Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Machine learning technology-based intelligent seal impression recognition and anti-fake method

A machine learning, identification and anti-counterfeiting technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of counterfeit seals, counterfeit certificates flooding, difficulty, etc., achieve high confidence, improve accuracy, and effectively judge Effect

Active Publication Date: 2018-09-07
GUANGXI NEW CHAPTER ELECTROSPRAY SEAL ANTI FORGERY TECH DEV CO LTD
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The above-mentioned anti-counterfeiting technology itself has defects and cannot fundamentally solve the problem of counterfeit seals
On the one hand, the current methods of identifying printed texts in my country still mainly rely on empirical judgments. Due to the differences in the sealing conditions of the seal, including the complexity of the background of the document, the force of the seal, the amount and quality of the ink pad, etc., it will have a great impact on the seal image. In this case, it is not only difficult to manually compare the extracted stamped text with the original stamped text, but also the accuracy rate Low and extremely inconvenient, it is not conducive to the real-time identification of seals by the public. On the other hand, the development and application of high-simulation technology provides convenience for engraving counterfeit seals. Seriously disrupted the normal economic and social order

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Machine learning technology-based intelligent seal impression recognition and anti-fake method
  • Machine learning technology-based intelligent seal impression recognition and anti-fake method
  • Machine learning technology-based intelligent seal impression recognition and anti-fake method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] An anti-counterfeiting method for intelligent identification of stamps and imprints based on machine learning technology, comprising the following steps:

[0057] Step 1, the intelligent anti-counterfeiting database of the printed text obtains the data collected when the original seal printed data and affix the seal; the intelligent anti-counterfeited database of the printed text is connected to the public security management information system of the public security bureau's seal; the described original sealed printed data includes Stamp die and the irregular dot matrix that is automatically generated by the feature dot matrix generation algorithm; The data collected when stamping includes the characteristic data of the printed text content view and the background content view;

[0058] Step 2: Collect images of a limited area of ​​the printed text to be detected, preprocess the collected image to obtain a naked printed text, and save the naked printed text image inform...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a machine learning technology-based intelligent seal impression recognition and anti-fake method. The method comprises the following steps of: obtaining original seal impression data and data acquired during sealing by an intelligent impression anti-fake database; carrying out image acquisition on a to-be-detected impression in a limited area and carrying out preprocessingto obtain a naked impression; carrying out matching verification on naked impression data comprising seal specification information and the original seal impression data to obtain a weight value of the seal specification information; carrying out matching verification on feature data of a to-be-detected impression content view and the data acquired during the sealing so as to obtain a weight valueof the impression content view; carrying out matching verification on feature data of a to-be-detected background content view and the data acquired during the sealing so as to obtain a weight valueof the background content view; and carrying out weight add operation on the obtained weight value of the seal specification information, weight value of the impression content view and weight value of the background content view, and judging whether the impression is true or not through a total weight value so as to achieve the aim of rapidly verifying whether the seal is true or not.

Description

technical field [0001] The invention relates to the technical field of anti-counterfeiting identification of seals, in particular to an anti-counterfeiting method for intelligent identification of seal texts based on machine learning technology. Background technique [0002] In our country, the seal is an important certificate to prove the identity of party and government agencies, enterprises, social organizations and other organizations, and to represent their rights and legal effects. Seals play an extremely important role in social, political and economic life. [0003] With the development of modern science and technology, especially the development of computer technology and laser engraving technology, while the technology and quality of seal making have been continuously improved, the technology of counterfeiting seals has also been continuously improved. The crime of counterfeiting seals has become the same as that of guns and drugs. Crime has also become a major pu...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/56G06F18/22G06F18/213Y02P90/30
Inventor 陈明斌桂乐汉
Owner GUANGXI NEW CHAPTER ELECTROSPRAY SEAL ANTI FORGERY TECH DEV CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products