Research on recognition method of ferrographic image wear particle based on image segmentation

Yukai Fu

doi:10.1117/12.3005799

10 October 2023 Research on recognition method of ferrographic image wear particle based on image segmentation

Yukai Fu

Proceedings Volume 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023); 127995V (2023) https://doi.org/10.1117/12.3005799
Event: 3rd International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 2023, Kuala Lumpur, Malaysia

Abstract

The recognition method of ferrographic image was studied in order to improve the accuracy, efficiency, and engineering operability of wear particle recognition in ferrographic images. The impacts of color changes and noise filtering on wear particle recognition in ferrographic images were also researched based on the collected ferrographic images after the process of wear particle recognition in ferrographic images was analyzed. Then each respectively, the Otsu segmentation, region growing segmentation algorithm (RGSA), iterative segmentation, and K-means clustering algorithm were used for wear particle recognition in ferrographic images. The results show that the K-means clustering method used to segment complex images can preserve detailed features to the utmost extent, eliminate noise points correctly, and is more beneficial for subsequent edge feature extraction.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yukai Fu "Research on recognition method of ferrographic image wear particle based on image segmentation", Proc. SPIE 12799, Third International Conference on Advanced Algorithms and Signal Image Processing (AASIP 2023), 127995V (10 October 2023); https://doi.org/10.1117/12.3005799

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available