Static text region detection in video sequences using color and orientation consistencies

Daehyun Kim, Kwanghoon Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Motion compensated error of the static text in the frame rate conversion (FRC) is most annoying artifact because people cannot read it. In this paper, we present a novel static text region detection algorithm for preventing the motion compensation error in FRC. We use some consistent properties of the static text that the color of the text is spatio-temporally consistent and the orientation of the text boundary is preserved in consecutive frames. We observe whether each pixel's consistency is preserved for several frames, and then we decide it as a static text. Our algorithm can not only perfectly extract the static text region but also easily be implemented in hardware because of its ease.

Original languageEnglish
Title of host publication2008 19th International Conference on Pattern Recognition, ICPR 2008
Publication statusPublished - 2008 Dec 1
Event2008 19th International Conference on Pattern Recognition, ICPR 2008 - Tampa, FL, United States
Duration: 2008 Dec 82008 Dec 11

Other

Other2008 19th International Conference on Pattern Recognition, ICPR 2008
CountryUnited States
CityTampa, FL
Period08/12/808/12/11

Fingerprint

Color
Motion compensation
Pixels
Hardware

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Kim, D., & Sohn, K. (2008). Static text region detection in video sequences using color and orientation consistencies. In 2008 19th International Conference on Pattern Recognition, ICPR 2008 [4761629]
Kim, Daehyun ; Sohn, Kwanghoon. / Static text region detection in video sequences using color and orientation consistencies. 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008.
@inproceedings{486aa475064c4d0a9f5a60a3d9b2e5ee,
title = "Static text region detection in video sequences using color and orientation consistencies",
abstract = "Motion compensated error of the static text in the frame rate conversion (FRC) is most annoying artifact because people cannot read it. In this paper, we present a novel static text region detection algorithm for preventing the motion compensation error in FRC. We use some consistent properties of the static text that the color of the text is spatio-temporally consistent and the orientation of the text boundary is preserved in consecutive frames. We observe whether each pixel's consistency is preserved for several frames, and then we decide it as a static text. Our algorithm can not only perfectly extract the static text region but also easily be implemented in hardware because of its ease.",
author = "Daehyun Kim and Kwanghoon Sohn",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781424421756",
booktitle = "2008 19th International Conference on Pattern Recognition, ICPR 2008",

}

Kim, D & Sohn, K 2008, Static text region detection in video sequences using color and orientation consistencies. in 2008 19th International Conference on Pattern Recognition, ICPR 2008., 4761629, 2008 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, United States, 08/12/8.

Static text region detection in video sequences using color and orientation consistencies. / Kim, Daehyun; Sohn, Kwanghoon.

2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761629.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Static text region detection in video sequences using color and orientation consistencies

AU - Kim, Daehyun

AU - Sohn, Kwanghoon

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Motion compensated error of the static text in the frame rate conversion (FRC) is most annoying artifact because people cannot read it. In this paper, we present a novel static text region detection algorithm for preventing the motion compensation error in FRC. We use some consistent properties of the static text that the color of the text is spatio-temporally consistent and the orientation of the text boundary is preserved in consecutive frames. We observe whether each pixel's consistency is preserved for several frames, and then we decide it as a static text. Our algorithm can not only perfectly extract the static text region but also easily be implemented in hardware because of its ease.

AB - Motion compensated error of the static text in the frame rate conversion (FRC) is most annoying artifact because people cannot read it. In this paper, we present a novel static text region detection algorithm for preventing the motion compensation error in FRC. We use some consistent properties of the static text that the color of the text is spatio-temporally consistent and the orientation of the text boundary is preserved in consecutive frames. We observe whether each pixel's consistency is preserved for several frames, and then we decide it as a static text. Our algorithm can not only perfectly extract the static text region but also easily be implemented in hardware because of its ease.

UR - http://www.scopus.com/inward/record.url?scp=77957940275&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957940275&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781424421756

BT - 2008 19th International Conference on Pattern Recognition, ICPR 2008

ER -

Kim D, Sohn K. Static text region detection in video sequences using color and orientation consistencies. In 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761629