27 March 2018 Image-based corrosion recognition for ship steel structures
Author Affiliations +
Ship structures are subjected to corrosion inevitably in service. Existed image-based methods are influenced by the noises in images because they recognize corrosion by extracting features. In this paper, a novel method of image-based corrosion recognition for ship steel structures is proposed. The method utilizes convolutional neural networks (CNN) and will not be affected by noises in images. A CNN used to recognize corrosion was designed through fine-turning an existing CNN architecture and trained by datasets built using lots of images. Combining the trained CNN classifier with a sliding window technique, the corrosion zone in an image can be recognized.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yucong Ma, Yucong Ma, Yang Yang, Yang Yang, Yuan Yao, Yuan Yao, Shengyuan Li, Shengyuan Li, Xuefeng Zhao, Xuefeng Zhao, "Image-based corrosion recognition for ship steel structures", Proc. SPIE 10602, Smart Structures and NDE for Industry 4.0, 106020U (27 March 2018); doi: 10.1117/12.2296540; https://doi.org/10.1117/12.2296540


Network tutoring strategy model based on multi-agent plan
Proceedings of SPIE (November 15 2011)
Networked vision system using a prolog controller
Proceedings of SPIE (November 16 2005)
Contour-based computer stereo vision system
Proceedings of SPIE (November 30 1995)
Fast computation of the 2D discrete wavelet transform
Proceedings of SPIE (August 05 1993)

Back to Top