New method for detecting surface defects of the rotational parts in remanufacturing service

DOI

10.2991/icmmct-17.2017.146How to use a DOI?

Keywords

remanufacturing service, surface defect, two-dimensional reciprocal cross entropy, image segmentation

Abstract

Remanufacturing is an important path to realize the sustainable development on modern industry. Defect detection is considered one of the most scientific and developed services in remanufacturing. Aiming to find surface defects of the rotational parts rapidly and accurately in the process of remanufacturing service, a new method based on improved two-dimensional reciprocal cross entropy is proposed in this paper. By using the adaptive morphological filtering, the 2D histogram is established, which enhances the anti-noise performance of the method. To accelarate the running time, the 2D reciprocal cross entropy threshold selection criterion function is decomposed into two independent 1D threshold selection criterion functions, then, the threshold determined by these two functions are jointed together to achieve the desired. Finally, through a case study of rollers, compared with one dimensional maximum entropy method, two-dimensional Otsu method and two-dimensional maximum entropy method, the practicability and effectiveness of the method is verified.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiang Liu
AU  - Xuhui Xia
AU  - Lei Wang
PY  - 2017/04
DA  - 2017/04
TI  - New method for detecting surface defects of the rotational parts in remanufacturing service
BT  - Proceedings of the 2017 5th International Conference on Machinery, Materials and Computing Technology (ICMMCT 2017)
PB  - Atlantis Press
SP  - 714
EP  - 724
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmct-17.2017.146
DO  - 10.2991/icmmct-17.2017.146
ID  - Liu2017/04
ER  -