Supercharge Your Innovation With Domain-Expert AI Agents!

Offline signature authentic identification method and system based on multi-feature metric learning

A metric learning, multi-feature technology, applied in the field of digital image processing and handwriting identification, can solve the problems of poor accuracy of offline signature verification system, and achieve the effects of stable verification results, improved accuracy and small errors

Active Publication Date: 2021-02-23
HOHAI UNIV CHANGZHOU
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem of poor accuracy of the current offline signature authentication system, the present invention proposes an offline signature authentication system based on multi-feature metric learning, aiming at effective, accurate and rapid authentication of signature handwriting

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
  • Offline signature authentic identification method and system based on multi-feature metric learning
  • Offline signature authentic identification method and system based on multi-feature metric learning
  • Offline signature authentic identification method and system based on multi-feature metric learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0044] An embodiment, an offline signature verification system based on multi-feature metric learning, the system adopts a modular design method, the whole system is mainly composed of a database module, an image acquisition module, a signature preprocessing module, a signature feature extraction module and classification decision-making The module consists of five modules (such as figure 1 shown), the specific scheme is as follows:

[0045] Database module: Pre-store digital information such as the user's handwritten signature image, personal information (such as name, gender, ID number), etc., and use these information to verify the authenticity of the signature image to be authenticated in the subsequent authentication process;

[0046]Image acquisition module: use equipment to collect users' personal information and signature images, such as a 5-megapixel self-focus camera, and control the data of the sample handwriting through the software operating system to enter the s...

Embodiment 2

[0050] Embodiment 2: An off-line signature verification method based on multi-feature metric learning.

[0051] The flow chart of the counterfeiting method in the embodiment of the present invention is as follows: figure 2 Shown:

[0052] The database used in the specific embodiment includes a sample signature database and collected images of handwritten signatures as samples to be tested. In this embodiment, when the system performs signature verification, first, the signature to be tested is collected and imaged by a high-speed camera. At the same time, according to the user's personal information, 3 reserved real signature images are called from the information database module, and signature images other than the user in the database are called, and each person-time has 3 real images and 3 forged images.

[0053] Step 1: Perform preprocessing on the sample image to be detected and the called signature image respectively. The preprocessing includes processing steps such a...

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 an offline signature authentic identification method and system based on multi-feature metric learning. The system comprises a database module, an image acquisition module, a signature preprocessing module, a signature feature extraction module and a classification decision module. The image acquisition module is responsible for acquiring personal information and a signature image of a user; the signature preprocessing module is responsible for preprocessing a to-be-detected image input into the system; the signature feature extraction module is responsible for extracting dynamic features and static features of the preprocessed images, normalizing the obtained feature values, and finally obtaining an image feature array connected in sequence; and the classificationdecision module is responsible for performing Euclidean distance calculation on the to-be-measured sample, the shared layer and the separation layer by using a depth multi-feature measurement method,and taking a result as a measurement for measuring the difference between the two individuals. The off-line signature authentic identification system provided by the invention has good robustness andeffectiveness in the authentic identification process, the authentic identification result is more stable, and the error is smaller.

Description

technical field [0001] The invention relates to an off-line signature authentication method and system based on multi-feature metric learning, and belongs to the technical field of digital image processing and handwriting identification. [0002] technical background [0003] With the rapid development of information science, the popularization of computers and the advent of the network information age make people's lives more and more convenient, but the problem of information security is becoming more and more prominent. Almost every day, users' passbooks or card numbers and passwords are stolen. There will be a large number of credit card password theft incidents, which bring a lot of inconvenience and insecurity to our life, and also bring a lot of economic losses. In addition, in the fields of credit card signature, bank deposit, shopping malls, online transactions, insurance and other fields, a fast and safe personal identification system is required. As a result, trad...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06T5/00G06T7/12G06T7/45G06T7/62
CPCG06T7/45G06T7/12G06T7/62G06T2207/20032G06T2207/20064G06T2207/20132G06V30/347G06V30/36G06F18/214G06T5/70
Inventor 王遥王纯款李庆武柯静马云鹏周亚琴储露露
Owner HOHAI UNIV CHANGZHOU
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com