959B (en) | Public opinion monitoring method and system | |
| US20220261427A1 (en) | Methods and system for semantic search in large databases | |
| US10445359B2 (en) | Method and system for classifying media content | |
| CN104537116B (en) | A kind of books searching method based on label | |
| CN104216942A (en) | Query suggestion templates | |
| WO2022068543A1 (en) | Multimedia content publishing method and apparatus, and electronic device and storage medium | |
| Zhang et al. | A novel hot topic detection framework with integration of image and short text information from twitter | |
| Fan et al. | Photo-to-search: using multimodal queries to search the web from mobile devices | |
| CN111881283A (en) | Business keyword library creating method, intelligent chat guiding method and device | |
| EP3485394A1 (en) | Contextual based image search results | |
| Li et al. | Question answering over community-contributed web videos | |
| US20070112839A1 (en) | Method and system for expansion of structured keyword vocabulary | |
| Bellare et al. | Lightly-supervised attribute extraction | |
| CN107423294A (en) | A kind of community image search method and system | |
| Akasaki et al. | Early discovery of emerging entities in microblogs | |
| Wu et al. | Clustering results of image searches by annotations and visual features | |
| EP1876539A1 (en) | Method and system for classifying media content | |
| Liu et al. | Multigraph-based query-independent learning for video search | |
| Jadhav et al. | Twitris: socially influenced browsing | |
| Dai et al. | Efficient tag mining via mixture modeling for real-time search-based image annotation |
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 |
Application publication date: 20111130 |