Multilevel Threshold Segmentation Method for Infrared Image of Power Equipment with Two-dimensional Entropy Based on Bat Algorithm
- DOI
- 10.2991/icmmcce-17.2017.117How to use a DOI?
- Keywords
- power equipment; infrared image segmentation; bat algorithm; two-dimensional entropy
- Abstract
The region of interest (ROI) segmentation of infrared image is one of the key steps in intelligent fault diagnosis of power equipment. Subsequently, a two-dimensional entropy multilevel threshold based on bat algorithm is proposed. By analyzing the multilevel threshold segmentation principle with two-dimensional entropy, the bat algorithm is used to search the optimal segmentation threshold, and these thresholds are used to the threshold segmentation experiment on the infrared image of the power equipment. The results show that this method improves time consuming of the algorithm and the precision of image segmentation compared with the multi-threshold segmentation method with two-dimensional entropy based on particle swarm optimization algorithm, which effectively solves the problem of multilevel threshold segmentation of infrared image. It lays the foundation for the extraction and analysis of temperature field characteristics of follow-up equipment, and is more suitable for the intelligent diagnosis of infrared images of power equipment failure.
- 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/).
Cite this article
TY - CONF AU - Xin Li AU - Haoyang Cui AU - Lunming Qin AU - Gaofang Li PY - 2017/09 DA - 2017/09 TI - Multilevel Threshold Segmentation Method for Infrared Image of Power Equipment with Two-dimensional Entropy Based on Bat Algorithm BT - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017) PB - Atlantis Press SP - 640 EP - 646 SN - 2352-5401 UR - https://doi.org/10.2991/icmmcce-17.2017.117 DO - 10.2991/icmmcce-17.2017.117 ID - Li2017/09 ER -