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

Video image character detecting method based on sparse expression

A video image and text detection technology, applied in image communication, TV, color TV, etc., can solve the problems of low accuracy, low efficiency, complex calculation, etc., achieve high recall rate and accuracy rate, and improve the effect of accuracy

Inactive Publication Date: 2010-09-15
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF2 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Due to the different sizes of text in the video, and various font types and colors, the traditional method has limitations such as low efficiency, complex calculation, and low accuracy.

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 image character detecting method based on sparse expression
  • Video image character detecting method based on sparse expression
  • Video image character detecting method based on sparse expression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0013] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0014] Such as figure 1 As shown, a kind of thick-to-fine video image text detection method based on sparse expression of the present invention specifically comprises the following steps:

[0015] 1. Video sequence preprocessing.

[0016] (1) Video sequence resampling:

[0017] According to statistics, the text in the video image appears in at least dozens of consecutive frames of images. Since the difference between two adjacent frames of images is very small, when the same algorithm is used for processing, the results obtained will be very similar. In this case, it would be computationally inefficient to process all frames independently. Therefore, on the basis of ensuring the accuracy and high performance of text detection and extraction, we resample the video sequence and take one frame of image every 10 frames, which can impr...

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 video image character detecting method based on sparse expression, which comprises the following steps of: S1, resampling a video sequence to obtain a color video image, and converting the gray level and the multi-scale of the color video image to obtain a multi-scale gray level image; S2, performing edge detection and morphological closed operation to the multi-scale gray level image with an improved Sobel operator to obtain an edge image and filter the edge density of the edge image; obtaining a candidate character region through connected domain analysis and regular analysis; and S3, performing vertical projection and horizontal projection to the candidate character region, diving a vertical projecting image and a horizontal projecting image to obtain candidate character lines, dividing the candidate character lines into small regions through sliding windows, extracting the edge characteristics of the small regions, respectively classifying each small region with a classifying method based on the sparse expression, judging whether the small regions are character regions, judging the candidate character lines according to the judging result of the small regions to obtain and output a final character line region.

Description

technical field [0001] The invention belongs to the category of image understanding and image retrieval, and in particular relates to a fast and accurate video text detection method and system implementation. Background technique [0002] With the rapid development of multimedia technology and the Internet, the amount of multimedia information is growing explosively. More and more databases include video information in addition to image and text information. Video information is the most common type of multimedia information, and it can be obtained in many ways, such as TV and the Internet. How to retrieve the concerned information from a large amount of video information has aroused the interest of scholars at home and abroad. In video understanding and retrieval, text can provide very rich semantic information for video, which is a very important component. For example, text titles in news programs, game scores in sports programs, names of commodities and manufacturers ...

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): G06K9/32H04N5/445
Inventor 王春恒李心洁程刚张荣国张阳肖柏华
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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