A corrosion detection algorithm via the random forest model

Tingting Liu; Kai Kang; Fen Zhang; Jialiang Ni; Tianyun Wang

doi:10.1117/12.2518313

14 February 2019 A corrosion detection algorithm via the random forest model

Tingting Liu, Kai Kang, Fen Zhang, Jialiang Ni, Tianyun Wang

Proceedings Volume 11048, 17th International Conference on Optical Communications and Networks (ICOCN2018); 110480B (2019) https://doi.org/10.1117/12.2518313
Event: 17th International Conference on Optical Communications and Networks (ICOCN2018), 2018, Zhuhai, China

Abstract

Corrosion is a serious issue causing damage in steel facilities. Timely inspection and repair is essential to avoid unprecedented structural failures. Employing non-destructive methods of manual inspection for large number of antennas to detect corrosion and related damages is time consuming and expensive. In addition to this, safety of inspector to climb structures possibly weakened by corrosion. In such a situation non-contact approach of automated visual inspection for corrosion and related damage detection through image processing of aerial based images is a viable option. For robust corrosion segmentation and detection, we investigate color classification based on random forest. A random forest is a statistical framework with a very high generalization accuracy and quick training times. We evaluate random forest based corrosion detection and compare it to Bayesian network, Multilayer Perceptron, SVM, Naive Bayes and RBF network. Results on a database of real images with manually annotated pixel-level ground truth show that with the IHLS colour space, the random forest approach outperforms other approaches.

Citation Download Citation

Tingting Liu, Kai Kang, Fen Zhang, Jialiang Ni, and Tianyun Wang "A corrosion detection algorithm via the random forest model", Proc. SPIE 11048, 17th International Conference on Optical Communications and Networks (ICOCN2018), 110480B (14 February 2019); https://doi.org/10.1117/12.2518313

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