Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Image extraction method and device, equipment and storage medium

An extraction method and image technology, applied in the field of image processing, can solve the problems affecting the efficiency of business processing, incomplete images in the effective area, inaccurate identification information, etc. Guaranteed Integrity Effect

Pending Publication Date: 2022-07-15
深圳怡化电脑科技有限公司
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, when the existing technology extracts the effective area image of the target area image through the circumscribed rectangle or the straight line fitted by the upper boundary point, the central point and the lower boundary point, one or more partial effective area images of the complete effective area image will be extracted, resulting in The extracted effective area image is incomplete, and multiple effective area images will lead to inaccurate identification information, which will ultimately affect the processing efficiency of the business

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
  • Image extraction method and device, equipment and storage medium
  • Image extraction method and device, equipment and storage medium
  • Image extraction method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] figure 1 A flowchart of an image extraction method is provided for the first embodiment of the present invention. This embodiment can be applied to the situation of accurate extraction of bill image recognition. The method can be executed by an image extraction device, and the classification device can use hardware and / or Implemented in the form of software, the classification device can be configured in electronic equipment. like figure 1 As shown, the method includes:

[0034] S110. Perform image preprocessing on the original image to obtain a binarized image.

[0035] Wherein, the original image may be an image to be detected collected by an image capture device, and it is understood that the image capture device may be a device with a camera scanning function; exemplarily, it may be an image capture device scanning a fixed capture area to be detected The original image of the bill may also be the original image of the bank card to be detected, the original image ...

Embodiment 2

[0060] figure 2 This is a flowchart of another image extraction method provided by the second embodiment of the present invention. The relationship between this embodiment and the above-mentioned embodiments is that the image of the binarized image is calculated according to the boundary points of the binarized image. The angle of inclination is further explained. like figure 2 As shown, the method includes:

[0061] S210: Perform image preprocessing on the original image to obtain a binarized image.

[0062] S220. Determine a boundary point of at least one boundary of the binarized image.

[0063] S230 , performing least squares fitting on the boundary points of each boundary of the binarized image, respectively, to obtain boundary straight lines and boundary point coordinates of each boundary of the binarized image after fitting.

[0064] In the embodiment of the present invention, the boundary points of the four sides of the binarized image are successively fitted by ...

Embodiment 3

[0093] image 3 is a schematic diagram of an image extraction device provided in Embodiment 3 of the present invention, such as image 3 As shown, the device includes: an image processing module 310, a boundary point search module 320, an inclination angle calculation module 330, a minimum region of interest determination module 340, and a target region image determination module 350, wherein:

[0094] an image processing module 310, configured to perform image preprocessing on the original image to obtain a binarized image;

[0095] a boundary point search module 320, configured to determine a boundary point of at least one boundary of the binarized image;

[0096] a tilt angle calculation module 330, configured to calculate the image tilt angle of the binarized image according to the boundary points of the binarized image;

[0097] A minimum region of interest determination module 340, configured to determine the minimum region of interest in the binarized image according ...

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 embodiment of the invention discloses an image extraction method and device, equipment and a storage medium. The method comprises the following steps: carrying out image preprocessing on an original image to obtain a binary image; determining a boundary point of at least one boundary of the binarized image; calculating an image inclination angle of the binarized image according to the boundary points of the binarized image; and rotating the minimum region of interest according to the image inclination angle, and removing a black edge of the rotated minimum region of interest to obtain a target region image. According to the invention, the efficiency and accuracy of determining the boundary points of the target area image are improved, so that the extracted target area image is more accurate.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, and in particular, to an image extraction method, apparatus, device, and storage medium. Background technique [0002] In the Internet era, the business of bills or certificates often needs to detect and identify the relevant content of the bills or certificates. There is often a lot of irrelevant information in the existing collected images of traditional bills and certificates. Therefore, it is necessary to locate and identify the collected images before processing the bills or certificates. It will increase the difficulty of locating and identifying the content of the bill, and it will also be relatively time-consuming. [0003] Therefore, we usually need to perform effective area extraction on the device-acquired images. In the prior art, for the original image recognition of bills, the image binarization is used to find the circumscribed rectangle in the connected doma...

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): G06V10/28G06V10/44G06V10/25G06V10/24
Inventor 曹川
Owner 深圳怡化电脑科技有限公司
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
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