Video Subtitle Refinement Method Based on Template Matching and Curve Fitting

A curve fitting and template matching technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as stroke distortion and loss

Inactive Publication Date: 2017-11-21
BEIJING INFORMATION SCI & TECH UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose an effective thinning method for video Chinese subtitles, combining the structural features of Chinese characters, extracting and redrawing the strokes of Chinese characters to achieve the effect of thinning Chinese characters, and solving the problem of other thinning algorithms for this type of object Problems such as stroke distortion and loss when thinning

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 Refinement Method Based on Template Matching and Curve Fitting
  • Video Subtitle Refinement Method Based on Template Matching and Curve Fitting
  • Video Subtitle Refinement Method Based on Template Matching and Curve Fitting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] A method for extracting video subtitles based on template matching and curve fitting provided by the present invention will be described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0065] A Chinese character image acquisition.

[0066] Use TV dramas with Chinese subtitles as input. Since China’s TV broadcasts 25 frames per second, in order to avoid too many repeated frames of subtitles, after deframing the video with FFMPEG, a frame saving operation is performed every 30 frames to extract 1000 frames. In the frame output process, save the frame as BMP format and use the formula of the following unequal weight strategy:

[0067]

[0068] Convert the image to 8-bit grayscale. In the formula, L(x,y) is the gray value of the pixel point (x,y), and R(x,y), G(x,y), and B(x,y) are the red, green, and ...

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

A video subtitle refinement method based on template matching and curve fitting relates to the field of multimedia information processing. The invention combines the structural features of Chinese characters to extract and redraw the strokes of Chinese characters, so as to achieve the effect of thinning Chinese characters, and solve the problems of stroke distortion, loss and low recognition rate caused by other thinning algorithms when thinning this type of objects The problem. The technical points of the present invention include: obtaining Chinese character images in video subtitles; determining the connected areas of Chinese character images; proposing a template matching method to extract Chinese character strokes in the same connected area; proposing to use horizontal and vertical line segments to redraw "horizontal" and "vertical" strokes, The quadratic Bezier curve redraws the strokes of "把" and "捷", and the method of redrawing the strokes of "dots" on oblique lines, so as to realize the refinement effect of Chinese character images. The invention maintains the shape and stroke structure of Chinese characters, avoids distortion; ensures the horizontal, vertical and vertical strokes and the curvature of left and right strokes, better redraws the shape of Chinese characters; and improves the recognition effect of video subtitles.

Description

technical field [0001] The invention belongs to the field of multimedia information processing, and in particular relates to a Chinese character image thinning method based on video subtitles. Background technique [0002] The rich semantic knowledge contained in video captions provides important information for multimedia retrieval. Therefore, how to automatically and effectively detect, segment, and recognize video subtitles has become a major challenge faced by academics, businesses, and political regulators. In recent years, there are many effective methods in video subtitle detection and segmentation, but it is still a research problem for low-pixel video subtitle recognition. [0003] At present, there is a mature OCR recognition technology for the recognition of Chinese characters. However, this technology can only achieve high recognition accuracy for high-resolution scanned fonts, and for low-resolution video subtitles, the recognition results are not ideal due to...

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 Patents(China)
IPC IPC(8): G06K9/20
Inventor 吕学强李钦瑞
Owner BEIJING INFORMATION SCI & TECH UNIV
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