A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile

Zhe Liu; Ying Weng; Yiming Zhang

doi:10.1007/978-3-031-92805-5_13

A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile

Zhe Liu, Ying Weng, Yiming Zhang

School of Computer Science

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

Magnetic grains are the crucial constituent of Nd-Fe-B magnet in electric vehicle (EV) driven motor. Hot-deformed manufacturing process is taken to enhance the coercivity of Nd-Fe-B magnet and enable it to reach the higher heat resistance of EV driven motor. The evaluation of specific parameters pertaining to the hot-deformed manufacturing process relies on the analysis of magnetic grain profiles. However, the current analysis procedure encompassing profile extraction, is conducted manually. To meet this challenge, we design and develop a computer vision system to assist the extraction of magnetic grain profile by incorporating the resolution-enhancing preprocess and refining the existing edge detection step. To evaluate the performance of our proposed computer vision system, a series of experiments have been conducted to validate the result completeness, assess the time consumption, and compare the prevailing methods of similar properties. The comprehensive appraisal demonstrates that the accuracy and processing time of our proposed computer vision system align with the desired industrial requirements.

Original language	English
Title of host publication	Computer Vision – ECCV 2024 Workshops, Proceedings
Editors	Alessio Del Bue, Cristian Canton, Jordi Pont-Tuset, Tatiana Tommasi
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	197-210
Number of pages	14
ISBN (Print)	9783031928048
DOIs	https://doi.org/10.1007/978-3-031-92805-5_13
Publication status	Published - 2025
Event	Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024 - Milan, Italy Duration: 29 Sept 2024 → 4 Oct 2024

Publication series

Name	Lecture Notes in Computer Science
Volume	15626 LNCS
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024
Country/Territory	Italy
City	Milan
Period	29/09/24 → 4/10/24

Keywords

Automated Edge Detection
Computer Vision
Magnetic Grain Profile

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-031-92805-5_13

Cite this

Liu, Z., Weng, Y., & Zhang, Y. (2025). A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision – ECCV 2024 Workshops, Proceedings (pp. 197-210). (Lecture Notes in Computer Science; Vol. 15626 LNCS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-92805-5_13

@inproceedings{295cae4ba52b43e0bb83468c0bc99e61,

title = "A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile",

abstract = "Magnetic grains are the crucial constituent of Nd-Fe-B magnet in electric vehicle (EV) driven motor. Hot-deformed manufacturing process is taken to enhance the coercivity of Nd-Fe-B magnet and enable it to reach the higher heat resistance of EV driven motor. The evaluation of specific parameters pertaining to the hot-deformed manufacturing process relies on the analysis of magnetic grain profiles. However, the current analysis procedure encompassing profile extraction, is conducted manually. To meet this challenge, we design and develop a computer vision system to assist the extraction of magnetic grain profile by incorporating the resolution-enhancing preprocess and refining the existing edge detection step. To evaluate the performance of our proposed computer vision system, a series of experiments have been conducted to validate the result completeness, assess the time consumption, and compare the prevailing methods of similar properties. The comprehensive appraisal demonstrates that the accuracy and processing time of our proposed computer vision system align with the desired industrial requirements.",

keywords = "Automated Edge Detection, Computer Vision, Magnetic Grain Profile",

author = "Zhe Liu and Ying Weng and Yiming Zhang",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024 ; Conference date: 29-09-2024 Through 04-10-2024",

year = "2025",

doi = "10.1007/978-3-031-92805-5\_13",

language = "English",

isbn = "9783031928048",

series = "Lecture Notes in Computer Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "197--210",

editor = "\{Del Bue\}, Alessio and Cristian Canton and Jordi Pont-Tuset and Tatiana Tommasi",

booktitle = "Computer Vision – ECCV 2024 Workshops, Proceedings",

address = "Germany",

}

Liu, Z, Weng, Y & Zhang, Y 2025, A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile. in A Del Bue, C Canton, J Pont-Tuset & T Tommasi (eds), Computer Vision – ECCV 2024 Workshops, Proceedings. Lecture Notes in Computer Science, vol. 15626 LNCS, Springer Science and Business Media Deutschland GmbH, pp. 197-210, Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024, Milan, Italy, 29/09/24. https://doi.org/10.1007/978-3-031-92805-5_13

A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile. / Liu, Zhe; Weng, Ying; Zhang, Yiming.
Computer Vision – ECCV 2024 Workshops, Proceedings. ed. / Alessio Del Bue; Cristian Canton; Jordi Pont-Tuset; Tatiana Tommasi. Springer Science and Business Media Deutschland GmbH, 2025. p. 197-210 (Lecture Notes in Computer Science; Vol. 15626 LNCS).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Computer Vision System for Automatic Edge Detection of Magnetic Grain Profile

AU - Liu, Zhe

AU - Weng, Ying

AU - Zhang, Yiming

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

PY - 2025

Y1 - 2025

N2 - Magnetic grains are the crucial constituent of Nd-Fe-B magnet in electric vehicle (EV) driven motor. Hot-deformed manufacturing process is taken to enhance the coercivity of Nd-Fe-B magnet and enable it to reach the higher heat resistance of EV driven motor. The evaluation of specific parameters pertaining to the hot-deformed manufacturing process relies on the analysis of magnetic grain profiles. However, the current analysis procedure encompassing profile extraction, is conducted manually. To meet this challenge, we design and develop a computer vision system to assist the extraction of magnetic grain profile by incorporating the resolution-enhancing preprocess and refining the existing edge detection step. To evaluate the performance of our proposed computer vision system, a series of experiments have been conducted to validate the result completeness, assess the time consumption, and compare the prevailing methods of similar properties. The comprehensive appraisal demonstrates that the accuracy and processing time of our proposed computer vision system align with the desired industrial requirements.

AB - Magnetic grains are the crucial constituent of Nd-Fe-B magnet in electric vehicle (EV) driven motor. Hot-deformed manufacturing process is taken to enhance the coercivity of Nd-Fe-B magnet and enable it to reach the higher heat resistance of EV driven motor. The evaluation of specific parameters pertaining to the hot-deformed manufacturing process relies on the analysis of magnetic grain profiles. However, the current analysis procedure encompassing profile extraction, is conducted manually. To meet this challenge, we design and develop a computer vision system to assist the extraction of magnetic grain profile by incorporating the resolution-enhancing preprocess and refining the existing edge detection step. To evaluate the performance of our proposed computer vision system, a series of experiments have been conducted to validate the result completeness, assess the time consumption, and compare the prevailing methods of similar properties. The comprehensive appraisal demonstrates that the accuracy and processing time of our proposed computer vision system align with the desired industrial requirements.

KW - Automated Edge Detection

KW - Computer Vision

KW - Magnetic Grain Profile

UR - http://www.scopus.com/inward/record.url?scp=105006898584&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-92805-5_13

DO - 10.1007/978-3-031-92805-5_13

M3 - Conference contribution

AN - SCOPUS:105006898584

SN - 9783031928048

T3 - Lecture Notes in Computer Science

SP - 197

EP - 210

BT - Computer Vision – ECCV 2024 Workshops, Proceedings

A2 - Del Bue, Alessio

A2 - Canton, Cristian

A2 - Pont-Tuset, Jordi

A2 - Tommasi, Tatiana

PB - Springer Science and Business Media Deutschland GmbH

T2 - Workshops that were held in conjunction with the 18th European Conference on Computer Vision, ECCV 2024

Y2 - 29 September 2024 through 4 October 2024

ER -