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

Video text extraction method

A text extraction and text technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as time-consuming, improve quality, improve text recognition rate, and improve system efficiency

Inactive Publication Date: 2018-01-05
北京新岸线网络技术有限公司
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are many videos in one video, so this process will consume a lot of time

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
  • Video text extraction method
  • Video text extraction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment provides a method for video text extraction of text, comprising the following steps:

[0044] S101, dividing the video sequence into each shot, so that the text tracking in step S104 can be carried out inside the shot instead of the entire video sequence, which can simplify the problem, and can support parallel text positioning and tracking, greatly improving system efficiency .

[0045] The so-called shot refers to the video image sequence recorded by one camera operation of the camera. The shot boundary is the result of switching between two shots, and the content of the video has changed, that is to say, the shot boundary reflects the discontinuity of the video content.

[0046] S102, detecting and locating the specific position of the candidate text in a single video frame; minimizing the number of false text regions.

[0047] S103, on the basis of the text positioning, the text is tracked inside the video lens, and the text area sequence of the sa...

Embodiment 2

[0051] The present invention aims at extracting structured text information from video programs. The main links are divided into: segmentation, positioning, tracking, identification and layout analysis.

[0052] The system uses a "semi-automatic" strategy to process video, that is, while providing the system with the processed video, it also needs to provide the corresponding configuration file.

[0053] There are many kinds of video programs, and the production styles of different programs, such as whether the stroke width of characters is uniform, the color contrast between characters and background, and the arrangement characteristics of characters, etc., are very different. It is impossible to find a general text feature and processing suitable for all video text information. method.

[0054] Algorithms and their parameters in text processing are highly specific. An algorithm can achieve high performance in a specific application environment, but the performance becomes ...

Embodiment 3

[0150] Embodiment 3 of the present invention provides a system for video text extraction, including:

[0151] Video shot segmentation module 11, for video sequence is divided into single shot;

[0152] Text location module 12, for detecting and locating the specific position of candidate text in a single video frame sequence;

[0153] The text tracking module 13 is used to track the text inside the video shot on the basis of the text positioning, so as to obtain the text region sequence of the same text object in continuous multi-frames;

[0154] Enhancement and binarization module 14, for utilizing the text sequence obtained by text tracking to enhance the text, suppress the background, and then perform binarization to obtain a binarized text image;

[0155] The text recognition module 15 is configured to perform text recognition on the binarized text image to obtain character sequence information of the text.

[0156] Preferably, the text positioning module 12 specifically...

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 video text extraction method, comprising: dividing a video sequence into a single shot; detecting and locating the specific position of a candidate text in a single video frame sequence; Track the text to obtain the text area sequence of the same text object in consecutive multiple frames; use the text sequence obtained by text tracking to enhance the text, suppress the background, and then perform binarization to obtain a binarized text image; The final text image is subjected to text recognition to obtain the character sequence information of the text. By adopting the technical scheme provided by the invention, the text in the video can be better detected and separated from the complex polygonal background, the system efficiency can be improved, and the quality of the text can be improved, thereby helping to improve the text recognition rate.

Description

technical field [0001] The invention relates to the field of image-based and information technologies, in particular to a method for extracting video text. Background technique [0002] In order to extract text from a video frame, it is necessary to first find the frame containing the text, and then determine the position of the text. Usually in a video program, not all video frames contain text, and sometimes in a video program, most of the frames may not contain text. Existing technologies generally detect each video frame, and then match each video frame, thereby removing duplicate results. There are many videos in one video, so this process will consume a lot of time. Contents of the invention [0003] In view of this, an object of the present invention is to provide a method for video text extraction, which divides the video into shots, and then detects the text inside each shot, which is conducive to simplifying the problem, and after being divided into shots, it c...

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): G06K9/00G06K9/32
Inventor 张师群罗旻
Owner 北京新岸线网络技术有限公司
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