Automatic classification of TV news articles based on telop character recognition

Author

Ariki, Y. ; Matsuura, K.

Author_Institution

Dept. of Sci. & Technol., Ryukoku Univ., Ohtsu, Japan

Volume

2

fYear

1999

fDate

36342

Firstpage

148

Abstract

The purpose of this study is to develop a multimedia database system for TV news video data. TV news video data consist of speech, characters and images. In this study, telop characters are recognized and given to the news articles as indices for classification. At first, telop frames which include telop characters are detected and then the telop characters are extracted and recognized. Through morphological analysis of the recognized telop characters, keywords are extracted which consist of more than two characters. Their keywords are used as indices to classify the TV news articles. We carried out experiments for 30 days of NHK 5 minutes news and obtained 95.4% telop character extraction rate, 81.4% character recognition rate and 83.8% article classification rate. We improved the article classification rate by 43.4% through character recognition improvement from 44.1% to 81.4%

Keywords

character recognition; image classification; multimedia databases; performance evaluation; television; video databases; TV news article classification; TV news video database; character extraction; experiments; image classification; keyword extraction; morphological analysis; multimedia database; speech processing; telop character recognition; telop frames; Character recognition; Data mining; Database systems; Digital video broadcasting; Information retrieval; Multimedia databases; Multimedia systems; Satellite broadcasting; Speech; TV;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Computing and Systems, 1999. IEEE International Conference on

Conference_Location

Florence

Print_ISBN

0-7695-0253-9

Type

conf

DOI

10.1109/MMCS.1999.778210

Filename

778210