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

Scene character detection method

A text detection and scene technology, applied in the field of text recognition, can solve the problems of text detection diversity in cumbersome post-processing steps, detection speed and accuracy need to be improved, and achieve the effect of improving quality and performance

Active Publication Date: 2019-09-20
UNIV OF SCI & TECH OF CHINA +1
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because these methods contain cumbersome post-processing steps and the diversity of text detection itself, the speed and accuracy of detection still need to be improved.

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
  • Scene character detection method
  • Scene character detection method
  • Scene character detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, 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.

[0020] An embodiment of the present invention provides a scene text detection method. First, the extracted feature maps of different sizes are mapped to a unified size. Then, a scale relationship module is established in the feature map to realize feature transfer at different scales. Since these feature maps have better representations for texts of different scales (small-size feature maps can better detect large objects and lose detail detection ...

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 scene character detection method, which comprises the following steps of: carrying out feature extraction on an input image by utilizing a neural network, and carrying out up-sampling operation on the extracted feature map to obtain feature maps with different sizes; mapping the feature maps of the rest sizes into the same size as the feature map of the maximum size by taking the feature map of the maximum size as a standard; carrying out scale information fusion on the feature maps mapped to the same size to obtain a fused feature map, wherein characters of different sizes are uniformly activated in the fused feature map through the fusion operation; and carrying out text box regression and classification operation on the fused feature map to obtain a scene text detection result. According to the method, the quality of the feature map can be fundamentally improved, so that the scene character detection performance is improved.

Description

technical field [0001] The invention relates to the technical field of character recognition, in particular to a scene character detection method. Background technique [0002] Natural scene text detection and recognition is a general text recognition technology, which has become a hot research direction in the field of computer vision and document analysis in recent years. It is widely used in license plate recognition, driverless driving, human-computer interaction and other fields. [0003] Due to the difficulties of text detection and recognition in natural scenes, such as complex background, low resolution, and variable fonts, traditional text detection and recognition technologies cannot be applied to text detection and recognition in natural scenes. As the basis of recognition, text detection technology has great research significance. [0004] In recent years, with the development of deep learning technology in the field of object detection, general object detection...

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): G06K9/62G06K9/32
CPCG06V20/63G06V30/10G06F18/253G06F18/24G06F18/214
Inventor 张勇东王裕鑫谢洪涛李岩
Owner UNIV OF SCI & TECH OF CHINA
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