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

A Calligraphy Font Type and Text Content Synchronous Recognition Method

A text content and type recognition technology, applied in the field of image processing, can solve the problems of low recognition accuracy and efficiency, cumbersome recognition process, etc., achieve the effect of improving training efficiency and recognition efficiency, overcoming low recognition efficiency, and saving computing time

Active Publication Date: 2021-11-23
XIDIAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are: the method has requirements for the angle of calligraphy characters (requiring vertical placement) and the color of calligraphy characters (requiring black characters on a white background); it can only identify the font style of a single calligraphy character image
However, the shortcomings of this method are: the recognition process is cumbersome, and the recognition accuracy and efficiency are relatively low; only the text content of a single calligraphy image can be recognized

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 Calligraphy Font Type and Text Content Synchronous Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Attached below figure 1 The present invention is further described.

[0036] Step 1, generate a training set.

[0037] Select at least 2,500 images of individual calligraphy characters, of which 500 images are selected for each of the five font types, and each image is a commonly used Chinese character.

[0038] Reset the image dimensions to 103×103 pixels.

[0039] Label the font type and text content corresponding to each image.

[0040]The labeled 2500 images form the training set.

[0041] Step 2, construct a deep convolutional neural network.

[0042] Build a 7-layer deep convolutional neural network, and its structure is as follows: input layer → first convolutional layer → first maximum pooling layer → second convolutional layer → second maximum pooling layer → fully connected layer → output layer.

[0043] Set the size of the input layer to 103×103, set the size of the convolution kernel of the first convolution layer and the second convolution layer to 11...

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 method for synchronous recognition of calligraphy font type and text content, which belongs to the technical field of image processing, and further relates to a method for synchronous recognition of calligraphy font type and text content in the technical field of image text recognition. First generate a training set, then build a 7-layer deep convolutional neural network, use fonts and text content as labels respectively, train font type recognition networks and text content recognition networks, and finally combine font type recognition networks and text recognition networks to form fonts Type and Text Content Synchronous Recognition Network, which is used to simultaneously recognize the font type and text content of a single calligraphic character image. The invention improves network training and identification efficiency by using deep migration learning technology, and improves identification robustness by using online data enhancement technology. It has broad application prospects in calligraphy teaching, calligraphy evaluation and other scenarios.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a method for synchronously recognizing calligraphy font type and text content in the technical field of image character recognition. The invention is used for synchronously identifying the font type and text content of a single calligraphy character image, and can be applied to scenarios such as intelligent calligraphy teaching and calligraphy evaluation. Background technique [0002] There are many characters in Chinese calligraphy, and different fonts have distinct characteristics. Divided from the type of calligraphy character recognition, it is mainly divided into two categories: font style recognition and text content recognition. However, in many scenarios, it is necessary to recognize the font style and text content of a single calligraphy image at the same time. Synchronous recognition of the font style and text content of a single calligraphy character i...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06V30/413G06V30/226G06N3/045G06F18/214
Inventor 王俊平张亚琼方永强
Owner XIDIAN UNIV
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