Feature extraction method based on cascade noise elimination for sketch recognition

Junyeong Yang, Hyeran Byun

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

Abstract

Freehand sketching is a very efficient means for us to communicate each other. As Table PC is widely popularized, the research about sketch recognition became one of important research issue. To recognize sketch, the feature point should be extracted and then each feature point is analyzed as line or curve. However, most of feature extraction algorithms suffers from noise which is occurred from the bad drawing sketch. In this paper, we propose the feature extraction algorithm robust to noise. The proposed algorithm consists of three cascade steps: candidate feature point extraction, noise reduction, and hook elimination. At the candidate feature point extraction step, the feature points is selected among input points. Then, in second step, we reduce the noise which is occurred from the previous step by using noise reduction rule based on inner product between two neighbor vectors. Finally, the hook, which can not be eliminated from two previous steps, is eliminated by the proposed hook elimination method. The experimental result shows that the average approximation error is less than 1 about 1004 line-curve hybrid shapes, and the proposed algorithm is the good feature methods.

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

Feature extraction
Hooks
Noise abatement

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition

Cite this

Yang, J., & Byun, H. (2008). Feature extraction method based on cascade noise elimination for sketch recognition. In 2008 19th International Conference on Pattern Recognition, ICPR 2008 [4761630]
Yang, Junyeong ; Byun, Hyeran. / Feature extraction method based on cascade noise elimination for sketch recognition. 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008.
@inproceedings{ebcecbf13fbd47ab9c1f8e5ed4e21f9c,
title = "Feature extraction method based on cascade noise elimination for sketch recognition",
abstract = "Freehand sketching is a very efficient means for us to communicate each other. As Table PC is widely popularized, the research about sketch recognition became one of important research issue. To recognize sketch, the feature point should be extracted and then each feature point is analyzed as line or curve. However, most of feature extraction algorithms suffers from noise which is occurred from the bad drawing sketch. In this paper, we propose the feature extraction algorithm robust to noise. The proposed algorithm consists of three cascade steps: candidate feature point extraction, noise reduction, and hook elimination. At the candidate feature point extraction step, the feature points is selected among input points. Then, in second step, we reduce the noise which is occurred from the previous step by using noise reduction rule based on inner product between two neighbor vectors. Finally, the hook, which can not be eliminated from two previous steps, is eliminated by the proposed hook elimination method. The experimental result shows that the average approximation error is less than 1 about 1004 line-curve hybrid shapes, and the proposed algorithm is the good feature methods.",
author = "Junyeong Yang and Hyeran Byun",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781424421756",
booktitle = "2008 19th International Conference on Pattern Recognition, ICPR 2008",

}

Yang, J & Byun, H 2008, Feature extraction method based on cascade noise elimination for sketch recognition. in 2008 19th International Conference on Pattern Recognition, ICPR 2008., 4761630, 2008 19th International Conference on Pattern Recognition, ICPR 2008, Tampa, FL, United States, 08/12/8.

Feature extraction method based on cascade noise elimination for sketch recognition. / Yang, Junyeong; Byun, Hyeran.

2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761630.

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

TY - GEN

T1 - Feature extraction method based on cascade noise elimination for sketch recognition

AU - Yang, Junyeong

AU - Byun, Hyeran

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Freehand sketching is a very efficient means for us to communicate each other. As Table PC is widely popularized, the research about sketch recognition became one of important research issue. To recognize sketch, the feature point should be extracted and then each feature point is analyzed as line or curve. However, most of feature extraction algorithms suffers from noise which is occurred from the bad drawing sketch. In this paper, we propose the feature extraction algorithm robust to noise. The proposed algorithm consists of three cascade steps: candidate feature point extraction, noise reduction, and hook elimination. At the candidate feature point extraction step, the feature points is selected among input points. Then, in second step, we reduce the noise which is occurred from the previous step by using noise reduction rule based on inner product between two neighbor vectors. Finally, the hook, which can not be eliminated from two previous steps, is eliminated by the proposed hook elimination method. The experimental result shows that the average approximation error is less than 1 about 1004 line-curve hybrid shapes, and the proposed algorithm is the good feature methods.

AB - Freehand sketching is a very efficient means for us to communicate each other. As Table PC is widely popularized, the research about sketch recognition became one of important research issue. To recognize sketch, the feature point should be extracted and then each feature point is analyzed as line or curve. However, most of feature extraction algorithms suffers from noise which is occurred from the bad drawing sketch. In this paper, we propose the feature extraction algorithm robust to noise. The proposed algorithm consists of three cascade steps: candidate feature point extraction, noise reduction, and hook elimination. At the candidate feature point extraction step, the feature points is selected among input points. Then, in second step, we reduce the noise which is occurred from the previous step by using noise reduction rule based on inner product between two neighbor vectors. Finally, the hook, which can not be eliminated from two previous steps, is eliminated by the proposed hook elimination method. The experimental result shows that the average approximation error is less than 1 about 1004 line-curve hybrid shapes, and the proposed algorithm is the good feature methods.

UR - http://www.scopus.com/inward/record.url?scp=77957942589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957942589&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77957942589

SN - 9781424421756

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

ER -

Yang J, Byun H. Feature extraction method based on cascade noise elimination for sketch recognition. In 2008 19th International Conference on Pattern Recognition, ICPR 2008. 2008. 4761630