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

Text detection and localization method in natural scene based on deep learning

A text detection and natural scene technology, applied in the field of computer vision, to achieve the effect of improving the detection effect

Active Publication Date: 2017-11-14
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF3 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is still a big difference between text and ordinary objects. Therefore, it is a great challenge to design a reasonable and efficient text detection method based on the characteristics of text.

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
  • Text detection and localization method in natural scene based on deep learning
  • Text detection and localization method in natural scene based on deep learning
  • Text detection and localization method in natural scene based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention.

[0041] In the text detection and positioning method in natural scenes based on deep learning proposed by the present invention, the text detection network is mainly obtained by improving the RPN, and mainly includes two stages, namely, the network generation and training stage and the text positioning and detection stage.

[0042] In the network generation and training phase,

[0043] First, based on the RPN network, set the strip anchor and regression method for the test picture, and introduce the RNN network layer to construct a text detection network;

[0044] Drawing on the idea of ​​Connectionist Text Proposal Network (CTPN) [10. Tian, ​​Zhi, etal. Detecting Text in Natural Image with Connectionist Text Proposal Network. Computer Vision–ECCV 2016. Springer International Pub...

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 provides a text detection and localization method in a natural scene based on deep learning. The size of anchor and the regression mode in an RPN (region proposal network) based on Faster-R CNN are changed according to the characteristic information of text. An RNN network layer is added to analyze image context information. A text detection network capable of detecting texts is constructed. In addition, the size of anchor is set through clustering. In particular, cascaded training is carried out through mining difficult samples, which can reduce the false detection rate of texts. In the aspect of test, a cascaded test method is employed. Finally, accurate and efficient text localization is realized.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and specifically relates to a deep learning-based text detection and positioning method in natural scenes, which can accurately locate text in natural scenes. Background technique [0002] As the carrier of human information dissemination, text contains rich semantic information. In natural scenes, text is everywhere, such as traffic signs, billboards in shops, posters, etc., where there are artificial traces, there are basically texts. Recognizing text from natural scenes is helpful in many fields. For example, in terms of image search, recognizing the text in the image will help us better classify and match the image; in terms of unmanned driving, recognizing the text information in traffic signs and other signs from natural scenes can assist driving. Text recognition in natural scenes is an indispensable and important part of development in today's rapid development of artificial int...

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): G06K9/00G06K9/32G06K9/62
CPCG06V30/414G06V20/62G06F18/23213G06F18/214
Inventor 操晓春伍蹈王蕊代朋纹张月莹
Owner INST OF INFORMATION ENG 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