CN106909684A - Panoramic picture is retrieved and methods of exhibiting - Google Patents
Panoramic picture is retrieved and methods of exhibiting Download PDFInfo
- Publication number
- CN106909684A CN106909684A CN201710126566.2A CN201710126566A CN106909684A CN 106909684 A CN106909684 A CN 106909684A CN 201710126566 A CN201710126566 A CN 201710126566A CN 106909684 A CN106909684 A CN 106909684A
- Authority
- CN
- China
- Prior art keywords
- image
- index
- panorama
- feature
- user
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/5838—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using colour
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Processing Or Creating Images (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A kind of panoramic picture retrieval and methods of exhibiting, it is characterised in that main to include index establishment step（A）With image querying step（B）, index establishment step（A）The feature of the image file in picture library is extracted, index file is generated；User（C）To image querying step（B）The image to be retrieved is uploaded, by image querying step（B）Extraction will retrieve the feature of image, by user（C）The image of upload and index establishment step（A）The feature of index file carry out similarity mode, and to user（C）Matching result list is provided.It is an advantage of the invention that：System design simultaneously realizes panoramic picture search function, it is intended to allow user to upload normal picture, system can be returned correspond to therewith and similar panorama sketch information and panorama displaying, allow user quickly to navigate to corresponding scene, improve Consumer's Experience, very easy to use.
Description
Technical field
The present invention relates to a kind of retrieval of panoramic picture and methods of exhibiting, it is mainly used in digital culture multidimensional exhibition, Yi Jiyong
Show in the multidimensional panorama of every profession and trade environment, product etc..The present invention is various to Public Culture Service content-form, mutual in face of the public
The dynamic demand for participating in, by WebGIS, the integrated use of the technology such as Web3D and virtual reality can be used to research and develop old revolutinary base area spy
Color digital culture multidimensional, interactive experience application service system, there is provided various culture such as museum 3D displayings, ruins former residence Panoramic Warping
Circulation way, realizes that cultural taste is experienced by the multiple network terminal such as mobile phone, computer, publicized on line so as to be reached, line lower body
Test the purpose of cultural issues.
Background technology
It is currently at internet to contain emerging epoch, common word, 2-dimentional photo information far can not meet user
Visual experience variation and the demand of Information Communication abundantization, 3D, Panoramic Warping technology are by feat of the superpower sense of reality and rich
Rich information content, has been widely used in all trades and professions, for they provide more comprehensively, more rich, more perfect Digital Display
Scheme.Many industry such as house property, hotel, civic building, university campus, automobile indoor settings etc. are all doing the comprehensive exhibition of some products
The work shown, including the well-known e-commerce venture such as Taobao, Jingdone district, also all by correlation techniques such as 3D, intuitively to
Family shows product information.
Likewise, as red museum, this instructive place of tool of revolutionary site former residence, how to allow user with more
Full visual effect sense of reality publicized on line, the purpose of line experience cultural issues to Locale information so as to reach, it appears
It is particularly important.For cultural place manager, a panorama displaying method that function is full, abundant in content and interactivity is good,
Can well help carry out propaganda work, attract user.
Sometimes, user is interested for some particular culture pictures, but do not know belong in museum or ruins it is specific which
It is individual to view and admire a little, can only be found according to specific route in system, interactivity is very poor, and efficiency is very low.
Technically, traditional image retrieval is described first by caption based on word to image, then
Picture and description are stored in database according to corresponding relation, what is finally retrieved refers to the retrieval to word, by what is retrieved
Word description corresponds to picture again.This retrieval mode needs artificial addition to each pictures to describe, in face of current magnanimity
Panoramic picture resource, workload will be very huge, it is clear that has been not suitable for current system.
The content of the invention
It is an object of the invention to provide a kind of retrieval of panoramic picture and methods of exhibiting, to solve the interaction of prior art presence
The very poor, efficiency of property is very low and in-convenience in use problem.
The technical scheme is that：A kind of panoramic picture retrieval and methods of exhibiting, it is characterised in that main to include index
Establishment step A and image querying step B, index establishment step A extract the feature of the image file in picture library, generation index text
Part；User C uploads the image to be retrieved to image querying step B, and being extracted by image querying step B will retrieve the feature of image,
The image that user C is uploaded carries out similarity mode with the feature of the index file of index establishment step A, and is provided to user C
Matching result list, panorama displaying is done to result.
The specific method of the feature extraction in described index establishment step A and image querying step B includes：
Step1：Obtain panorama image information；
Step2：Traversal image resource, will be cut into 40*40=1600 small picture block per pictures；
Step3：To each image block, by CEDD instruments, make RGB models and turn HSV model treatments；
Step4：By 10-bins blur filters, the HSV information outputs that will be obtained to 10 dimension histograms；
Step5：10 dimension histograms and S (saturation degree), V (brightness) component in Step4 are input to 24-bins blur filters
In device, 24 dimension histograms of thumbnail are obtained；
Step6：Each small image block is made into RGB models and turns YIQ model treatments；
Step7：Again by each blockage quartering, the digital filter structure used during texture information is extracted is corresponded to, point
Each piece of gray value is not calculated and is normalized；
Step8：The texture information of each piece for obtaining is planned in 6 dimension edge histograms；
Step9：Two parts histogram that will be obtained in Step5 and Step8 is combined, and obtains one 144 dimension histogram, completes image
The extraction work of feature.
The detailed step of described index establishment step A is as follows：
Step1:Create document composer DocumentBuilder (CEDD.class) object, and the characteristics of image letter that will be obtained
Breath is dissolved into composer；
Step2：Using document composer, image feature information is added in the document D ocument of structure；
Step3：Index of definition document write-in object IndexWrite；
Step4：Finally, will be indexed during document D ocument writes server by configuration address by writing object.
The detailed step of described image querying step B is as follows：
Step1:Obtain image of the user by take pictures upload or Network Capture；
Step2：The characteristic value of input picture is extracted using extract ()；
Step3：According to the characteristic value extracted, similar picture is searched using findSimilar ()；
Step4:A newly-built ImageSearchHits is used to store the result searched；
Step5：Traversal ImageSearchHits, gets correspondence or similar panorama sketch for information about respectively, including score,
Path and name information.
Also include the specific steps that Krpano frameworks realize Panoramic Warping are given below：
Step1：Browser loads html files, and the html files do the entrance configuration of Panoramic Warping, including set Panoramic Warping
Xml document；
Step2：The html pages load Krpano html5 panorama engines；
Step3：The main xml document of panorama engine loading correspondence panorama sketch, the xml document is configured with and is obtained by image search method
The results list for arriving, reads panorama image resource；
Step4：The panorama resource that will be read, is added in container with browser-presented.
It is an advantage of the invention that：Realize panoramic picture search function, it is intended to allow user to upload normal picture, and can return
Correspond to therewith and similar panorama sketch information and panorama displaying, allow user quickly to navigate to corresponding scene, improve user's body
Test, it is very easy to use.
Brief description of the drawings
Fig. 1 is basic flow sheet of the invention；
Fig. 2 is index creation flow chart of the invention；
Fig. 3 is inverted index corresponding relation figure of the invention；
Fig. 4 is index file catalogue of the invention；
Fig. 5 is image querying flow of the invention；
Fig. 6 is modification xml path configuration informations of the invention；
Fig. 7 is Krpano loadings panorama sketch process schematic of the invention.
Specific embodiment
Referring to Fig. 1, a kind of panoramic picture of the invention is retrieved and methods of exhibiting, it is characterised in that main to include that index is set up
Step A and image querying step B, index establishment step A extracts the feature of the image file in picture library, generates index file；With
Family C uploads the image to be retrieved to image querying step B, and being extracted by image querying step B will retrieve the feature of image, by user
The image that C is uploaded carries out similarity mode with the feature of the index file of index establishment step A, and provides matching knot to user C
Fruit list.
Runtime of the invention（System mentioned below is the present invention and runtime）Mainly server and user
Terminal, picture library is located in server, and user terminal includes smart mobile phone and various PC.The invention mainly comprises 3 big functions：Input
Function, search function, query function.Input function is mainly carries out feature extraction to panoramic picture resources bank, and index is set up, so
Index file is preserved afterwards.Search function is mainly and index file is retrieved and is filtered.Last query function is mainly root
According to the feedback of user, the panoramic picture similar to the picture that user uploads is retrieved.Flow of the present invention is：System is carried successively first
Take the feature of panoramic picture in picture library, generate index file, and index file is saved in server is used for retrieval.Then
User signs in server and uploads image by user terminal, and it is similar that extraction user submits to the feature of image to be carried out to index file
Property matching, image is returned into user according to the order of Similarity value height（As shown in Figure 1）.
Figure core process of the invention is described in detail below, mainly there is image characteristics extraction, index creation and image to look into
Ask.
1st, image retrieval flow：
（1）Image characteristics extraction：
Core of the invention includes two big functions, creates index and inquires about.It is to be carried to substantial amounts of image resource to create index
Characteristics of image is taken, index database preservation is set up, the troublesome operation that picture library extracts feature is traveled through when saving retrieval every time, carried significantly
Rise recall precision.Inquiry operation is needed also exist for extracting image characteristic analysis and compared with the image resource information in index database, most
After obtain the results list.
From this, in whole image retrieving, image characteristics extraction serves highly important effect, below will
Tell about the first step of the invention --- image characteristics extraction.Image is mentioned, it is most exactly intuitively color to inform us, that is,
Say that color is most intuitively visual signature, the colouring information that piece image is technically represented by color histogram is also most straight
Connect simplest conventional method.But piece image is retrieved only by colouring information, accuracy rate is low-down, it is necessary to will
When image unity and coherence in writing characteristic information is also added to retrieve in the factor to be inquired about.
So during feature extraction, the texture information of image is also to have to one of factor for considering, and texture is special
Levying histogram can be divided into multiple classifications by the texture information of image, while can be by the good combination of colouring information one
Rise.Directionality description (Color and Edge Directivity Descriptor, CEDD) at color and edge is exactly to combine
A kind of description method of color of image and texture.So in system development, we used the image inspection based on Lucene
The image characteristic extracting method that rope instrument (Lucene Image Retrieval, LIRE) is provided.
Feature extraction pair as if system maintenance personnel upload panoramic picture.Concretely comprise the following steps：
Step1：Obtain the panorama image information that system maintenance personnel upload.
Step2：Traversal image resource, will be cut into 40*40=1600 small picture block per pictures.
Step3：To each image block, by CEDD instruments, make RGB models and turn HSV model treatments（It is routine techniques,
Referring to document, " RGB color model and hsv color model conversion realizes scientific and technological informations, 2009 (2) in the gorgeous VB of Tang Guang:
457-458”）.
Step4：By 10-bins blur filters, the HSV information outputs that will be obtained to 10 dimension histograms.
Step5：10 dimension histograms and S (saturation degree), V (brightness) component in Step4 are input into 24-bins to obscure
In filter, 24 dimension histograms of thumbnail are obtained.
Step6：Each small image block is made into RGB models and turns YIQ model treatments.
Step7：Again by each blockage quartering, the digital filter knot used during texture information is extracted is corresponded to
Structure, calculates each piece of gray value and normalizes respectively.
Step8：The texture information of each piece for obtaining is planned in 6 dimension edge histograms.
Step9：Two parts histogram that will be obtained in step5 and step8 is combined, and obtains one 144 dimension histogram, is completed
Image zooming-out works.The specific method of each step is routine techniques above（Referring to document " Fu Zhicheng, Li Xiaoqiang, Li Fu phoenix
Tongue picture based on radial edges detection and Snake models splits Journal of Image and Graphics, 2009,14 (4):688-693；
Basil G. Mertzios, Konstantinos D. Tsirikolias. Coordinate logic filters:
theory and applications in image analysis. Nonlinear image processing.2001:
331-354；The adaptive flesh colour detection algorithm University of Fuzhou journal that Wei Zhen, Zhu Min treasure are based on YIQ color spaces is (natural
Science version), 2008,36 (3):336-340；Official is pretty peaceful, Qin Tuanfa, texture and color in the synthesis MPEG-7 such as handsome duty
The image search method computer applications research of feature, 2008,25 (3):957-960.”）.
The core code of generation characteristic information is given below：
Fuzzy10BinResultTable = Fuzzy10.ApplyFilter(HSV[0], HSV[1], HSV[2], 2);
Fuzzy24BinResultTable = Fuzzy24.ApplyFilter(HSV[0], HSV[1], HSV[2],
Fuzzy10BinResultTable, 2);
for (inti = 0; i<= T; i++) {
for (intj = 0; j< 24; j++) {
if (Fuzzy24BinResultTable[j] > 0) CEDD[24 *Edges[i] + j] +=
Fuzzy24BinResultTable[j];
}
}
（2）Create index：
It is above-mentioned（1）Save us and obtain the color and textural characteristics of image.In order to reduce amount of calculation during inquiry, inquiry effect is improved
Rate, inverted index is built to characteristic information.Index creation process is illustrated in fig. 2 shown below.
Its principle is that in index database, the characteristic information of each pictures can all correspond to unique No. ID, a generation rope
When drawing catalogue, characteristic value and its corresponding relation appeared in certain record are preserved.Such as feature Feature1 is 1 and 3 in ID
Image feature information in, then save as Feature1->1,3.Inverted index schematic diagram is as shown in Figure 3.
Establishment index detailed step is given below：
Step1:Document composer DocumentBuilder (CEDD.class) object is created, and image feature information is incorporated
To in composer.
Step2：Using document composer, image feature information is added in the document D ocument of structure.
Step3：Index of definition document write-in object IndexWrite.
Step4：Finally, will be indexed during document D ocument writes server by configuration address by writing object.
The core code for creating index document is as follows：
for (Iterator<String>it = images.iterator(); it.hasNext(); ) {
String imageFilePath = it.next();
BufferedImage img = ImageIO.read(new FileInputStream(imageFilePath));
Document document = globalDocumentBuilder.createDocument(img,
imageFilePath);
iw.addDocument(document);
}
The index list structure for having created is as shown in Figure 4.
（3）Image querying：
Pass through（1）Section and（2）The work of section, we have obtained the feature of image and have created index file, below will
Introduce the process of panoramic picture inquiry.The particular flow sheet of image querying is given first, as shown in Figure 5.
Retrieve functions of modules mainly to be realized by Searcher classes, GenericFastImageSearcher is have invoked first
Class, sets the quantity of returning result, the method that characteristic value is extracted in addition.Code is as follows：
ImageSearcher searcher = new GenericFastImageSearcher(30, CEDD.class);
Next calls search (img, ir) method of ImageSearchHits classes, and wherein img is the path of picture to be searched,
Ir is the index file information for reading.In search methods, the distance of image and characteristic value in index is queried by comparing
(maxDistance=findSimilar (reader, globalFeature)), return meets the result of specific threshold.
Its detailed step is given below：
Step1:Obtain user and upload image.
Step2：The characteristic value of input picture is extracted using extract ().
Step3：According to the characteristic value extracted, similar picture is searched using findSimilar ().
Step4:A newly-built ImageSearchHits is used to store the result searched.
Step5：Traversal ImageSearchHits, gets score, path, the title of correspondence or similar panorama sketch respectively
Etc. information.
2nd, Panoramic Warping displaying：
The panorama retrieval flow saved by above-mentioned 1, we can obtain a series of panorama Figure Lists similar to user's inquiry, purpose
It is to carry out 360 ° of comprehensive displayings.After obtaining list, it is necessary first to the xml document of change configuration panorama sketch, make the road in file
Footpath information points to the result of this inquiry.Then panorama engine load document could realize the panorama displaying of this Query Result.
The process of xml document modification is as shown in Figure 6.
Panoramic Warping operation will be done to panorama sketch below.Have already given above and realized with the mode of Krpano.Which master
Realize it being that Krpano html5 panorama engines are loaded by html files, read panoramic picture, and be shown to the mistake of browser
Journey.Implementation process is illustrated in fig. 7 shown below.
The specific steps that Krpano frameworks realize Panoramic Warping are given below：
Step1：Browser loads html files, and the html files do the entrance configuration of Panoramic Warping, including set Panoramic Warping
Xml document.
Step2：The html pages load Krpano html5 panorama engines.
Step3：The main xml document of panorama engine loading correspondence panorama sketch, the xml document is configured with by image retrieval flow
The results list for getting, reads panorama image resource.
Step4：The panorama resource that will be read, is added in container with browser-presented.
4 steps more than, it is possible to achieve panorama shows.In last, the panorama sketch that user clicks on of panorama sketch retrieval module
Will show, remaining panorama will show that it is any that user can click on thumbnail in the form of thumbnail below browser
Switching, facilitates user to check.
To sum up, the detailed process that panorama displaying is retrieved from panoramic picture is realized, can be very good to solve prior art
The interactivity of presence is very poor, efficiency is very low and in-convenience in use problem.
The function declaration of panorama retrieval of the present invention and displaying is as follows：
The upload panorama sketch button first clicked under the homepage panoramic picture management of backstage jumps to the upload page.
After having uploaded all panoramic pictures, the establishment index that administrative staff are clicked under the homepage panoramic picture management of backstage is pressed
Button, performs index creation work.The index file for creating index generation is stored in server, and the file structure of index has been described above
Be given.
After completing above-mentioned work, in browser access system home page.System support browser include Chrome32 and
The above, Firefox, cheetah browser and other browsers with Chrome as kernel.
System realizes image retrieval function, and in the system home page page, user clicks on picture retrieval button, jumps to use
Family uploads search pictures interface.
Present invention uses image retrieval (CBIR, Content the Based Image based on image content
Retrieval), the method is, by extracting characteristics of image, setting up index database, image retrieval to be completed finally by matching characteristic
, this mode not only substantially increases the accuracy rate and efficiency of retrieval, and process is all automatically performed, it is not necessary to artificial
Intervene.
The concrete methods of realizing of each step is routine techniques in the present invention.
Claims (5)
1. a kind of panoramic picture is retrieved and methods of exhibiting, it is characterised in that main to include index establishment step A and image querying step
Rapid B, index establishment step A extracts the feature of the image file in picture library, generates index file；User C is to image querying step B
The image to be retrieved is uploaded, being extracted by image querying step B will retrieve the feature of image, the image and index that user C is uploaded
The feature of the index file of establishment step A carries out similarity mode, and provides matching result list to user C, and result is done entirely
Scape shows.
2. panoramic picture according to claim 1 is retrieved and methods of exhibiting, it is characterised in that described index establishment step
The specific method of the feature extraction in A and image querying step B includes：
Step1：Obtain panorama image information；
Step2：Traversal image resource, will be cut into 40*40=1600 small picture block per pictures；
Step3：To each image block, by CEDD instruments, make RGB models and turn HSV model treatments；
Step4：By 10-bins blur filters, the HSV information outputs that will be obtained to 10 dimension histograms；
Step5：10 dimension histograms and S (saturation degree), V (brightness) component in Step4 are input to 24-bins blur filters
In device, 24 dimension histograms of thumbnail are obtained；
Step6：Each small image block is made into RGB models and turns YIQ model treatments；
Step7：Again by each blockage quartering, the digital filter structure used during texture information is extracted is corresponded to, point
Each piece of gray value is not calculated and is normalized；
Step8：The texture information of each piece for obtaining is planned in 6 dimension edge histograms；
Step9：Two parts histogram that will be obtained in Step5 and Step8 is combined, and obtains one 144 dimension histogram, completes image
The extraction work of feature.
3. panoramic picture according to claim 2 is retrieved and methods of exhibiting, it is characterised in that described index establishment step
The detailed step of A is as follows：
Step1:Create document composer DocumentBuilder (CEDD.class) object, and the characteristics of image letter that will be obtained
Breath is dissolved into composer；
Step2：Using document composer, image feature information is added in the document D ocument of structure；
Step3：Index of definition document write-in object IndexWrite；
Step4：Finally, will be indexed during document D ocument writes server by configuration address by writing object.
4. panoramic picture according to claim 1 is retrieved and methods of exhibiting, it is characterised in that described image querying step
The detailed step of B is as follows：
Step1:Obtain image of the user by take pictures upload or Network Capture；
Step2：The characteristic value of input picture is extracted using extract ()；
Step3：According to the characteristic value extracted, similar picture is searched using findSimilar ()；
Step4:A newly-built ImageSearchHits is used to store the result searched；
Step5：Traversal ImageSearchHits, gets correspondence or similar panorama sketch for information about respectively, including score,
Path and name information.
5. panoramic picture according to claim 1 is retrieved and methods of exhibiting, it is characterised in that also including being given below
Krpano frameworks realize the specific steps of Panoramic Warping：
Step1：Browser loads html files, and the html files do the entrance configuration of Panoramic Warping, including set Panoramic Warping
Xml document；
Step2：The html pages load Krpano html5 panorama engines；
Step3：The main xml document of panorama engine loading correspondence panorama sketch, the xml document is configured with and is obtained by image search method
The results list for arriving, reads panorama image resource；
Step4：The panorama resource that will be read, is added in container with browser-presented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710126566.2A CN106909684A (en) | 2017-03-06 | 2017-03-06 | Panoramic picture is retrieved and methods of exhibiting |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710126566.2A CN106909684A (en) | 2017-03-06 | 2017-03-06 | Panoramic picture is retrieved and methods of exhibiting |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106909684A true CN106909684A (en) | 2017-06-30 |
Family
ID=59186659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710126566.2A Pending CN106909684A (en) | 2017-03-06 | 2017-03-06 | Panoramic picture is retrieved and methods of exhibiting |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106909684A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491521A (en) * | 2017-08-16 | 2017-12-19 | 深圳市爱思拓信息存储技术有限公司 | A kind of image search system and method |
| CN107994994A (en) * | 2017-11-24 | 2018-05-04 | 深圳中兴网信科技有限公司 | Image authentication code verification method, system, server and terminal |
| CN108009588A (en) * | 2017-12-01 | 2018-05-08 | 深圳市智能现实科技有限公司 | Localization method and device, mobile terminal |
| CN109947378A (en) * | 2017-12-20 | 2019-06-28 | 鸿合科技股份有限公司 | The method and apparatus of exhibiting pictures |
| CN111189440A (en) * | 2019-12-31 | 2020-05-22 | 中国电建集团华东勘测设计研究院有限公司 | Positioning navigation method based on comparison of spatial information model and real-time image |
| CN112347289A (en) * | 2019-08-06 | 2021-02-09 | Tcl集团股份有限公司 | Image management method and terminal |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063478A (en) * | 2010-12-22 | 2011-05-18 | 张丛喆 | Three-dimensional file format conversion method and search engine suitable for Internet search |
| US20120093395A1 (en) * | 2009-09-16 | 2012-04-19 | Olaworks, Inc. | Method and system for hierarchically matching images of buildings, and computer-readable recording medium |
| CN105160039A (en) * | 2015-10-13 | 2015-12-16 | 四川携创信息技术服务有限公司 | Query method based on big data |
-
2017
- 2017-03-06 CN CN201710126566.2A patent/CN106909684A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120093395A1 (en) * | 2009-09-16 | 2012-04-19 | Olaworks, Inc. | Method and system for hierarchically matching images of buildings, and computer-readable recording medium |
| CN102063478A (en) * | 2010-12-22 | 2011-05-18 | 张丛喆 | Three-dimensional file format conversion method and search engine suitable for Internet search |
| CN105160039A (en) * | 2015-10-13 | 2015-12-16 | 四川携创信息技术服务有限公司 | Query method based on big data |
Non-Patent Citations (2)
| Title |
|---|
| WEIXIN_33698823: "基于Krpano 的全景漫游系统的实现", pages 217 - 220, Retrieved from the Internet <URL:https://blog.csdn.net/weixin_33698823/article/details/92010290> * |
| 官倩宁等: "综合MPEG-7中纹理和颜色特征的图像检索方法", vol. 25, no. 3 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107491521A (en) * | 2017-08-16 | 2017-12-19 | 深圳市爱思拓信息存储技术有限公司 | A kind of image search system and method |
| CN107994994A (en) * | 2017-11-24 | 2018-05-04 | 深圳中兴网信科技有限公司 | Image authentication code verification method, system, server and terminal |
| CN108009588A (en) * | 2017-12-01 | 2018-05-08 | 深圳市智能现实科技有限公司 | Localization method and device, mobile terminal |
| WO2019104953A1 (en) * | 2017-12-01 | 2019-06-06 | 深圳市智能现实科技有限公司 | Positioning method and apparatus, and mobile terminal |
| CN109947378A (en) * | 2017-12-20 | 2019-06-28 | 鸿合科技股份有限公司 | The method and apparatus of exhibiting pictures |
| CN112347289A (en) * | 2019-08-06 | 2021-02-09 | Tcl集团股份有限公司 | Image management method and terminal |
| CN111189440A (en) * | 2019-12-31 | 2020-05-22 | 中国电建集团华东勘测设计研究院有限公司 | Positioning navigation method based on comparison of spatial information model and real-time image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107045730B (en) | Multi-dimensional display system and method for digital cultural scene or image | |
| CN106909684A (en) | Panoramic picture is retrieved and methods of exhibiting | |
| Liu et al. | Scenesketcher: Fine-grained image retrieval with scene sketches | |
| JP4893243B2 (en) | Image summarization method, image display device, k-tree display system, k-tree display program, and k-tree display method | |
| US20080215548A1 (en) | Information search method and system | |
| Wang et al. | Cher-ob: A tool for shared analysis and video dissemination | |
| Zeng et al. | Mobile visual search model for Dunhuang murals in the smart library | |
| Ji et al. | When location meets social multimedia: A survey on vision-based recognition and mining for geo-social multimedia analytics | |
| AU2022228142B2 (en) | Intelligent change summarization for designers | |
| Purificato et al. | Multimedia and geographic data integration for cultural heritage information retrieval | |
| TW200407736A (en) | System and method for classifying patents and displaying patent classification | |
| Doulamis et al. | 4D modelling in cultural heritage | |
| Ufer et al. | Large-scale interactive retrieval in art collections using multi-style feature aggregation | |
| US9158852B2 (en) | Geographical area correlated websites | |
| Tsai | A review of image retrieval methods for digital cultural heritage resources | |
| JP6144968B2 (en) | Information presenting apparatus, method, and program | |
| US20080015843A1 (en) | Linguistic Image Label Incorporating Decision Relevant Perceptual, Semantic, and Relationships Data | |
| Li et al. | A new algorithm for product image search based on salient edge characterization | |
| Mueller et al. | An IT system for the simultaneous management of vector and raster images | |
| Peng et al. | Viewing streaming spatially-referenced data at interactive rates | |
| Togo et al. | Similar interior coordination image retrieval with multi-view features | |
| Belarbi et al. | Indexing video by the content | |
| KR20190106107A (en) | Method for generating and servicing smart image content based on location mapping | |
| Gouveia et al. | Project Lx Conventos: Travelling through space and time in Lisbon's religious buildings | |
| Gu et al. | Personal photo organization using event annotation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170630 |