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

Method for identifying text font in natural scene picture

A technology of natural scenes and recognition methods, applied in the fields of computer image processing and artificial intelligence, can solve the problems of large difference in authenticity, low recognition accuracy, and difficulty in accurately recognizing Chinese fonts, and achieve the effect of improving recognition accuracy.

Active Publication Date: 2018-08-07
PEKING UNIV
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the DeepFont method uses a relatively simple synthesis method to synthesize training data, and the data is quite different from natural scene pictures in terms of authenticity.
This defect makes it difficult to accurately identify Chinese fonts in natural scene pictures when dealing with pictures with noisy text backgrounds and rich font effects.

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
  • Method for identifying text font in natural scene picture
  • Method for identifying text font in natural scene picture
  • Method for identifying text font in natural scene picture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0053] The invention provides a font recognition method based on picture synthesis and transfer learning. First of all, the present invention uses a brand-new picture synthesis method to integrate texts of different fonts and languages ​​into natural scene pictures to obtain more realistic pictures. These pictures can train font classifiers and text positioning with high recognition accuracy device. The text locator then locates more text images from Internet images, and these images are used to further improve the recognition accuracy of the font classifier.

[0054] Flow chart of the present invention is attached figure 1 As shown, the specific implementation includes the following steps:

[0055] 1 Synthesize a large number of pictures containing text in different fonts, and record the location...

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 identifying a text font in a natural scene picture. With a picture synthesis method, lots of natural scene pictures that are integrated with different font texts and are similar to real effects specifically are obtained; picture training is carried out to obtain a font identifying device and a text location device; more text pictures are located in an internetpicture by using the text location device; and on the basis of a migration learning method, learning is carried out in the pictures by using the font identifying device, so that the identification precision is improved. According to the invention, the high-quality training picture is synthesized automatically, so that manual marking needing lots of time and efforts is avoided and the cost is lowered substantially; with the font classification device, the high identification precision is realized. Besides, because of introduction of the migration learning method, the accuracy of the font classification device is enhanced by using lots of font-tag-free pictures.

Description

technical field [0001] The invention belongs to the fields of computer image processing and artificial intelligence, and relates to a font recognition method, in particular to a method for recognizing text fonts in natural scene pictures. Background technique [0002] In the field of computer image processing, font recognition refers to allowing the computer to automatically determine which font the text in the picture belongs to in the font list. The font list is established by people in advance and usually includes the most commonly used fonts in real life. If the font of the text in a picture does not belong to the above font list, let the computer find the most similar font from the font list. Font recognition in natural scene pictures specifically refers to finding out the position of the text in a natural scene picture containing text, and then identifying the font of the text. Automatic recognition of text fonts has considerable practical value in meeting people's co...

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
IPC IPC(8): G06K9/00G06K9/20G06K9/34G06K9/62G06N3/08G06T7/90
CPCG06N3/08G06T7/90G06V30/413G06V10/225G06V30/153G06V10/267G06F18/285
Inventor 连宙辉王逸之唐英敏肖建国
Owner PEKING 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