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

Training method and detection method for automatically identifying copied images of original document

A training method and automatic recognition technology, applied in image enhancement, image analysis, image data processing, etc.

Active Publication Date: 2020-01-21
SHENZHEN UNIV
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, there is no training method and remake detection for the original document in the prior art

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
  • Training method and detection method for automatically identifying copied images of original document
  • Training method and detection method for automatically identifying copied images of original document
  • Training method and detection method for automatically identifying copied images of original document

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the drawings. In the following description, the same reference numerals are given to the same components, and repeated descriptions are omitted. In addition, the drawings are only schematic diagrams.

[0033] It should be noted that the terms "first", "second", "third" and "fourth" in the specification and claims of the present disclosure and the above drawings are used to distinguish different objects, rather than using to describe a specific order. Furthermore, the terms "include" and "have", as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally further includes For other steps or units inherent in these processes, methods, p...

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 training method for automatically identifying copied images of an original document. The method comprises: constructing an image database composed of a plurality of images from an original document, the image database comprising a training data subset, and the training data subset being provided with training images comprising initial images and duplicated images and annotation results associated with the training images; obtaining an initial convolutional neural network, wherein the initial convolutional neural network is a convolutional neural network obtained by training an existing image data set; and performing fine tuning training on the initial convolutional neural network by using the training data subset, thereby obtaining a target convolutional neural network capable of outputting a classification result of the training image of the original document. According to the invention, copy detection can be easily carried out on the original document.

Description

technical field [0001] The present disclosure generally relates to a training method and detection method for automatically identifying remake images of original documents. Background technique [0002] Current remake detection can include natural image detection and face fraud detection. Wherein, for face fraud detection, it may refer to detecting forged faces, and the way of forgery may be to print the faces on paper or display them on a monitor, and recapture them for the detection camera. For example, detectors are developed based on several physical features associated with recaptured natural images, including exploiting the non-linear properties of tone response curves, the spatial distribution of specularity in images, image contrast, color, hue, and sharpness, among others. In addition, face fraud can also be detected based on the LBPV features obtained by extending the LBP features. [0003] For the detection of natural image features, the fine texture pattern cha...

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): G06K9/00G06K9/62G06T7/11G06N3/04G06N3/08
CPCG06T7/11G06N3/08G06T2207/20021G06T2207/30176G06T2207/10004G06T2207/20081G06T2207/20084G06V30/40G06N3/045G06F18/241
Inventor 陈昌盛蓝锋博黄继武
Owner SHENZHEN 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