Anti-counterfeiting bill authentic identification system and method based on multispectral images

A multi-spectral image and bill technology, applied in the field of anti-counterfeiting bill authentication system, can solve the problems of increasing identification difficulty, incomplete identification of face information, slow matching speed, etc., and achieves improved accuracy and reliability, good grayscale invariance, To achieve the effect of accurate matching

Active Publication Date: 2019-12-20
HUAZHONG UNIV OF SCI & TECH
View PDF5 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009](1) The existing technology utilizes a single type of anti-counterfeiting features, resulting in poor accuracy and reliability of counterfeiting
[0010](2) The existing technology uses the global information of anti-counterfeiting features, but does not use its detailed information when matching, resulting in slow matching speed and poor real-time online detection
[0011](3) The existing technology does not fully recogniz

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
  • Anti-counterfeiting bill authentic identification system and method based on multispectral images
  • Anti-counterfeiting bill authentic identification system and method based on multispectral images
  • Anti-counterfeiting bill authentic identification system and method based on multispectral images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0080] In the prior art, the way of multi-modal and multi-feature fusion is not used for bill verification, resulting in poor accuracy and reliability of verification. The prior art does not use the SURF feature point matching method and cannot capture the detailed information of the anti-counterfeiting mark, resulting in slow matching speed and failing to meet the real-time requirements of online detection. The prior art does not perform effective identification of face information and has poor accuracy. The prior art does not establish a bill database, which is inconvenient for unified management of anti-counterfeit bill...

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 belongs to the technical field of financial security authentic identification and identification, and discloses an anti-counterfeiting bill authentic identification system and method based on multispectral image. The method comprises the steps: carrying out the image collection of an anti-counterfeiting bill through an image collection module, and obtaining anti-counterfeiting bill images under different spectrums; preprocessing the acquired bill images, wherein preprocessing includes color compensation, geometric correction, filtering and noise reduction; extracting anti-counterfeiting features from the infrared and ultraviolet images, and fusing multiple features to judge the authenticity of the anti-counterfeiting bill; and detecting a text area on the white light image, and recognizing bill face text information, wherein the bill face text information comprises bill types, affiliated organizations, bill numbers, accounts and money amounts. According to the invention,bill authentic identification is carried out by using a multi-mode multi-feature fusion mode, so that the authentic identification accuracy and reliability are improved; and the detail information ofthe anti-counterfeiting mark can be captured, and accurate matching of the feature points is achieved. Moreover, the matching speed is high, and the requirement of real-time performance of online detection can be met.

Description

technical field [0001] The invention belongs to the technical field of counterfeit identification and identification for public security, and in particular relates to a multi-spectral image-based anti-counterfeit bill identification system and method. Background technique [0002] Currently, the closest prior art: [0003] Anti-counterfeiting bills refer to various securities and certificates with anti-counterfeiting marks or features, including checks, bills of exchange, certificates of deposit, stocks, corporate bonds, invoices, tickets, etc. Anti-counterfeit bills are one of the important certificates in the circulation process of the national financial market, and undertake the capital circulation business among social entities such as individuals, enterprises, and banks. With the rapid development of our country's economy, all kinds of bill business have also developed rapidly. What followed was an increase in illegal cases caused by counterfeiting bills, which seriou...

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): G06K9/32G06K9/34G06K9/68G07D7/20
CPCG07D7/2016G07D7/2008G06V20/62G06V30/153G06V30/2455G06V30/287
Inventor 尤新革彭勤牧夏北浩沈钊
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products