Block-based connected component labeling algorithm with block prediction

Yunseok Jang; Junwon Mun; Kyoungmook Oh; Jaeseok Kim

doi:10.1109/TSP.2017.8076053

Block-based connected component labeling algorithm with block prediction

Yunseok Jang, Junwon Mun, Kyoungmook Oh, Jaeseok Kim

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

In this paper, we propose a block-based connected component labeling algorithm, which predicts current block’s label by exploiting the information obtained from previous block to reduce memory access. By generating a forest of decision trees according to some of previous block’s pixels, which are also needed for current block’s label decision, we can reduce trees’ depth and number of pixels to check. Experimental results show that our method is faster than the most recent labeling algorithms with image datasets which have various size and pixel density.

Original language	English
Title of host publication	2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017
Editors	Norbert Herencsar
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	578-581
Number of pages	4
ISBN (Electronic)	9781509039821
DOIs	https://doi.org/10.1109/TSP.2017.8076053
Publication status	Published - 2017 Oct 19
Event	40th International Conference on Telecommunications and Signal Processing, TSP 2017 - Barcelona, Spain Duration: 2017 Jul 5 → 2017 Jul 7

Publication series

Name	2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017
Volume	2017-January

Conference

Conference	40th International Conference on Telecommunications and Signal Processing, TSP 2017
Country/Territory	Spain
City	Barcelona
Period	17/7/5 → 17/7/7

Bibliographical note

Funding Information:
This work was supported by the Technological Innovation R&D Program (S2342832) funded by the Small and Medium Business Administration(SMBA, Korea)

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Signal Processing

Access to Document

10.1109/TSP.2017.8076053

Cite this

Jang, Y., Mun, J., Oh, K., & Kim, J. (2017). Block-based connected component labeling algorithm with block prediction. In N. Herencsar (Ed.), 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017 (pp. 578-581). (2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/TSP.2017.8076053

Jang, Yunseok ; Mun, Junwon ; Oh, Kyoungmook et al. / Block-based connected component labeling algorithm with block prediction. 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017. editor / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 578-581 (2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017).

@inproceedings{1c2c90941ea84f8e8b97dff5a80dddd0,

title = "Block-based connected component labeling algorithm with block prediction",

abstract = "In this paper, we propose a block-based connected component labeling algorithm, which predicts current block{\textquoteright}s label by exploiting the information obtained from previous block to reduce memory access. By generating a forest of decision trees according to some of previous block{\textquoteright}s pixels, which are also needed for current block{\textquoteright}s label decision, we can reduce trees{\textquoteright} depth and number of pixels to check. Experimental results show that our method is faster than the most recent labeling algorithms with image datasets which have various size and pixel density.",

author = "Yunseok Jang and Junwon Mun and Kyoungmook Oh and Jaeseok Kim",

note = "Funding Information: This work was supported by the Technological Innovation R&D Program (S2342832) funded by the Small and Medium Business Administration(SMBA, Korea) Publisher Copyright: {\textcopyright} 2017 IEEE.; 40th International Conference on Telecommunications and Signal Processing, TSP 2017 ; Conference date: 05-07-2017 Through 07-07-2017",

year = "2017",

month = oct,

day = "19",

doi = "10.1109/TSP.2017.8076053",

language = "English",

series = "2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "578--581",

editor = "Norbert Herencsar",

booktitle = "2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017",

address = "United States",

}

Jang, Y, Mun, J, Oh, K & Kim, J 2017, Block-based connected component labeling algorithm with block prediction. in N Herencsar (ed.), 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017. 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 578-581, 40th International Conference on Telecommunications and Signal Processing, TSP 2017, Barcelona, Spain, 17/7/5. https://doi.org/10.1109/TSP.2017.8076053

Block-based connected component labeling algorithm with block prediction. / Jang, Yunseok; Mun, Junwon; Oh, Kyoungmook et al.
2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017. ed. / Norbert Herencsar. Institute of Electrical and Electronics Engineers Inc., 2017. p. 578-581 (2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017; Vol. 2017-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Block-based connected component labeling algorithm with block prediction

AU - Jang, Yunseok

AU - Mun, Junwon

AU - Oh, Kyoungmook

AU - Kim, Jaeseok

N1 - Funding Information: This work was supported by the Technological Innovation R&D Program (S2342832) funded by the Small and Medium Business Administration(SMBA, Korea) Publisher Copyright: © 2017 IEEE.

PY - 2017/10/19

Y1 - 2017/10/19

N2 - In this paper, we propose a block-based connected component labeling algorithm, which predicts current block’s label by exploiting the information obtained from previous block to reduce memory access. By generating a forest of decision trees according to some of previous block’s pixels, which are also needed for current block’s label decision, we can reduce trees’ depth and number of pixels to check. Experimental results show that our method is faster than the most recent labeling algorithms with image datasets which have various size and pixel density.

AB - In this paper, we propose a block-based connected component labeling algorithm, which predicts current block’s label by exploiting the information obtained from previous block to reduce memory access. By generating a forest of decision trees according to some of previous block’s pixels, which are also needed for current block’s label decision, we can reduce trees’ depth and number of pixels to check. Experimental results show that our method is faster than the most recent labeling algorithms with image datasets which have various size and pixel density.

UR - http://www.scopus.com/inward/record.url?scp=85043256428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043256428&partnerID=8YFLogxK

U2 - 10.1109/TSP.2017.8076053

DO - 10.1109/TSP.2017.8076053

M3 - Conference contribution

AN - SCOPUS:85043256428

T3 - 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017

SP - 578

EP - 581

BT - 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017

A2 - Herencsar, Norbert

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 40th International Conference on Telecommunications and Signal Processing, TSP 2017

Y2 - 5 July 2017 through 7 July 2017

ER -

Jang Y, Mun J, Oh K, Kim J. Block-based connected component labeling algorithm with block prediction. In Herencsar N, editor, 2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 578-581. (2017 40th International Conference on Telecommunications and Signal Processing, TSP 2017). doi: 10.1109/TSP.2017.8076053

Block-based connected component labeling algorithm with block prediction

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this