2D template matching for automated inspection using generalized hough transform

Junwon Mun; Jaeseok Kim

doi:10.1109/SCORED.2017.8305439

2D template matching for automated inspection using generalized hough transform

Junwon Mun, Jaeseok Kim

Department of Electrical and Electronic Engineering

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

1 Citation (Scopus)

Abstract

In this paper, we modify GHT to reduce its memory requirement and computational cost and improve its performance under rigid motion. In the proposed algorithm, orientation and displacement are determined separately using a multi-stage scheme, and the displacement accumulator-which occupies most of the memory-is downsampled without degrading detection resolution. Moreover, the template pose becomes more reliable by using an adaptive weight scheme when incrementing. Experimental results show that the proposed scheme has advantages in both computational complexity and memory requirement over conventional GHT, and pose determination is more stable.

Original language	English
Title of host publication	IEEE Student Conference on Research and Development
Subtitle of host publication	Inspiring Technology for Humanity, SCOReD 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	461-466
Number of pages	6
ISBN (Electronic)	9781538621264
DOIs	https://doi.org/10.1109/SCORED.2017.8305439
Publication status	Published - 2018 Feb 28
Event	15th IEEE Student Conference on Research and Development, SCOReD 2017 - Putrajaya, Malaysia Duration: 2017 Dec 13 → 2017 Dec 14

Publication series

Name	IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings
Volume	2018-January

Conference

Conference	15th IEEE Student Conference on Research and Development, SCOReD 2017
Country/Territory	Malaysia
City	Putrajaya
Period	17/12/13 → 17/12/14

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This material is based upon work supported by the Ministry of Trade, Industry & Energy(MOTIE, Korea) under Industrial Technology Innovation Program(10080619).

Publisher Copyright:
© 2017 IEEE.

All Science Journal Classification (ASJC) codes

Energy Engineering and Power Technology
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Electronic, Optical and Magnetic Materials
Instrumentation

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SCORED.2017.8305439

Cite this

Mun, J., & Kim, J. (2018). 2D template matching for automated inspection using generalized hough transform. In IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings (pp. 461-466). (IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SCORED.2017.8305439

Mun, Junwon ; Kim, Jaeseok. / 2D template matching for automated inspection using generalized hough transform. IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 461-466 (IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings).

@inproceedings{48399ae8dd5a4dd1ae0a41985b1ddad0,

title = "2D template matching for automated inspection using generalized hough transform",

abstract = "In this paper, we modify GHT to reduce its memory requirement and computational cost and improve its performance under rigid motion. In the proposed algorithm, orientation and displacement are determined separately using a multi-stage scheme, and the displacement accumulator-which occupies most of the memory-is downsampled without degrading detection resolution. Moreover, the template pose becomes more reliable by using an adaptive weight scheme when incrementing. Experimental results show that the proposed scheme has advantages in both computational complexity and memory requirement over conventional GHT, and pose determination is more stable.",

author = "Junwon Mun and Jaeseok Kim",

note = "Funding Information: ACKNOWLEDGMENT This material is based upon work supported by the Ministry of Trade, Industry & Energy(MOTIE, Korea) under Industrial Technology Innovation Program(10080619). Publisher Copyright: {\textcopyright} 2017 IEEE.; 15th IEEE Student Conference on Research and Development, SCOReD 2017 ; Conference date: 13-12-2017 Through 14-12-2017",

year = "2018",

month = feb,

day = "28",

doi = "10.1109/SCORED.2017.8305439",

language = "English",

series = "IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings",

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

pages = "461--466",

booktitle = "IEEE Student Conference on Research and Development",

address = "United States",

}

Mun, J & Kim, J 2018, 2D template matching for automated inspection using generalized hough transform. in IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings. IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 461-466, 15th IEEE Student Conference on Research and Development, SCOReD 2017, Putrajaya, Malaysia, 17/12/13. https://doi.org/10.1109/SCORED.2017.8305439

2D template matching for automated inspection using generalized hough transform. / Mun, Junwon; Kim, Jaeseok.
IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 461-466 (IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings; Vol. 2018-January).

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

TY - GEN

T1 - 2D template matching for automated inspection using generalized hough transform

AU - Mun, Junwon

AU - Kim, Jaeseok

N1 - Funding Information: ACKNOWLEDGMENT This material is based upon work supported by the Ministry of Trade, Industry & Energy(MOTIE, Korea) under Industrial Technology Innovation Program(10080619). Publisher Copyright: © 2017 IEEE.

PY - 2018/2/28

Y1 - 2018/2/28

N2 - In this paper, we modify GHT to reduce its memory requirement and computational cost and improve its performance under rigid motion. In the proposed algorithm, orientation and displacement are determined separately using a multi-stage scheme, and the displacement accumulator-which occupies most of the memory-is downsampled without degrading detection resolution. Moreover, the template pose becomes more reliable by using an adaptive weight scheme when incrementing. Experimental results show that the proposed scheme has advantages in both computational complexity and memory requirement over conventional GHT, and pose determination is more stable.

AB - In this paper, we modify GHT to reduce its memory requirement and computational cost and improve its performance under rigid motion. In the proposed algorithm, orientation and displacement are determined separately using a multi-stage scheme, and the displacement accumulator-which occupies most of the memory-is downsampled without degrading detection resolution. Moreover, the template pose becomes more reliable by using an adaptive weight scheme when incrementing. Experimental results show that the proposed scheme has advantages in both computational complexity and memory requirement over conventional GHT, and pose determination is more stable.

UR - http://www.scopus.com/inward/record.url?scp=85048900571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048900571&partnerID=8YFLogxK

U2 - 10.1109/SCORED.2017.8305439

DO - 10.1109/SCORED.2017.8305439

M3 - Conference contribution

AN - SCOPUS:85048900571

T3 - IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings

SP - 461

EP - 466

BT - IEEE Student Conference on Research and Development

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th IEEE Student Conference on Research and Development, SCOReD 2017

Y2 - 13 December 2017 through 14 December 2017

ER -

Mun J, Kim J. 2D template matching for automated inspection using generalized hough transform. In IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 461-466. (IEEE Student Conference on Research and Development: Inspiring Technology for Humanity, SCOReD 2017 - Proceedings). doi: 10.1109/SCORED.2017.8305439

2D template matching for automated inspection using generalized hough transform

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this