Method and device for distinguishing fake certificate picture

A technology of pictures and certificates, applied in the field of image processing, can solve the problem of low accuracy and achieve the effect of improving accuracy

Inactive Publication Date: 2017-03-08
BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, the detection accuracy of active anti-counterfeiting technology and passive anti-counterfeiting technology in the prior art is relatively low

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
  • Method and device for distinguishing fake certificate picture
  • Method and device for distinguishing fake certificate picture
  • Method and device for distinguishing fake certificate picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0023] figure 1 It is a flowchart of the method for identifying forged document images provided in the first embodiment of the present invention. This embodiment can be applied to the qualification authentication of the client who publishes information. The method can be executed by a computer and specifically includes the following:

[0024] S110: Extract image features of the picture to be detected.

[0025] For example, the image of the picture to be detected is first transferred from the RGB color space to the HSV color space, quantized and sampled according to the accuracy of the application, and combined with the spatial information to perform position-related HSV histogram feature extraction on the image. x,y (h, s, v), where h, s, v represent colors, x, y represent the position coordinates of the colors represented by h, s, and v in the original image, and H represents h, s, and s within the relationship between x and y. The ratio of the number of pixels of the color represe...

Embodiment 2

[0041] figure 2 It is a flow chart of the method for identifying forged document images provided in the second embodiment of the present invention, which specifically includes the following:

[0042] S210: Extract image features of the picture to be detected.

[0043] S220: According to the image characteristics, search for similar pictures in the gallery search system.

[0044] S230: Compare the image feature of the picture to be detected with the image feature of the similar picture, and determine a similar picture that reaches a set similarity with the image feature of the picture to be detected.

[0045] By comparing the image features of the image to be detected with the image features of similar pictures, determine the similar pictures that reach the set similarity with the image features of the image to be detected, and select similar pictures that are closer to the image features of the image to be detected, thereby reducing similarity The number of pictures reduces the amoun...

Embodiment 3

[0055] image 3 It is a flow chart of the method for identifying forged document images provided in the third embodiment of the present invention, which specifically includes the following:

[0056] S310: Extract image features of the picture to be detected.

[0057] S320, according to the image characteristics, search for similar pictures in the gallery search system.

[0058] S330: Calculate the similarity between the picture to be detected and the similar picture.

[0059] S340: When the similarity exceeds a set threshold, it is determined that the picture to be detected is a forged document picture.

[0060] S350, display similar pictures for manual identification.

[0061] When the similarity between the picture to be detected and the similar picture exceeds the set threshold, similar pictures with the similarity exceeding the set threshold are displayed to facilitate manual verification and identification.

[0062] In this embodiment, by extracting the image characteristics of the 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 method and a device for distinguishing a fake certificate picture. The method comprises steps of: extracting image features of a to-be-detected picture; according to the image features, searching a similar picture in a picture library searching system; calculating similarity of the to-be-detected picture and the similar picture; and when the similarity exceeds a set threshold value, determining that the to-be-detected picture is a fake certificate picture. According to the invention, whether a to-be-detected picture is a fake certificate picture is distinguished by searching a similar picture in the picture library searching system, so accuracy of detection of certificate pictures is improved.

Description

Technical field [0001] The embodiment of the present invention relates to image processing technology, in particular to a method and device for identifying pictures of forged documents. Background technique [0002] With the increase in economic value brought about by commercial search, the business of publishing information on the Internet and the number of customers have also continued to increase. Many customers without legal qualifications have also been mixed in, relying on forged business licenses and other qualification images to publish and publish information through qualification review. In order to pass the verification of official data, some qualifications are fake qualification images generated by applying others' qualification templates, that is, qualification certificates. [0003] In the prior art, when judging whether a credential picture is forged, it is mostly used to identify tampering with the content of the picture itself, including active anti-counterfeiting ...

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): G06T1/00G06F17/30
Inventor 邓玥琳黄浩
Owner BAIDU ONLINE NETWORK TECH (BEIJIBG) CO LTD
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