Supercharge Your Innovation With Domain-Expert AI Agents!

Text content recognition method and device

A text and content technology, applied in the field of image processing, can solve the problems of low recognition accuracy, misinterpretation of real content, and no support for oblique text recognition.

Pending Publication Date: 2021-08-27
BEIJING QIYI CENTURY SCI & TECH CO LTD
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] When recognizing slanted text, due to the randomly selected text recognition algorithm, it does not support slanted text recognition, which will lead to garbled characters in the recognition, or it may be recognized as other text, which will lead to misinterpretation of the real content, resulting in low recognition accuracy

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
  • Text content recognition method and device
  • Text content recognition method and device
  • Text content recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0089] The technical solutions in the embodiments of the present invention will be described below with reference to the drawings in the embodiments of the present invention.

[0090] In the prior art, when there is slanted text in the image when performing graphic and text review, it is not possible to determine which text recognition algorithm to use for text recognition of the slanted text after the text detection is performed to determine the image area where the text is located. Randomly select a text recognition algorithm from text recognition algorithms that support landscape or portrait orientation, and perform text recognition on oblique text. When recognizing slanted text, due to the randomly selected text recognition algorithm, it does not support slanted text recognition, which will lead to garbled characters in the recognition, or it may be recognized as other text, which will lead to misinterpretation of the real content, which will lead to recognition accuracy. ...

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 embodiment of the invention provides a text content recognition method and device, and the method comprises the steps: obtaining a to-be-processed image, carrying out the text detection of the to-be-processed image, obtaining an image region containing a to-be-detected text in the to-be-processed image, and taking the image region as an initial image; rotating the initial image to obtain a to-be-detected image, wherein the longest boundary in the boundaries of the to-be-detected image is in the horizontal direction; determining a text direction of a to-be-detected text in the to-be-detected image based on a pre-trained text direction prediction model; and based on a text recognition algorithm corresponding to the text direction of the to-be-detected text, performing text recognition on the to-be-detected image to obtain text content of the to-be-detected text. Based on the processing, the recognition accuracy of text recognition can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for recognizing text content. Background technique [0002] When performing text recognition on an image, it is usually first to determine the position of the text to be detected in the image, and the image of the area where the text position is located can be called a target image. Then, based on the text recognition algorithm, text recognition is performed on the target image to obtain the text content. [0003] In the prior art, the text in the image is usually written horizontally or vertically. Therefore, by supporting horizontal or vertical text recognition algorithms, the horizontal text or vertical text in the target image can be recognized respectively to achieve better Text recognition effect. [0004] However, for the actual graphic and text review business, there is a high probability that the advertisements and other information mixed 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
IPC IPC(8): G06K9/32G06K9/46G06N3/04G06N3/08
CPCG06N3/08G06V20/62G06V10/44G06V30/10G06N3/044G06N3/045
Inventor 赵瑞书
Owner BEIJING QIYI CENTURY SCI & TECH CO LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com