A video indexing system using character recognition

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

doi:10.1109/ICCE.2000.854683

A video indexing system using character recognition

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

Department of Computer Science

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

7 Citations (SciVal)

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.

Original language	English
Title of host publication	Proc. IEEE International Conference on Consumer Electronics, 2000
Publisher	IEEE
Pages	358-359
Number of pages	2
ISBN (Print)	0780363019
DOIs	https://doi.org/10.1109/ICCE.2000.854683
Publication status	Published - 2000
Event	International Conference on Consumer Electronics, 2000. ICCE. 2000 Digest of Technical Papers - Los Angeles, USA United States Duration: 13 Jun 2000 → 15 Jun 2000

Conference

Conference	International Conference on Consumer Electronics, 2000. ICCE. 2000 Digest of Technical Papers
Country/Territory	USA United States
City	Los Angeles
Period	13/06/00 → 15/06/00

Access to Document

10.1109/ICCE.2000.854683

Cite this

@inproceedings{00d296c4fe5e4f8c91ce00390d4a9b94,

title = "A video indexing system using character recognition",

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.",

author = "Kim, {Eun Yi} and Kim, {Kwang In} and Keechul Jung and Kim, {Hang Joon}",

year = "2000",

doi = "10.1109/ICCE.2000.854683",

language = "English",

isbn = "0780363019 ",

pages = "358--359",

booktitle = "Proc. IEEE International Conference on Consumer Electronics, 2000",

publisher = "IEEE",

address = "USA United States",

note = "International Conference on Consumer Electronics, 2000. ICCE. 2000 Digest of Technical Papers ; Conference date: 13-06-2000 Through 15-06-2000",

}

TY - GEN

T1 - A video indexing system using character recognition

AU - Kim, Eun Yi

AU - Kim, Kwang In

AU - Jung, Keechul

AU - Kim, Hang Joon

PY - 2000

Y1 - 2000

N2 - 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.

AB - 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.

UR - http://dx.doi.org/10.1109/ICCE.2000.854683

U2 - 10.1109/ICCE.2000.854683

DO - 10.1109/ICCE.2000.854683

M3 - Chapter in a published conference proceeding

SN - 0780363019

SP - 358

EP - 359

BT - Proc. IEEE International Conference on Consumer Electronics, 2000

PB - IEEE

T2 - International Conference on Consumer Electronics, 2000. ICCE. 2000 Digest of Technical Papers

Y2 - 13 June 2000 through 15 June 2000

ER -

A video indexing system using character recognition

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this