Video subtitle information extracting method

A technology for information extraction and subtitles, which is used in TV, color TV, image communication, etc., and can solve the problems of background complexity, difficulty in finding the intersecting parts of strokes, and poor versatility.

Inactive Publication Date: 2009-06-10
INST OF COMPUTING TECH CHINESE ACAD OF SCI
View PDF0 Cites 49 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the threshold-based method has the disadvantages of poor generality and difficulty in adapting to complex backgrounds, while the stroke-based method has the disadvantage that stroke intersections are difficult to find, thus affecting subtitle recognition
[0008] In view of the fact that the existing video subtitle extraction methods have their own problems in each implementation step, and in various videos actually detected, the accuracy and robustness of video subtitle information extraction are restricted by the following four factors: 1. Background 2. Low resolution of video images; 3. Changes in font, size, color and arrangement; 4. Characteristics of characters in different languages

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 subtitle information extracting method
  • Video subtitle information extracting method
  • Video subtitle information extracting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] The method of the present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0100] Such as figure 1 Shown, video subtitle extracting method of the present invention comprises the following steps:

[0101] Step 10, performing preprocessing on the video images that need to extract subtitles. In this embodiment, the preprocessing of the video image is mainly to extract the luminance component from the video image, and then perform a grayscale operation on the luminance component. Assuming that the video image in this embodiment is coded in an RGB mode, the following formula is followed when performing grayscale operation on the brightness component Y:

[0102] Y=0.299R+0.587G+0.114B

[0103] Those of ordinary skill in the art should understand that in the YUV or YCrCb space, the brightness component is represented by Y, so the brightness component can be extracted according to the above formula, and then th...

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 provides a method for extracting video subtitle information, which comprises: preprocessing video images of which subtitles are required to be extracted; performing multi-dimensional subtitle region detection on the preprocessed video images, and obtaining rectangular blocks which represent the dimension and the position of subtitle regions; utilizing the rectangular blocks to split detected subtitle regions; enhancing the contrast of split subtitle regions; and adopting a K mean cluster method to realize extraction of the subtitles. The method has commonality on different language types, different fonts and different dimensions of the subtitles and different video program types, has the advantages of high accuracy of subtitle region detection and character recognition and high speed, does not need to perform model training under the condition of subtitle region detection, and reduces the possibility of influence of poor model training on prediction results.

Description

technical field [0001] The invention relates to subtitle information extraction in videos, in particular to a method for extracting video subtitles by using video semantic information. Background technique [0002] In recent years, the development of digital video technology is quite rapid, and it has gradually replaced the traditional storage and transmission mode in the field of broadcasting and television, and its application on the Internet has been expanded at an astonishing speed. Digital video has the advantages of convenient acquisition and access and large amount of information, but it also has the characteristics of large amount of data and difficult description. With the massive growth of video data, people urgently need advanced video processing technology to achieve effective video indexing, summarization, browsing and retrieval. Video subtitle information has important research and application value because it is relatively easy to extract, directly characteri...

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): H04N5/278
Inventor 刘安安宋砚庞琳李锦涛张勇东唐胜
Owner INST OF COMPUTING TECH CHINESE ACAD OF SCI
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap