Supercharge Your Innovation With Domain-Expert AI Agents!

Document image detection method, device and equipment and storage medium

A document image and detection method technology, which is applied in neural learning methods, instruments, biological neural network models, etc., can solve the problems of not taking into account document remakes and inability to accurately identify document remake images, and achieve fast detection speed and high detection accuracy. , the effect of small detection area

Pending Publication Date: 2021-02-23
SHENZHEN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, whether it is aimed at ordinary text in document images, or specific seal images and handwritten signatures, these detection methods that use special parts in document images do not take into account the practical problem of document remakes, resulting in the inability to accurately identify document remakes. image

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
  • Document image detection method, device and equipment and storage medium
  • Document image detection method, device and equipment and storage medium
  • Document image detection method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] figure 1 It is a schematic flow chart of a method for detecting a document image provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation where the bronzing area of ​​a document image is detected to identify whether it is a copy. detection means to perform, as figure 1 As shown, it specifically includes the following steps:

[0047] Step 1100, acquire the image of the document to be tested.

[0048] The image of the document to be tested is obtained based on the original document, which may be an image of the original document or a remake of the original document; the image of the document to be tested can be one or more, and the image of the document to be tested is a color image, such as RGB format image, LAB format image, TIFF format image, JPG format image and PNG format image, etc.

[0049] Step 1200, using a preset image extraction method to extract the hot stamping area image in the document image to be tested.

[0050...

Embodiment 2

[0062] Figure 2A It is a schematic flowchart of a document image detection method provided in Embodiment 2 of the present invention, Figure 2B It is a schematic sub-flow diagram of a document image detection method provided in Embodiment 2 of the present invention, Figure 2C It is a schematic sub-flow diagram of another document image detection method provided in Embodiment 2 of the present invention.

[0063] Such as Figure 2A As shown, a document image detection method specifically includes the following steps:

[0064] Step 2100, establishing a document image database, which includes original document images and reproduced document images.

[0065] Further, the document image database includes a plurality of document images with bronzing area images, which may include original document images with bronzing area images and reproduced document images.

[0066] Step 2200, process the images in the document image database to obtain a training data set and a verification...

Embodiment 3

[0103] image 3 A schematic structural diagram of a document image detection device provided in Embodiment 3 of the present invention, as shown in image 3 As shown, a detection device for a document image includes:

[0104] An image acquisition module 3100, configured to acquire an image of the document to be tested.

[0105] The image of the document to be tested is obtained based on the original document, which may be an image of the original document or a remake of the original document; the image of the document to be tested can be one or more, and the image of the document to be tested is a color image, such as RGB format image, LAB format image, TIFF format image, JPG format image and PNG format image, etc.

[0106] The image extraction module 3200 is configured to extract the bronzing area image in the document image to be tested by using a preset image extraction method.

[0107] In some qualification examinations and award evaluations, it is necessary to review th...

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 document image detection method and device, equipment and a storage medium. The method comprises the steps of obtaining a to-be-tested document image; extracting a gold stamping area image in the to-be-detected document image by adopting a preset image extraction method; detecting the gold stamping area image by adopting a preset copying detection model; and determining adetection result of the to-be-detected document image according to the detection result. The detection model trained by the gold stamping area image is adopted to detect the image block of the gold stamping area of the to-be-detected document image, so that whether the to-be-detected document image is the copied document image or not is judged, and the problem that an existing classification method cannot accurately identify the copied document image and the original document image is solved; whether the to-be-detected document image is the duplicated document image or not can be quickly recognized only by detecting the gold stamping area image, the detection area is small, the detection speed is high, and the detection precision is high.

Description

technical field [0001] Embodiments of the present invention relate to document image detection technologies, and in particular, to a document image detection method, device, device, and storage medium. Background technique [0002] In the existing detection of document images, specific features in legal images and forged images are extracted, such as text, seals and handwritten signatures, etc., and a classifier is trained based on the extracted features to build a classifier that can realize forgery detection. [0003] However, whether it is aimed at ordinary text in document images, or specific seal images and handwritten signatures, these detection methods that use special parts in document images do not take into account the practical problem of document remakes, resulting in the inability to accurately identify document remakes. image. Contents of the invention [0004] The invention provides a document image detection method, device, equipment and storage medium to ...

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): G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/443G06V10/267G06V10/751G06N3/045G06F18/241G06F18/214
Inventor 陈昌盛颜佳宾
Owner SHENZHEN UNIV
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