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

Identity card copy detection method based on Faster-RCNN (Regions with Convolutional Neural Network Feature)

A detection method and copy technology, applied in the field of pattern recognition, can solve the problems of waste of human resources, low efficiency, poor generalization ability, etc.

Inactive Publication Date: 2018-07-27
FUZHOU UNIV
View PDF10 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional ID card copy detection software based on machine learning can no longer meet the requirements. Government enterprises and institutions need a software that can quickly and accurately detect ID card copies to improve office efficiency and accuracy
[0003] Traditional ID card copy detection software uses classical machine learning methods for detection, which has low accuracy and poor generalization ability, while manual ID card copy detection is not only inefficient, but also wastes human resources

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
  • Identity card copy detection method based on Faster-RCNN (Regions with Convolutional Neural Network Feature)
  • Identity card copy detection method based on Faster-RCNN (Regions with Convolutional Neural Network Feature)
  • Identity card copy detection method based on Faster-RCNN (Regions with Convolutional Neural Network Feature)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0066] Such as figure 1 As shown, a Faster-RCNN-based ID card copy detection method includes the following steps:

[0067] Step S1: making a data set of the Faster-RCNN model;

[0068] The step S1 specifically includes:

[0069] Step S11: Select several ID card copy images as data set samples;

[0070] Step S12: Scale the data set samples to a uniform size, adopt the nearest neighbor interpolation method, and use the following formula:

[0071] dst y = dst w / src w *src y dst x = dst h / src h *src x f(dst x ,dst y ) = f(src x ,src y )

[0072] Among them, dst x Indicates the abscissa of the zoomed image, dst y Represents the ordinate of the image after zooming, dst w Indicates the width of the zoomed image, dst h Indicates the height of the scaled image, src x Represents the abscissa of the original image, src y Represents the or...

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 identity card copy detection method based on Faster-RCNN (Regions with Convolutional Neural Network Feature). The method comprises the following steps that: selecting a plurality of identity card copy images, manufacturing the dataset of a Faster-RCNN model, setting the parameter of the Faster-RCNN model, preprocessing an identity card copy test image, training the Faster-RCNN model on the basis of the dataset, inputting the test image, and utilizing the trained Faster-RCNN model for detection. By use of the method disclosed by the invention, a good detection resultalso can be obtained for the identity card copy with a blurry image, numerous angles and an unclear border, and the method has the advantages of high practicability, good detection effect and good development prospect.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method for detecting a copy of an ID card based on Faster-RCNN. Background technique [0002] With the development of the social real-name system, a copy of the ID card has become an effective proof of resident status. Many businesses in various financial industries require copies of ID cards, and correct copying of ID cards is a prerequisite for good office work. The development of economic science and the intensification of market competition have led to a sharp increase in the business of the financial industry, and a large number of ID card copies have to be tested every day. Traditional ID card copy detection software based on machine learning can no longer meet the requirements. Government enterprises and institutions need a software that can quickly and accurately detect ID card copies to improve office efficiency and accuracy. [0003] Traditional ID card ...

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): G06N99/00G06N3/04G06K9/62
CPCG06N20/00G06N3/045G06F18/214
Inventor 柯逍卢安琪牛玉贞
Owner FUZHOU UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com