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

Character detection method based on deformable convolutional neural network

A convolutional neural network, text detection technology, applied in the field of image processing, can solve the problem of low text detection accuracy, and achieve the effect of improving accuracy, reducing matrix multiplication, and improving efficiency

Pending Publication Date: 2019-11-01
GUANGDONG UNIV OF TECH
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a text detection method based on a deformable convolutional neural network in order to solve the problem of low detection accuracy of texts of different sizes in images in the prior art

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
  • Character detection method based on deformable convolutional neural network
  • Character detection method based on deformable convolutional neural network
  • Character detection method based on deformable convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0046] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0047] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0048] A text detection method based on deformable convolutional neural network, such as figure 1 shown, including the following steps:

[0049] S1. Receive an input image, the image includes text information to be detected;

[0050] S2. Construct a convolutional neural network, which includes a deformable convolutional structure;

[0051] The convolutional neural network uses the VGG19 network as the basic network architecture, and the deformable convolution structure is specifically: replace the Conv2D layer in the original VGG19 network 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 character detection method based on a deformable convolutional neural network, and the method comprises the steps: receiving an input image which comprises character information, constructing the convolutional neural network which comprises a deformable convolutional structure, carrying out the feature extraction of the image, and obtaining a plurality of feature maps; extracting a feature vector on the feature map by using a sliding window, and predicting a plurality of candidate boxes according to the feature vector; inputting the feature vector into a BiGRU network, and inputting an output result of the BiGRU network into a full connection layer; and classifying and regressing the feature vector result obtained from the full connection layer, and obtaining a text detection result in the image through a text construction algorithm based on the classification and regression result. Since the convolution area covers the vicinity of the object in any shape andthe multilayer detection is used, the too large or too small font in the image is effectively detected, and the problem of low detection accuracy of characters in different sizes in the image in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of image processing, and more specifically, to a text detection method based on a deformable convolutional neural network. Background technique [0002] In recent years, with the development of deep learning, text detection technology has been greatly improved. The application of text detection and recognition technology in natural scenes is very extensive. Various application systems have begun to be launched, such as business card recognition system, ID card and bank card recognition system. , license plate recognition system, bank bill recognition system, value-added tax invoice recognition and authentication system, etc. Among them, text detection and recognition in natural scenes includes two tasks, namely text detection and text recognition. Since the correct rate of text detection directly determines the correct rate of subsequent text recognition, text detection occupies a very important posi...

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): G06K9/46G06N3/04
CPCG06V10/40G06V30/10G06N3/045
Inventor 黄国恒杨帆黄和锟
Owner GUANGDONG UNIV OF TECH
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