Document correction method based on deep learning semantic segmentation

A semantic segmentation and deep learning technology, applied in the field of image processing, can solve problems such as application scene limitations, and achieve the effect of accurate and reliable image correction

Pending Publication Date: 2020-09-04
东莞茅飞信息科技有限公司
View PDF0 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method often needs to collect images from multiple angles in order to obtain a 3D model that can solve the equations enough to reconstruct the document image, which is also limited by the application scene

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 correction method based on deep learning semantic segmentation
  • Document correction method based on deep learning semantic segmentation
  • Document correction method based on deep learning semantic segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0049] In view of the existing correction algorithms for distorted document images, it is necessary to take multiple images of objects and combine a series of parameters for image correction, which is easily restricted by factors such as operating thresholds and application scenarios. The present invention provides a method based on deep learning The document correction method of semantic segmentation does not require additional support such as hardware equipment and system calibration, and mobile devices such as m...

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 image processing, in particular to a document correction method based on deep learning semantic segmentation, which comprises the following steps: classifying document pixels of an image to be corrected by using a deep neural network model to obtain a document semantic segmentation feature map; performing contour analysis on the document, and determining document deformation information in the to-be-corrected image; constructing an assistance correction plane, obtaining a transformation relationship of document deformation information in the to-be-corrected image on an auxiliary correction plane. According to the method, image correction is carried out through the transformation relation, so that additional hardware equipment is canceled to obtain enough shooting freedom degree, limitations caused by factors such as an operation threshold and an application scene are broken through, and image correction can still be accurately and reliably carried out when complex documents or documents with complex backgrounds are faced.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a document correction method based on deep learning semantic segmentation. Background technique [0002] Mobile products are increasingly infiltrating people's daily life. Using mobile terminals to scan documents has become a trend, and there are more and more software products in the application market to address such needs. However, when pursuing the convenience brought by mobile document scanning, it also encounters various limitations in its technical implementation, such as lens distortion caused by optical path refraction caused by lenses, perspective distortion caused by projection of three-dimensional space onto the imaging plane, and document plane itself. These factors have become a major obstacle to the popularization of mobile document scanning. [0003] At present, traditional correction algorithms for distorted document images generally mainly include corr...

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): G06T3/60G06T7/11G06T7/187
CPCG06T3/608G06T2207/10004G06T2207/20081G06T2207/20084G06T7/11G06T7/187
Inventor 涂旭平林浩泓黄斐
Owner 东莞茅飞信息科技有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap