A video indexing system using character recognition

Author

Eun Yi Kim ; Kwang In Kim ; Keechul Jung ; Hang Joon Kim

Author_Institution

Dept. of Comput. Eng., Kyungpook Nat. Univ., Taegu, South Korea

fYear

2000

fDate

13-15 June 2000

Firstpage

358

Lastpage

359

Abstract

We design and implement a video indexing system. For automatic indexing of video images, character recognition information is utilized. The proposed system consists of three components: keyframe extraction, text extraction, and text recognition. It extracts text regions using a neural network that operates as a set of texture discrimination filters, and performing profile analysis with some heuristics. To ensure accurate segmentation of touching characters, character segmentation and recognition are performed in turn. The proposed system has been tested with 390 Korean news archives.

Keywords

character recognition; database indexing; feature extraction; image segmentation; image texture; neural net architecture; video databases; Korean news archives; automatic indexing; backpropagation algorithm; character recognition; character segmentation; heuristics; keyframe extraction; neural network; neural network architecture; profile analysis; text extraction; text recognition; text region extraction; texture discrimination filters; video images; video indexing system; Character recognition; Data mining; Filters; Image segmentation; Image texture analysis; Machine assisted indexing; Neural networks; Performance analysis; System testing; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Consumer Electronics, 2000. ICCE. 2000 Digest of Technical Papers. International Conference on

Conference_Location

Los Angles, CA, USA

Print_ISBN

0-7803-6301-9

Type

conf

DOI

10.1109/ICCE.2000.854683

Filename

854683