Method for extracting video captions quickly and accurately

Abstract

The invention discloses a method for extracting video captions quickly and accurately, and the procedure thereof is as follows: extracting video key frame brightness images; generating a texture, projecting and positioning caption strips; confirming the initiation frame and the termination frame of the caption strips; and extracting characters. Texture diagrams of the video key frame brightness images are extracted by wavelet transform; the positions of the caption strips of the key frame images are positioned by utilizing the texture diagram projection method; the same caption of two frames are judged by the caption point match method; and the initiation frame and the termination frame of the caption strip can be quickly confirmed in the video, therefore, all the continuous frames of the caption strips can be confirmed only by invoking one localization; and the characters in the caption strips are extracted by the texture noise elimination method.

Description

technical field [0001] The invention relates to the field of multimedia video analysis, in particular to a fast and accurate method for extracting subtitles in video signals. Background technique [0002] With the rapid development of communication technology and the explosive increase of multimedia video resources, technologies such as video analysis, video retrieval, and video management have emerged. How to effectively describe the content of these video resources has become a challenging research topic. [0003] The subtitle information of the video directly describes the target object and the content of the story in the video, so that people can understand and appreciate the content of the video more intuitively, so it is a direct and effective feature to describe the content of the video. At the same time, subtitles provide a lot of important information in the video, such as names, scenes, dates, times, game scores, program introductions, etc. At this stage, the ana...

AI Technical Summary

Problems solved by technology

In the patent ZL03123473.9, "A Method for Extracting Subtitles Using Subtitle Position and Other Information" is disclosed, and the extracted results are effectively used to assist the disabled, but one limitation of this technology is the position where the subtitles appear in the screen Information sensitive, not well applied if useful information is not within the scope of the developed detection

[0011] There are at least the following defects in the prior art: the speed and performance of video extraction cannot be excellent at the same time

Images