[go: up one dir, main page]

CN110442739A - A kind of search technique based on picture recognition - Google Patents

A kind of search technique based on picture recognition Download PDF

Info

Publication number
CN110442739A
CN110442739A CN201910599492.3A CN201910599492A CN110442739A CN 110442739 A CN110442739 A CN 110442739A CN 201910599492 A CN201910599492 A CN 201910599492A CN 110442739 A CN110442739 A CN 110442739A
Authority
CN
China
Prior art keywords
picture recognition
picture
recognition system
user
search technique
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
Application number
CN201910599492.3A
Other languages
Chinese (zh)
Inventor
谢玉辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Search Material Information Technology Co Ltd
Original Assignee
Guangzhou Search Material Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Search Material Information Technology Co Ltd filed Critical Guangzhou Search Material Information Technology Co Ltd
Priority to CN201910599492.3A priority Critical patent/CN110442739A/en
Publication of CN110442739A publication Critical patent/CN110442739A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/53Querying
    • G06F16/538Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/55Clustering; Classification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Image Analysis (AREA)

Abstract

A kind of search technique based on picture recognition, comprising the following steps: S1: the pictorial information that user's upload needs to identify to picture recognition system;S2: user inputs known product information to picture recognition system;S3: picture recognition system calling searches material net and is based on picture recognition analysis system technology, scans the corresponding image data of name of product and data of picture classification in the database or scanning user's input;S4: picture recognition system returns to corresponding search data result collection.In the present invention, the picture and product information that picture recognition system is uploaded according to user identify picture, and corresponding search data result collection is returned, consult convenient for user;Picture recognition system queries speed is fast, and inquiry accuracy is high.

Description

A kind of search technique based on picture recognition
Technical field
The present invention relates to picture recognition analysis technical field more particularly to a kind of search techniques based on picture recognition.
Background technique
In Plastics Industry chain, the name of product of most of semi-finished product can not describe or without Uniform Name, can not use text Word accurate description, brings problems, such as the relevant product information that major search engine can not all be found the drawbacks of.I.e. It is that title and picture are issued to client, title cannot be unified, and it is even more impossible to find corresponding production case, data and trade mark certificate Etc. relevant informations.The big data advantage that material net combines itself is searched, by product picture or semi-finished product picture, product information, production case Example, production trade mark information carry out unified standard arrangement, intuitively look for stream journey as user's offer is convenient, provide for industrial chain Quickly look for the solution of material.
Summary of the invention
(1) goal of the invention
To solve technical problem present in background technique, the present invention proposes a kind of search technique based on picture recognition.
(2) technical solution
To solve the above problems, the present invention provides a kind of search techniques based on picture recognition, comprising the following steps:
S1: the pictorial information that user's upload needs to identify to picture recognition system;
S2: user inputs known product information to picture recognition system;
S3: picture recognition system calling searches material net and is based on picture recognition analysis system technology, scans the picture in the database The corresponding image data of name of product and data of classification or scanning user's input;
S4: picture recognition system returns to corresponding search data result collection.
Preferably, picture recognition system establishes data model according to a large amount of pictures.
Preferably, intelligence learning model algorithm is arranged in picture recognition internal system, for instructing to picture recognition system Practice.
Preferably, double of finished product picture of picture recognition system is marked and stores.
Preferably, after picture is identified every time, picture recognition system marks the picture again.
In the present invention, the picture and product information that picture recognition system is uploaded according to user identify picture, and will Corresponding search data result collection is returned, and is consulted convenient for user;Picture recognition system queries speed is fast, inquires accuracy It is high.
In the present invention, double of finished product picture of picture recognition system is marked and stores, and corresponding trade mark information, corresponding Case information.The picture that picture recognition system uploads user identifies;After picture recognition success, system can be directed to the picture Label study again is carried out, is not necessarily to scan mass file after identifying similar pictures in order to other users, standard can be matched to True corresponding data information is shown.The function can be used to find corresponding product picture for user, can also be looked for picture To corresponding title, the recognition efficiency of picture recognition system is improved.
Detailed description of the invention
Fig. 1 is the method and step flow chart of the search technique proposed by the present invention based on picture recognition.
Specific embodiment
In order to make the objectives, technical solutions and advantages of the present invention clearer, With reference to embodiment and join According to attached drawing, the present invention is described in more detail.It should be understood that these descriptions are merely illustrative, and it is not intended to limit this hair Bright range.In addition, in the following description, descriptions of well-known structures and technologies are omitted, to avoid this is unnecessarily obscured The concept of invention.
As shown in Figure 1, a kind of search technique based on picture recognition proposed by the present invention, comprising the following steps:
S1: the pictorial information that user's upload needs to identify to picture recognition system;
S2: user inputs known product information to picture recognition system;
S3: picture recognition system calling searches material net and is based on picture recognition analysis system technology, scans the picture in the database The corresponding image data of name of product and data of classification or scanning user's input;
S4: picture recognition system returns to corresponding search data result collection.
In an alternative embodiment, double of finished product picture of picture recognition system is marked and stores.
In an alternative embodiment, after picture is identified every time, picture recognition system carries out deutero-albumose again to the picture Note.
In the present invention, the picture and product information that picture recognition system is uploaded according to user identify picture, and will Corresponding search data result collection is returned, and is consulted convenient for user;Picture recognition system queries speed is fast, inquires accuracy It is high.
In the present invention, double of finished product picture of picture recognition system is marked and stores, and corresponding trade mark information, corresponding Case information.The picture that picture recognition system uploads user identifies;After picture recognition success, system can be directed to the picture Label study again is carried out, is not necessarily to scan mass file after identifying similar pictures in order to other users, standard can be matched to True corresponding data information is shown.The function can be used to find corresponding product picture for user, can also be looked for picture To corresponding title, the recognition efficiency of picture recognition system is improved.
In an alternative embodiment, picture recognition system establishes data model according to a large amount of pictures.
In an alternative embodiment, intelligence learning model algorithm is arranged in picture recognition internal system, for picture Identifying system is trained, optimization system algorithm, improves the recognition efficiency of picture recognition system.
It should be understood that above-mentioned specific embodiment of the invention is used only for exemplary illustration or explains of the invention Principle, but not to limit the present invention.Therefore, that is done without departing from the spirit and scope of the present invention is any Modification, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.In addition, appended claims purport of the present invention Covering the whole variations fallen into attached claim scope and boundary or this range and the equivalent form on boundary and is repairing Change example.

Claims (5)

1. a kind of search technique based on picture recognition, which comprises the following steps:
S1: the pictorial information that user's upload needs to identify to picture recognition system;
S2: user inputs known product information to picture recognition system;
S3: picture recognition system calling searches material net and is based on picture recognition analysis system technology, scans the picture in the database The corresponding image data of name of product and data of classification or scanning user's input;
S4: picture recognition system returns to corresponding search data result collection.
2. the search technique according to claim 1 based on picture recognition, which is characterized in that picture recognition system is according to big Spirogram piece establishes data model.
3. the search technique according to claim 2 based on picture recognition, which is characterized in that picture recognition internal system is set Intelligence learning model algorithm is set, for being trained to picture recognition system.
4. the search technique according to claim 1 based on picture recognition, which is characterized in that picture recognition system half-and-half at Product picture is marked and stores.
5. the search technique according to claim 1 based on picture recognition, which is characterized in that after picture is identified every time, Picture recognition system marks the picture again.
CN201910599492.3A 2019-07-04 2019-07-04 A kind of search technique based on picture recognition Pending CN110442739A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910599492.3A CN110442739A (en) 2019-07-04 2019-07-04 A kind of search technique based on picture recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910599492.3A CN110442739A (en) 2019-07-04 2019-07-04 A kind of search technique based on picture recognition

Publications (1)

Publication Number Publication Date
CN110442739A true CN110442739A (en) 2019-11-12

Family

ID=68429082

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910599492.3A Pending CN110442739A (en) 2019-07-04 2019-07-04 A kind of search technique based on picture recognition

Country Status (1)

Country Link
CN (1) CN110442739A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102768683A (en) * 2012-06-29 2012-11-07 北京奇虎科技有限公司 A search method and search device for picture information
CN104239445A (en) * 2014-09-01 2014-12-24 百度在线网络技术(北京)有限公司 Method and device for representing search results
CN105138618A (en) * 2015-08-11 2015-12-09 百度在线网络技术(北京)有限公司 Method and apparatus for performing secondary search in combination with speech in image search
CN105808671A (en) * 2016-03-01 2016-07-27 王博 Product information acquisition method and terminal
CN109299391A (en) * 2018-11-19 2019-02-01 广州搜料信息技术有限公司 Intelligent search method and device based on synonym semantics recognition
CN109635178A (en) * 2018-11-19 2019-04-16 广州搜料信息技术有限公司 Intelligent search method based on product information semantics recognition

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102768683A (en) * 2012-06-29 2012-11-07 北京奇虎科技有限公司 A search method and search device for picture information
CN104239445A (en) * 2014-09-01 2014-12-24 百度在线网络技术(北京)有限公司 Method and device for representing search results
CN105138618A (en) * 2015-08-11 2015-12-09 百度在线网络技术(北京)有限公司 Method and apparatus for performing secondary search in combination with speech in image search
CN105808671A (en) * 2016-03-01 2016-07-27 王博 Product information acquisition method and terminal
CN109299391A (en) * 2018-11-19 2019-02-01 广州搜料信息技术有限公司 Intelligent search method and device based on synonym semantics recognition
CN109635178A (en) * 2018-11-19 2019-04-16 广州搜料信息技术有限公司 Intelligent search method based on product information semantics recognition

Similar Documents

Publication Publication Date Title
CN101292259B (en) Method and system for image matching in a mixed media environment
CN110020185A (en) Intelligent search method, terminal and server
US9652534B1 (en) Video-based search engine
CN107408212A (en) System and method for identifying the unwanted photo being stored in equipment
CN108959586A (en) Text vocabulary is identified in response to visual query
CN105550190A (en) Knowledge graph-oriented cross-media retrieval system
CN101211370A (en) Content register device, content register method and content register program
US11768871B2 (en) Systems and methods for contextualizing computer vision generated tags using natural language processing
CN105894362A (en) Method and device for recommending related item in video
Nguyen et al. Enhanced vireo kis at vbs 2018
US20170308525A1 (en) Citation explanations
Truong et al. Video search based on semantic extraction and locally regional object proposal
KR101650888B1 (en) Content collection and recommendation system and method
CN114090777A (en) Text data processing method and device
Leibetseder et al. Sketch-based similarity search for collaborative feature maps
CN111949639A (en) Brand library creating method and system and brand query and analysis platform
Abu-Qdais et al. Intelligent system for solid waste classification using combination of image processing and machine learning models
CN110442739A (en) A kind of search technique based on picture recognition
RU2011138862A (en) METHOD FOR INDEXING AND SEARCHING DIGITAL IMAGES
US20130054553A1 (en) Method and apparatus for automatically extracting information of products
Bolettieri et al. An image retrieval system for video
CN110706699A (en) Method and system for realizing interaction task by adopting voice recognition mode
CN110427511A (en) It is a kind of that material method is looked for based on taking pictures for artificial intelligence picture recognition technology
CN110020078A (en) A kind of method and relevant apparatus for generating relevance map dictionary and its verifying correlation
KR101896177B1 (en) An Image Searching System Providing Multiplex Result

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20191112