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

Curved character recognition method and system based on complex scene

A technology for character recognition and complex scenes, which is applied in the field of curved character recognition methods and systems, can solve problems such as poor recognition of curved characters, and achieve the effects of improving the accuracy of character recognition, improving the ability, and improving the application effect

Active Publication Date: 2022-01-04
北京数美时代科技有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, practice has shown that this pipeline is not good at recognizing curved text, which is more common in complex natural scenes

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
  • Curved character recognition method and system based on complex scene
  • Curved character recognition method and system based on complex scene
  • Curved character recognition method and system based on complex scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The principles and features of the present invention will be described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0052] like figure 1 As shown, a method for recognizing curved characters based on complex scenes provided by an embodiment of the present invention includes:

[0053] S1, detecting the first text region of the picture to be recognized based on the text segmentation model;

[0054] S2. Mark the non-text content in the first text area;

[0055] S3, removing the marked non-text content in the first text area to obtain a second text area;

[0056] In a certain embodiment, it may include: inputting the picture Xh*w*c into the text segmentation model f D (), where h and w are the height and width of the picture respectively, c is the number of channels of the picture, and the model outputs the detection result f w...

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 curved character recognition method and system based on a complex scene, and relates to the field of character recognition. The method comprises the steps of detecting a first character region of a to-be-recognized picture based on a character segmentation model, marking non-character content in the first character region, removing the marked non-character content in the first character region to obtain a second character region, inputting the second character region into a CRNN model improved by a convolutional layer, and obtaining a character recognition result. Compared with a regression method in an existing character recognition scheme, the segmentation method based on the character segmentation model has the advantages that bent characters can be more accurately detected, compact text lines can be effectively distinguished, and the processing speed is high. According to the scheme, curved characters frequently appearing in a natural scene can be accurately recognized, and the character recognition accuracy of the OCR in the natural scene is effectively improved. The application effect of various characters needing to be recognized is also improved.

Description

technical field [0001] The invention relates to the field of character recognition, in particular to a method and system based on curved character recognition in complex scenes. Background technique [0002] With the continuous development of society, the demand for image text recognition is also expanding. For example, texts and pictures with bad content emerge in an endless stream in online social media, which undermines the healthy development of the green network and will also damage the physical and mental health of netizens, especially young and middle-aged netizens. Although there is a character recognition technology, the existing technology cannot accurately recognize curved characters. However, curved text is especially common in natural scenes. [0003] The main process of relevant picture text recognition technology at this stage can include: two steps of detection and recognition, 1. Use the text detection model to detect the position of the text in the pictur...

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): G06V30/146G06V30/148G06V10/44G06V10/764G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24
Inventor 马丹峰唐会军梁堃刘拴林陈建
Owner 北京数美时代科技有限公司
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