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

Natural scene text detection method and system

A text detection and natural scene technology, applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve problems such as text confusion in complex backgrounds and foregrounds, and achieve the effects of simple methods, high prediction accuracy, and high recall rate

Inactive Publication Date: 2019-08-06
INST OF COMPUTING TECH CHINESE ACAD OF SCI +1
View PDF2 Cites 65 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the complex background is easily confused with the foreground text in the natural scene text detection method based on deep convolutional neural network

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
  • Natural scene text detection method and system
  • Natural scene text detection method and system
  • Natural scene text detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] Due to the complexity of natural scenes, there are two key points to improve natural scene text detection technology: 1. Improve the recall rate of natural scene texts; 2. Improve the accuracy rate of recalled texts. The technology of the present invention creatively improves the FCN (full convolutional neural network) structure used for object segmentation, and improves the accuracy of natural scene texts under the premise of ensuring the recall rate; at the same time, by improving the text recognition convolution loop neural network The network is an Attention-based (attention mechanism-based) text recognition network to improve the text recognition ability of the network, and then modify it to a text classification network to refine (fine-tune) the detection results to filter false detections due to confusing appearance as positive text regions, thereby achieving higher accuracy. Therefore, the technology of the present invention mainly includes two neural network mo...

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 natural scene text detection method and system. The system comprises two neural network models: a text detection network based on multi-level semantic feature fusion and a detection screening network based on an attention mechanism, wherein the text detection network is an FCN-based image feature extraction fusion network, and is used for extracting multi-semantic level information of input data, carrying out full fusion of multi-scale features, and finally predicting the position and confidence degree of text information in a natural scene by carrying out convolutionoperation on the fused multi-scale information. According to the detection screening network, the trained convolutional recurrent neural network is used for discriminating and scoring an initial detection result output by the convolutional neural network of the first part, so that a background which is easy to confuse with foreground characters is filtered out, and the accuracy of natural scene text recognition is further improved.

Description

technical field [0001] The invention relates to the fields of computer vision, document analysis and recognition, and natural scene text detection, and in particular to a natural scene text detection method and system. Background technique [0002] Text detection in natural scenes is both an important and extremely challenging task. Since text detection in natural scenes usually recognizes text in the scene in an open scene, factors such as illumination, angle, and distortion cause great interference to text detection, which seriously affects the accuracy of text detection. Traditional text detection generally uses technology based on ConnectedComponents (connected components), but this technology can only extract more obvious text regions, and it is difficult to take global information in the image into account, so the performance of this technology is relatively limited. At present, the natural scene text detection based on deep learning mostly adopts the technology based...

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): G06K9/32G06K9/62G06N3/04
CPCG06V20/62G06V20/63G06N3/045G06F18/214
Inventor 韩琥宋宇崔元顺山世光陈熙霖
Owner INST OF COMPUTING TECH 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