A text recognition method based on attention mechanism

A text recognition and attention technology, applied in the field of scene text recognition, can solve problems such as difficulties

Active Publication Date: 2019-03-29
BEIJING UNIV OF TECH
View PDF6 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to overcome the problem that it is very difficult to make the spatial attention mechanism accurately pay attention to the 2D features directly, and how to improve the representation ability of the features, including spatial information and semantic information

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
  • A text recognition method based on attention mechanism
  • A text recognition method based on attention mechanism
  • A text recognition method based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0054] like Figure 1-3 As shown, a text recognition method based on the attention mechanism, the spatial attention network (SAN) is an end-to-end text recognition model, the main structure consists of figure 1 As shown, the text recognition model includes a feature extractor with local neural network, residual neural network and coordinate information, and a spatial decoder based on attention mechanism. The text recognition model is based on the encoding and decoding structure, so the text recognition model can also be understood as an encoder and a decoder. The encoder is used to encode the input image to obtain a coded feature sequence that the decoder can recognize. The decoder is used to decode the encoded features of the encoder, so as to realize the recognition of text in the image.

[0055] Think of the encoder as a feature extraction netwo...

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 text recognition method based on attention mechanism. The network SAN based on spatial attention is an end-to-end text recognition model. The text recognition model comprisesa feature extractor with a local neural network, a residual neural network and coordinate information, and a spatial decoder based on attention mechanism. The text recognition model is based on the encoding and decoding structure, so the text recognition model can also be understood as encoder and decoder. The encoder is used to encode the input image to obtain the encoded feature sequence whichcan be recognized by the decoder. A decoder is used to decode the encoded features of the encoder, thereby realizing recognition of text in an image. For the arc text CUTE80 dataset, the result of this method is superior to all the existing methods, and the accuracy is 77.43%. In other scene text datasets, this method also has a good effect.

Description

technical field [0001] The present invention is based on a spatial attention network (SAN) to identify irregular text in natural scenes, and uses the obtained spatial information as the input of the encoder-decoder model to generate a character sequence, and especially relates to a text recognition based on an attention mechanism The method belongs to the technical field of scene text recognition. Background technique [0002] In the past few years, the task of scene text recognition has received a lot of attention, and there are already some solutions. Text recognition is usually divided into two types: traditional single character detection recognition and sequence text recognition. Most traditional models use a bottom-up mechanism by first extracting low-level features for a single detected character and then recognizing the character, and finally combining the characters into a string through a set of prior knowledge. This type of identification persisted in earlier st...

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): G06K9/20G06T9/00
CPCG06T9/002G06V10/22
Inventor 李宏伟李蓉
Owner BEIJING UNIV OF TECH
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