CN111639724A - Article identification method based on machine vision - Google Patents
Article identification method based on machine vision Download PDFInfo
- Publication number
- CN111639724A CN111639724A CN202010276885.3A CN202010276885A CN111639724A CN 111639724 A CN111639724 A CN 111639724A CN 202010276885 A CN202010276885 A CN 202010276885A CN 111639724 A CN111639724 A CN 111639724A
- Authority
- CN
- China
- Prior art keywords
- article
- machine vision
- label
- identification method
- feature code
- 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; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
- G06V20/63—Scene text, e.g. street names
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an article identification method based on machine vision, which relates to the technical field of article labels. The feature code is generated based on the natural features of the original label of the article, has uniqueness and can uniquely identify the article. The article identification method based on machine vision not only can realize identification of different articles, but also has stronger anti-counterfeiting performance because the characteristic data of the natural form of the existing label is used and is coded according to a certain rule.
Description
Technical Field
The invention relates to the technical field of article labels, in particular to an article identification method based on machine vision.
Background
On many articles, the tags are specific. For example, the production date printed on an article may vary depending on the shape, relative position, color shade, etc. of the characters on the article, even on different articles of the same type, due to factors such as the label printing accuracy and the label pasting accuracy. This patent uses machine vision techniques to achieve some clarity to identify these difference features. The difference characteristic data are coded according to a certain rule, and then the coded data are added to the object label to form a new object label, so that the identification of different objects is realized, and the anti-counterfeiting function is realized. However, the existing article identification method is more traditional, and the coding method is very simple and traditional, so that the anti-counterfeiting capability is not strong.
Disclosure of Invention
The invention aims to solve the problem of providing an article identification method based on machine vision, which not only can realize identification of different articles, but also has stronger anti-counterfeiting performance because the characteristic data of the natural form of the existing label is used and is coded according to a certain rule.
In order to achieve the purpose, the invention adopts the technical scheme that:
the article identification method based on the machine vision comprises the following steps:
(1) performing machine vision analysis on article labels (such as the outgoing date of spray painting) to generate a data feature set according to the characters of the labels, such as font shapes, relative positions, color shades and the like;
(2) coding the data feature set of the object according to a certain rule (such as SHA-1 algorithm and the like) to generate a unique feature code of the article;
(3) adding the feature code to the article label to form a new article label;
(4) the item information (data feature set, feature code, etc.) is stored in a database.
The article identification method based on machine vision further comprises the following steps of tag verification:
(1) performing machine vision analysis on the label without the feature code part of the article to generate a data feature set;
(2) then, coding the data feature set of the object according to a rule when the feature code is generated to obtain the object feature code;
(3) and comparing whether the generated characteristic code is consistent with the characteristic code on the label of the article, if so, checking to pass, and if not, checking not to pass.
The article identification method based on the machine vision also comprises the query of article information, when the query of the article information is implemented, the article can be uniquely identified directly through a feature code part in an article label, and the article information is queried through matching records in a database through the feature code.
Has the advantages that: the article label containing the feature code generated by the article identification method based on machine vision can be used for verifying the article label, and has strong anti-counterfeiting property. The feature code is generated based on the natural features of the original label of the article, has uniqueness and can uniquely identify the article. The article identification method based on the machine vision is based on a machine vision technology, a characteristic data set is generated according to natural characteristics (such as font shape, relative position, color shade and the like of production date sprayed on an article) of an article label, the characteristic data set of the article is coded according to a certain rule to form a characteristic code, and the article can be uniquely identified according to the characteristic code and has certain anti-counterfeiting capacity. The article identification method based on machine vision not only can realize identification of different articles, but also has stronger anti-counterfeiting performance because the characteristic data of the natural form of the existing label is used and is coded according to a certain rule.
Detailed Description
Example 1:
the article identification method based on the machine vision comprises the following steps:
(1) performing machine vision analysis on the article label, and generating a data feature set according to the characters of the label, such as font shape, relative position, color shade and the like;
(2) coding the data feature set of the object according to a Hash algorithm to generate a unique feature code of the article;
(3) adding the feature code to the article label to form a new article label;
(4) the item information is stored in a database.
The article identification method based on machine vision further comprises the following steps of tag verification:
(1) performing machine vision analysis on the label without the feature code part of the article to generate a data feature set;
(2) then, coding the data feature set of the object according to a rule when the feature code is generated to obtain the object feature code;
(3) and comparing whether the generated characteristic code is consistent with the characteristic code on the label of the article, if so, checking to pass, and if not, checking not to pass.
The article identification method based on the machine vision also comprises the query of article information, when the query of the article information is implemented, the article can be uniquely identified directly through a feature code part in an article label, and the article information is queried through matching records in a database through the feature code.
Example 2:
the article identification method based on the machine vision comprises the following steps:
(1) performing machine vision analysis on the article label, and generating a data feature set according to the characters of the label, such as font shape, relative position, color shade and the like;
(2) coding the data feature set of the object according to an SHA-1 algorithm to generate a unique feature code of the article;
(3) adding the feature code to the article label to form a new article label;
(4) the item information is stored in a database.
The article identification method based on machine vision further comprises the following steps of tag verification:
(1) performing machine vision analysis on the label without the feature code part of the article to generate a data feature set;
(2) then, coding the data feature set of the object according to a rule when the feature code is generated to obtain the object feature code;
(3) and comparing whether the generated characteristic code is consistent with the characteristic code on the label of the article, if so, checking to pass, and if not, checking not to pass.
The article identification method based on the machine vision also comprises the query of article information, when the query of the article information is implemented, the article can be uniquely identified directly through a feature code part in an article label, and the article information is queried through matching records in a database through the feature code.
Example 3:
the article identification method based on the machine vision comprises the following steps:
(1) performing machine vision analysis on the article label, and generating a data feature set according to the characters of the label, such as font shape, relative position, color shade and the like;
(2) coding the data feature set of the object according to a DES algorithm to generate a unique feature code of the article;
(3) adding the feature code to the article label to form a new article label;
(4) the item information is stored in a database.
The article identification method based on machine vision further comprises the following steps of tag verification:
(1) performing machine vision analysis on the label without the feature code part of the article to generate a data feature set;
(2) then, coding the data feature set of the object according to a rule when the feature code is generated to obtain the object feature code;
(3) and comparing whether the generated characteristic code is consistent with the characteristic code on the label of the article, if so, checking to pass, and if not, checking not to pass.
The article identification method based on the machine vision also comprises the query of article information, when the query of the article information is implemented, the article can be uniquely identified directly through a feature code part in an article label, and the article information is queried through matching records in a database through the feature code.
The above description is only an example of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and embodiments, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (3)
1. An article identification method based on machine vision is characterized by comprising the following steps:
(1) performing machine vision analysis on article labels (such as the outgoing date of spray painting) to generate a data feature set according to the characters of the labels, such as font shapes, relative positions, color shades and the like;
(2) coding the data feature set of the object according to a certain rule (such as SHA-1 algorithm and the like) to generate a unique feature code of the article;
(3) adding the feature code to the article label to form a new article label;
(4) the item information (data feature set, feature code, etc.) is stored in a database.
2. A machine vision based item identification method as claimed in claim 1, wherein: the article identification method based on machine vision further comprises the following steps of tag verification:
(1) performing machine vision analysis on the label without the feature code part of the article to generate a data feature set;
(2) then, coding the data feature set of the object according to a rule when the feature code is generated to obtain the object feature code;
(3) and comparing whether the generated characteristic code is consistent with the characteristic code on the label of the article, if so, checking to pass, and if not, checking not to pass.
3. A machine vision based item identification method as claimed in claim 1, wherein: the article identification method based on the machine vision also comprises the query of article information, when the query of the article information is implemented, the article can be directly and uniquely identified through a feature code part in an article label, and the article information is queried through matching records in a database through the feature code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010276885.3A CN111639724A (en) | 2020-04-07 | 2020-04-07 | Article identification method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010276885.3A CN111639724A (en) | 2020-04-07 | 2020-04-07 | Article identification method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111639724A true CN111639724A (en) | 2020-09-08 |
Family
ID=72331208
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010276885.3A Pending CN111639724A (en) | 2020-04-07 | 2020-04-07 | Article identification method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639724A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004986A (en) * | 2010-10-26 | 2011-04-06 | 梁庆生 | Product anti-counterfeiting method based on digital signature and public key system and verifying method |
| US20120234908A1 (en) * | 2011-03-18 | 2012-09-20 | Name Technology, Inc. | Systems and methods for anti-counterfeit authentication through communication networks |
| CN108154208A (en) * | 2016-12-06 | 2018-06-12 | 上海众人信息技术有限公司 | A kind of article mark method, recognition methods and system based on Quick Response Code |
| CN109636417A (en) * | 2018-12-04 | 2019-04-16 | 雷华 | A kind of method for anti-counterfeit and device |
-
2020
- 2020-04-07 CN CN202010276885.3A patent/CN111639724A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102004986A (en) * | 2010-10-26 | 2011-04-06 | 梁庆生 | Product anti-counterfeiting method based on digital signature and public key system and verifying method |
| US20120234908A1 (en) * | 2011-03-18 | 2012-09-20 | Name Technology, Inc. | Systems and methods for anti-counterfeit authentication through communication networks |
| CN108154208A (en) * | 2016-12-06 | 2018-06-12 | 上海众人信息技术有限公司 | A kind of article mark method, recognition methods and system based on Quick Response Code |
| CN109636417A (en) * | 2018-12-04 | 2019-04-16 | 雷华 | A kind of method for anti-counterfeit and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106022805B (en) | A kind of anti-fake traceability system and method based on tag readable degree | |
| CN202916873U (en) | Multifunctional product anti-counterfeit identification system | |
| CN102663592A (en) | Two-dimensional code-based object identity dual-code identification method | |
| CN103455574B (en) | The method and apparatus of Internet of Things unifying identifier coding multimode recognition | |
| CN102708391B (en) | A kind of antifalsification label based on fractal graph and anti-counterfeit authentication method | |
| CN113469714A (en) | Product anti-counterfeiting tracing method based on industrial internet identification analysis system | |
| CN101515352A (en) | Article anti-counterfeiting system combining radio frequency identification and two-dimension code | |
| CN101795783A (en) | Method of processing postal packages with client codes associated with digital imprints | |
| CN202512813U (en) | Character anti-fake and bar code combination marking structure | |
| CN101957905A (en) | Checking technology and security label | |
| CN109993129B (en) | Fingerprint identification method based on fingerprint thin node cylindrical code | |
| CN1866320A (en) | Anti-counterfeit packaging method and apparatus | |
| CN103247229A (en) | Manufacture method of multiple anti-counterfeit labels | |
| CN111882327A (en) | Anti-counterfeiting tracing method with identity characteristics and capable of actively feeding back information to system | |
| CN108229627A (en) | Agricultural product quality and safety whole process is traced to the source space-time hybrid coding and coding method | |
| CN201457950U (en) | Cluster RFID electronic tag | |
| CN101667247A (en) | Method for anti-counterfeiting metal parts | |
| CN111639724A (en) | Article identification method based on machine vision | |
| CN103996059A (en) | Informatization system and method for article tags | |
| CN1564166A (en) | Muli-graded anti-fraud recognition method for wine products | |
| CN108009616B (en) | Novel bar graph code with anti-counterfeiting function and application method | |
| CN104555008B (en) | Bottle cap and bottle information association Packaging Bottle and preparation method thereof | |
| CN109472150A (en) | A kind of setting read method of the file information | |
| CN104636932A (en) | Method for manufacturing anti-counterfeiting label with uniqueness and unduplicatedness and anti-counterfeiting system | |
| CN1815485A (en) | Intelligent identification card/card management number and serial number setting and using method |
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 |