Improved simple linear iterative clustering superpixels

Kwang Shik Kim, Dongni Zhang, Mun Cheon Kang, Sung-Jea Ko

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

15 Citations (Scopus)

Abstract

The superpixels are small regions in an image which do not contain edges inside. Among all the superpixel algorithms, the simple linear iterative clustering (SLIC) method is widely adopted due to its practicality. However, the resultant superpixels sometimes do not well adhere to the edges. In this paper, we present an improved SLIC superpixel method to solve this problem. Experiments show that the proposed method produces superpixels whose boundaries better adhere to the image edges without significantly increasing the processing time compared with the conventional method.

Original languageEnglish
Title of host publicationProceedings of the International Symposium on Consumer Electronics, ISCE
Pages259-260
Number of pages2
DOIs
Publication statusPublished - 2013 Sep 11
Event2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013 - Hsinchu, Taiwan, Province of China
Duration: 2013 Jun 32013 Jun 6

Other

Other2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013
CountryTaiwan, Province of China
CityHsinchu
Period13/6/313/6/6

Fingerprint

Processing
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Kim, K. S., Zhang, D., Kang, M. C., & Ko, S-J. (2013). Improved simple linear iterative clustering superpixels. In Proceedings of the International Symposium on Consumer Electronics, ISCE (pp. 259-260). [6570216] https://doi.org/10.1109/ISCE.2013.6570216

Improved simple linear iterative clustering superpixels. / Kim, Kwang Shik; Zhang, Dongni; Kang, Mun Cheon; Ko, Sung-Jea.

Proceedings of the International Symposium on Consumer Electronics, ISCE. 2013. p. 259-260 6570216.

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

Kim, KS, Zhang, D, Kang, MC & Ko, S-J 2013, Improved simple linear iterative clustering superpixels. in Proceedings of the International Symposium on Consumer Electronics, ISCE., 6570216, pp. 259-260, 2013 IEEE 17th International Symposium on Consumer Electronics, ISCE 2013, Hsinchu, Taiwan, Province of China, 13/6/3. https://doi.org/10.1109/ISCE.2013.6570216
Kim KS, Zhang D, Kang MC, Ko S-J. Improved simple linear iterative clustering superpixels. In Proceedings of the International Symposium on Consumer Electronics, ISCE. 2013. p. 259-260. 6570216 https://doi.org/10.1109/ISCE.2013.6570216
Kim, Kwang Shik ; Zhang, Dongni ; Kang, Mun Cheon ; Ko, Sung-Jea. / Improved simple linear iterative clustering superpixels. Proceedings of the International Symposium on Consumer Electronics, ISCE. 2013. pp. 259-260
@inproceedings{74fe621e73f54c59908a8de961bd730a,
title = "Improved simple linear iterative clustering superpixels",
abstract = "The superpixels are small regions in an image which do not contain edges inside. Among all the superpixel algorithms, the simple linear iterative clustering (SLIC) method is widely adopted due to its practicality. However, the resultant superpixels sometimes do not well adhere to the edges. In this paper, we present an improved SLIC superpixel method to solve this problem. Experiments show that the proposed method produces superpixels whose boundaries better adhere to the image edges without significantly increasing the processing time compared with the conventional method.",
author = "Kim, {Kwang Shik} and Dongni Zhang and Kang, {Mun Cheon} and Sung-Jea Ko",
year = "2013",
month = "9",
day = "11",
doi = "10.1109/ISCE.2013.6570216",
language = "English",
isbn = "9781467361996",
pages = "259--260",
booktitle = "Proceedings of the International Symposium on Consumer Electronics, ISCE",

}

TY - GEN

T1 - Improved simple linear iterative clustering superpixels

AU - Kim, Kwang Shik

AU - Zhang, Dongni

AU - Kang, Mun Cheon

AU - Ko, Sung-Jea

PY - 2013/9/11

Y1 - 2013/9/11

N2 - The superpixels are small regions in an image which do not contain edges inside. Among all the superpixel algorithms, the simple linear iterative clustering (SLIC) method is widely adopted due to its practicality. However, the resultant superpixels sometimes do not well adhere to the edges. In this paper, we present an improved SLIC superpixel method to solve this problem. Experiments show that the proposed method produces superpixels whose boundaries better adhere to the image edges without significantly increasing the processing time compared with the conventional method.

AB - The superpixels are small regions in an image which do not contain edges inside. Among all the superpixel algorithms, the simple linear iterative clustering (SLIC) method is widely adopted due to its practicality. However, the resultant superpixels sometimes do not well adhere to the edges. In this paper, we present an improved SLIC superpixel method to solve this problem. Experiments show that the proposed method produces superpixels whose boundaries better adhere to the image edges without significantly increasing the processing time compared with the conventional method.

UR - http://www.scopus.com/inward/record.url?scp=84883498707&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883498707&partnerID=8YFLogxK

U2 - 10.1109/ISCE.2013.6570216

DO - 10.1109/ISCE.2013.6570216

M3 - Conference contribution

AN - SCOPUS:84883498707

SN - 9781467361996

SP - 259

EP - 260

BT - Proceedings of the International Symposium on Consumer Electronics, ISCE

ER -