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

Video character recognition method and device, equipment and storage medium

A video and target video technology, applied in the field of computer vision, can solve problems such as low efficiency and achieve the effect of improving extraction efficiency

Pending Publication Date: 2022-04-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when using OCR to recognize text in a video, it is usually necessary to screenshot the video several times per second, and to recognize the text in the image for each captured video image, which will make the recognized subtitles have certain Redundancy, so inefficient when obtaining the final video text

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 character recognition method and device, equipment and storage medium
  • Video character recognition method and device, equipment and storage medium
  • Video character recognition method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0078] Wherein, the method of determining the video image to be recognized in the image sequence based on the text tracking track may be: respectively selecting the target text image area from each group of text tracking tracks, and obtaining the video image to be identified corresponding to the text image area from the image sequence. Under this kind of embodiment, specifically can be to select respectively the text image region with the highest clarity or contrast as the target text image region from each group of text tracking tracks; it can also be to arbitrarily select a target text image from each group of text tracking tracks area; it can also be weighted processing on each text image area in each group of text tracking tracks to obtain the target text image area; it can also be to obtain at least one text image whose clarity is greater than a preset threshold from each group of text tracking tracks region as the target text image region.

[0079] The number of target t...

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 character recognition method and device, electronic equipment and a storage medium, and the method comprises the steps: respectively determining a text detection box from each video image of an image sequence corresponding to a video, carrying out the matching of text image regions in adjacent video images based on the text detection boxes, obtaining a text tracking trajectory of the same text, and carrying out the recognition of the same text. According to the method and the device, text image areas corresponding to continuous multiple frames of video images with matched text features or information corresponding to the text image areas are added into a group of text tracking trajectories, so that video characters corresponding to a video are extracted; in the embodiment of the invention, the to-be-recognized video image is determined in the image sequence for each group of text tracking trajectory, and character recognition is performed on the determined to-be-recognized video image to obtain the video character corresponding to the video, so that the extraction efficiency of the video character can be effectively improved.

Description

technical field [0001] The present application relates to the field of computer vision technology in artificial intelligence technology, and more specifically, relates to a video text recognition method, device, equipment and storage medium. Background technique [0002] With the development of digital media technology, video has become an indispensable part of people's daily life, and video usually carries information such as sound, image and text at the same time. In order to analyze the information in the video, such as sound, text and image, etc., the information in the video needs to be obtained. [0003] At present, when acquiring text information carried in a video, an optical character recognition (Optical Character Recognition, OCR) technology may be used to recognize characters on a video screen to obtain video text. However, when using OCR to recognize text in a video, it is usually necessary to screenshot the video several times per second, and to recognize the ...

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): G06V30/418G06V30/24G06V30/18G06V30/19G06N3/04G06N3/08
Inventor 王洪松
Owner TENCENT TECH (SHENZHEN) CO LTD
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