CN103793520A - Moving visual searching method embedded with image processing software - Google Patents
Moving visual searching method embedded with image processing software Download PDFInfo
- Publication number
- CN103793520A CN103793520A CN201410052555.0A CN201410052555A CN103793520A CN 103793520 A CN103793520 A CN 103793520A CN 201410052555 A CN201410052555 A CN 201410052555A CN 103793520 A CN103793520 A CN 103793520A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- search
- moving
- vision
- 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
- 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
Abstract
The invention discloses a moving visual searching method embedded with image processing software. A category selecting module, an image capturing or calling module, an image preprocessing module, a feature extracting module, a large-scale visual searching module, a displaying module and a cloud processing module are adopted in the method. Operation such as geometric correction, tailoring, edge extracting and target marking can be carried out on a captured or called image through image preprocessing operation. The feature extracting module can be used for carrying out feature extraction and compact visual description sub-representation on the image. The large-scale visual searching module can be used for comparing and matching the marked image with an image in a database. The cloud processing module is used for inquiring an image, processing and storing a research result and improving the inquiring predicting function and the feedback function. The moving visual searching method embedded with the image processing software can be applied to all sorts of moving visual searching systems, time cost in moving visual searching is greatly shortened, the searching efficiency and accuracy are improved, the visual retrieving performance is improved and the user experience index is improved.
Description
Technical field
The invention belongs to field of computer technology, relate to a kind of moving-vision searching method of embedded images process software.
Background technology
Although moving-vision search technique emerges, be not currently widely used, because it is faced with bottleneck and the challenge of some technology.Wherein, how improving vision retrieval performance is a problem demanding prompt solution.
Summary of the invention
The object of the invention is to overcome the defect that above-mentioned technology exists, a kind of moving-vision searching method of embedded images process software is provided, design category mark and embedded images process software in moving-vision search system, search in order to accessorial visual, shorten search time, improve efficiency and the accuracy rate of search.Its concrete technical scheme is:
A kind of moving-vision searching method of embedded images process software, embed image processing software and cloud treatment technology, comprised classification selection module, image capture or transfer module, image pretreatment operation, characteristic extracting module, extensive visual search module, display module, cloud processing module.Comprise the following steps:
(1) enter after moving-vision search system, at mobile terminal pickup image or before transferring local image, select corresponding classification for search (for example: clothes, electronic product, books and periodicals, commodity etc.);
(2) enter after corresponding classification, again by mobile terminal pickup image or transfer local image, then in the image processing software embedding, manually carry out geometry correction, cutting, and carry out that main target mark, image are cut apart, the operation such as edge extracting or key point extraction, leave out useless image detail, the outstanding interested part of user, image a after formation mark;
(3) to image a after mark, carry out feature extraction, compact visual descriptor represents, and and database in image mate, retrieve the image matching, and show corresponding application platform, be convenient to user and directly enter;
(4), based on cloud treatment technology, preserve user search vestige and corresponding correct Search Results, to improve inquiry forecast function and feedback function.That is: in the time that all any users carry out new inquiry, judge the correlativity of itself and historical rudiment, predicted query result, provides relevant feedback as the case may be, and prompting user does corresponding modify.
In addition,, by user search vestige and cloud storage, can improve inquiry forecast function and feedback function.That is: utilize cloud memory technology to preserve the vestige of each vision inquiry, in the time that all any users carry out new inquiry, judge itself and the correlativity of historical rudiment, predicted query result, provides relevant feedback as the case may be, points out user to do corresponding modify.This prediction and feedback function can be avoided unnecessary wireless bandwidth expense, promote user and experience.
Preferably, in described moving-vision search system, embedded the software for image processing.
Preferably, described image processing software can meet the image of user to mobile terminal picked-up or the image that therefrom extracts carries out the image processing operations such as cutting, geometry correction, target label, edge extracting, image are cut apart, key point extraction.
Preferably, in described moving-vision search system, added classified search process.
Preferably, described moving-vision search system can, according to user search vestige and cloud memory technology, be improved inquiry forecast function and feedback function.
Compared with prior art, beneficial effect of the present invention is: the present invention is based on image processing techniques and computer technology, design a kind of moving-vision searching method of embedded images process software, in moving-vision search system, add class indication and embedded images process software, in order to accessorial visual search, improve inquiry forecast function and feedback function simultaneously.Compared with prior art, the present invention has shortened search time greatly, has improved efficiency and the accuracy rate of search, has improved vision retrieval performance, and promotes user's experience.
Accompanying drawing explanation
Fig. 1 is the system chart of the moving-vision searching method of embedded images process software of the present invention.
Embodiment
Below in conjunction with the drawings and specific embodiments, technical scheme of the present invention is described in more detail.
With reference to Fig. 1, the invention provides a kind of moving-vision searching method of embedded images process software, comprise classification selection module, image capture or transfer module, image pretreatment operation, characteristic extracting module, extensive visual search module, display module, cloud processing module.Described classification selects module to be provided with the class indications such as electronics, clothes, footwear shoe, books and periodicals, electrical equipment.Described image capture or transfer module and can use acquisition for mobile terminal image, also can transfer local image.Described image pretreatment operation can be carried out the operations such as geometry correction, cutting, edge extracting, target label to picked-up or the image of transferring.Described characteristic extracting module can be carried out feature extraction and compact visual descriptor represents to image.Described extensive visual search module can contrast marking image, mate with the image in database.Described display module can display of search results, and provides user directly to click the function that enters corresponding system.Described cloud processing module comprises processing and the storage of query image and Search Results, can improve inquiry forecast function and feedback function.
The above; it is only preferably embodiment of the present invention; protection scope of the present invention is not limited to this; any be familiar with those skilled in the art the present invention disclose technical scope in, the simple change of the technical scheme that can obtain apparently or equivalence replace all fall within the scope of protection of the present invention.
Claims (2)
1. the moving-vision searching method of an embedded images process software, it is characterized in that, image processing software and cloud treatment technology are embedded, comprise classification selection module, image capture or transfer module, image pretreatment operation, characteristic extracting module, extensive visual search module, display module, cloud processing module, comprise the following steps:
(1) enter after moving-vision search system, at mobile terminal pickup image or before transferring local image, select corresponding classification for search;
(2) enter after corresponding classification, again by mobile terminal pickup image or transfer local image, then in the image processing software embedding, manually carry out geometry correction, cutting, and carry out that main target mark, image are cut apart, the operation such as edge extracting or key point extraction, leave out useless image detail, the outstanding interested part of user, image a after formation mark;
(3) to image a after mark, carry out feature extraction, compact visual descriptor represents, and and database in image mate, retrieve the image matching, and show corresponding application platform, be convenient to user and directly enter;
(4) based on cloud treatment technology, preserve user search vestige and corresponding correct Search Results, to improve inquiry forecast function and feedback function, in the time that all any users carry out new inquiry, judge the correlativity of itself and historical rudiment, predicted query result, provides relevant feedback as the case may be, and prompting user does corresponding modify.
2. the moving-vision searching method of embedded images process software according to claim 1, it is characterized in that, in described moving-vision search system, embed the software for image processing, described image processing software can meet the image of user to mobile terminal picked-up or the image therefrom extracting carries out cutting, geometry correction, target label, edge extracting, image is cut apart, the image processing operations that key point is extracted, in described moving-vision search system, add classified search process, described moving-vision search system can be according to user search vestige and cloud memory technology, improve inquiry forecast function and feedback function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410052555.0A CN103793520A (en) | 2014-02-14 | 2014-02-14 | Moving visual searching method embedded with image processing software |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410052555.0A CN103793520A (en) | 2014-02-14 | 2014-02-14 | Moving visual searching method embedded with image processing software |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103793520A true CN103793520A (en) | 2014-05-14 |
Family
ID=50669186
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410052555.0A Pending CN103793520A (en) | 2014-02-14 | 2014-02-14 | Moving visual searching method embedded with image processing software |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103793520A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105989628A (en) * | 2015-02-06 | 2016-10-05 | 北京网梯科技发展有限公司 | Method and system device for obtaining information through mobile terminal |
CN107392238A (en) * | 2017-07-12 | 2017-11-24 | 华中师范大学 | Outdoor knowledge of plants based on moving-vision search expands learning system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1299488A (en) * | 1998-03-16 | 2001-06-13 | Nbci新西兰有限责任合伙公司 | Improved search engine |
CN102395966A (en) * | 2009-04-14 | 2012-03-28 | 高通股份有限公司 | Systems and methods for image recognition using mobile devices |
CN102968632A (en) * | 2012-10-15 | 2013-03-13 | 北京大学 | Method for obtaining compact global characteristic descriptors of images and image searching method |
CN103106408A (en) * | 2013-01-25 | 2013-05-15 | 西安电子科技大学 | Stomach computer tomography (CT) image lymph node automatic auxiliary detecting system without supervision segmentation |
CN103235949A (en) * | 2013-04-12 | 2013-08-07 | 北京大学 | Method and device for detecting points of interest in images |
-
2014
- 2014-02-14 CN CN201410052555.0A patent/CN103793520A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1299488A (en) * | 1998-03-16 | 2001-06-13 | Nbci新西兰有限责任合伙公司 | Improved search engine |
CN102395966A (en) * | 2009-04-14 | 2012-03-28 | 高通股份有限公司 | Systems and methods for image recognition using mobile devices |
CN102968632A (en) * | 2012-10-15 | 2013-03-13 | 北京大学 | Method for obtaining compact global characteristic descriptors of images and image searching method |
CN103106408A (en) * | 2013-01-25 | 2013-05-15 | 西安电子科技大学 | Stomach computer tomography (CT) image lymph node automatic auxiliary detecting system without supervision segmentation |
CN103235949A (en) * | 2013-04-12 | 2013-08-07 | 北京大学 | Method and device for detecting points of interest in images |
Non-Patent Citations (1)
Title |
---|
段凌宇等: "《移动视觉搜索技术研究与标准化进展》", 《信息通信技术》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105989628A (en) * | 2015-02-06 | 2016-10-05 | 北京网梯科技发展有限公司 | Method and system device for obtaining information through mobile terminal |
CN107392238A (en) * | 2017-07-12 | 2017-11-24 | 华中师范大学 | Outdoor knowledge of plants based on moving-vision search expands learning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210233319A1 (en) | Context-aware tagging for augmented reality environments | |
CN102902819B (en) | A kind of Intelligent video analysis method and device | |
US20150055879A1 (en) | Method, Server and System for Setting Background Image | |
CN102411582B (en) | Image searching method, device and client | |
CN105184238A (en) | Human face recognition method and system | |
US20100135527A1 (en) | Image recognition algorithm, method of identifying a target image using same, and method of selecting data for transmission to a portable electronic device | |
CN103995889A (en) | Method and device for classifying pictures | |
CN104765891A (en) | Searching shopping method based on pictures | |
CN105824928A (en) | Mobile terminal, server, content-based image recognition searching method and system | |
WO2014032419A1 (en) | Method and system for obtaining consultation information based on picture | |
CN107590154B (en) | Object similarity determination method and device based on image recognition | |
CN102682134A (en) | Intelligent bookshelf based on radio frequency identification technology and working method thereof | |
CN104392007A (en) | Streetscape retrieval and identification method of intelligent mobile terminal | |
US11429923B2 (en) | Method and device for determining mail path information | |
JP2017004252A (en) | Image information processing system | |
CN103428537A (en) | Video processing method and video processing device | |
CN104951553B (en) | A kind of accurate content of data processing is collected and data mining platform and its implementation | |
CN106326454A (en) | Image identification method | |
CN104520848A (en) | Searching for events by attendants | |
CN109299307B (en) | Trademark retrieval early warning method and device based on structural analysis | |
CN106610983A (en) | Picture management method and apparatus, and terminal | |
CN104765877A (en) | Photo processing method and system | |
CN102508901A (en) | Content-based massive image search method and content-based massive image search system | |
CN111709303A (en) | Face image recognition method and device | |
CN103530377A (en) | Scene information searching method based on binary feature codes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140514 |