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

Method for registration of document image and selection of characteristic points

A document image and image registration technology, applied in image data processing, graphic image conversion, instruments, etc., can solve the problem of uncommon registration methods, improve ease of use and versatility, avoid extra work, and achieve high efficiency. awesome effect

Inactive Publication Date: 2009-03-04
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF0 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method can only be used for specific documents, and for many documents, these positioning marks are not provided, making the registration method not universal

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 for registration of document image and selection of characteristic points
  • Method for registration of document image and selection of characteristic points
  • Method for registration of document image and selection of characteristic points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0035] This implementation example takes document image filling content extraction as an example to describe the implementation method of the document image registration method therein. In the extraction of document image filling content, the registration image is firstly registered with the reference image through the image registration method, and then the difference between the registration image and the reference image is compared. The difference is the content filled in by the user, which can be extracted for further processing. Reference images refer to documents that users have not filled in, forms or explanatory texts printed to guide users to fill in content, etc. The registration image is a document image with content filled in by the user, that is, the content filled in by the user is included in addition to the same pre-printed content as in the reference image. In the description of this embodiment, the reference image and the registration image are binary images...

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 relates to the technical field of the image processing subject, in particular to a general document image registration and feature point selection method. In the method, image outlines are used as document image registration features and outline points are used for representing document image outlines. The method comprises the following steps: a plurality of points are selected automatically from a reference image and a registered image as image registration feature points with document image outline points as candidates by adopting the feature point selection method; subsequently, a plurality of candidate matching point set pairs are selected in a centralized way from the feature points with projective transformation invariables as similarities; geometric transformation corresponding to the point set pairs is figured out as candidate registration transformation; finally, being measured in outline matching degree, the optimal matching transformation is looked for from candidate registration transformation as the ultimate registration transformation for registration of document images. The method is applicable for registration of document images of different types, and is very efficient and robust.

Description

technical field [0001] The invention relates to the technical field of image processing disciplines, in particular to a method for registering document images and selecting feature points. Background technique [0002] Document image is the digital image form of paper documents, and it is also an important way to bring paper documents into computer management. The goal of document image processing is often to provide image processing support for processing the content contained in the document, which is an important part of office automation technology, such as extracting text images from document images and submitting them to text recognition technology to realize the recognition of text information Wait. Document image registration is an important content in document image processing. Image registration refers to performing a certain geometric transformation on an image and mapping it to another image, so that the relevant points in the two images are consistent in space...

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): G06T3/00
Inventor 戴汝为朱远平肖柏华王春恒
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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