Method for indexing TV news by utilizing computer system

Abstract

The invention discloses a method for indexing TV news, which introduces artificial intelligence method such as speech recognition, image recognition, and the like into traditional TV news indexing work. The method comprises the following steps: (1) video capture and video segmentation; (2) video preprocessing; (3) continuous speech recognition; (4) image and text recognition; (5) text error correction and word segmentation; and (6) human-supervised proofreading. The method redefines the indexing process and indexing mode of TV new programs and solves the problems of low working efficiency, insufficient indexing and information mining, and the like.

Description

technical field [0001] The invention relates to a method for intelligent indexing of TV news by using a computer system, which introduces artificial intelligence methods such as voice recognition and image recognition into traditional TV news indexing work. Background technique [0002] TV stations produce a large number of TV news video programs every day, and these video programs will enter the media asset management system. The traditional media asset management system can manually classify and catalog these video programs, add titles and subscripts, define keywords or tags, so that Make these video programs orderly and retrievable. The traditional indexing method of TV news programs usually adopts the following steps: first, collect video programs, and convert various TV program signal acquisitions into digital video files; after collection, manual pre-processing is used; and then imported into the media asset system And perform certain automatic processing; after stora...

AI Technical Summary

Problems solved by technology

[0003] But this traditional method has the following problems: (1) manual operation is inefficient; (2) there is no corresponding relationship between video frames and manuscripts, keywords or tags; (3) the defined keywords or tags are not sufficient; (4) Fine-grained retrieval to the frame level, insufficient information mining

Due to these problems, the TV station needs a large number of editors to complete complicated manual operations, which is not only low in efficiency, but also low in accuracy

More importantly, the traditional manual method cannot realize the analysis of video frames and voice, so that fine-grained retrieval cannot be achieved, resulting in a large amount of information being lost in storage, causing great waste, and making these news video programs unavailable Take advantage of

Under the traditional method, the utilization rate of video is low, and it is far from being able to display the amount of information of video programs, which greatly reduces the degree of freedom of program retrieval, the richness of information, and the reuse value of programs.

Images