A caption extraction method based on image segmentation and dynamic threshold

A dynamic threshold and image segmentation technology, applied in image analysis, image enhancement, image data processing, etc.

Inactive Publication Date: 2019-01-25
COMMUNICATION UNIVERSITY OF CHINA
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The technical problem mainly solved by the present invention is how to filter out the noise pixels in the video frame containing subtitles in a high-pervasive manner

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
  • A caption extraction method based on image segmentation and dynamic threshold
  • A caption extraction method based on image segmentation and dynamic threshold
  • A caption extraction method based on image segmentation and dynamic threshold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the examples provided here are only used to explain the present invention, not to limit the present invention. In addition, the embodiments provided below are some embodiments for implementing the present invention, rather than providing all embodiments for implementing the present invention. Under the premise that those skilled in the art do not pay creative work, the technical solutions of the following embodiments Embodiments obtained through recombination and other embodiments based on the implementation of the invention all belong to the protection scope of the present invention.

[0044] Such as figure 1 Shown, technical scheme of the present invention comprises seven key steps:

[0045] S1. Traversing video frames containing subtitles in a certain period of time in the video, performing contour search and de...

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 caption extraction method based on image segmentation and dynamic threshold, which comprises the following steps: S1, traversing a video frame containing captions in a certain period of time in a video, and performing contour searching and delimiting operations of an outer rectangular boundary of the contour; S2, analyzing the characteristics of the rectangular boundary and obtaining the position of the caption area; S3, taking video frames with fixed intervals, and performing image segmentation on the caption area; S4, performing grayscale processing on the segmentedgraphics, and obtaining a binary dynamic threshold value according to the pixel straight distribution of the grayscale image; S5, binarizing the image based on the dynamic threshold obtained in the preamble step, highlighting the caption pattern and eliminating noise pixel points; S6, judging according to the dynamic threshold value and the binary image, ignoring the image without subtitles, andonly performing character recognition on the image with subtitles; S7, summarizing the recognition results to remove redundancy, and writing the caption text of the entire video into the csv file according to the time sequence. The invention can effectively filter out the interference pixels except the subtitle pixels in the video frame, realize the extraction of the subtitle, and finally obtain the subtitle text file sorted according to the time.

Description

technical field [0001] The invention relates to the technical field of image processing in video, in particular to a subtitle extraction method based on image segmentation and dynamic threshold. Background technique [0002] Video is an important cultural carrier. The subtitle text in the form of subtitles in the video provides great convenience for video dissemination and understanding. At the same time, for video media such as film and television dramas, translated multilingual parallel subtitles help the international dissemination of this type of cultural products. The subtitle text in the video has extremely high value in many fields, but due to the limitation of the encoding format, the distribution format of many film and television dramas cannot achieve subtitle separation, resulting in the subtitle cannot be extracted as a separate material, which is very important for scholars. Research and atopic storage of film and television dramas provide many obstacles. [0...

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): G06K9/34G06T7/136
CPCG06T7/136G06T2207/20116G06T2207/10016G06V30/153G06V10/267
Inventor 石民勇艾莫尔夫李春芳王冬
Owner COMMUNICATION UNIVERSITY OF CHINA
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