Giegerich W.V., Fedorishin D.C., Forte III L., Christie L., Schneider P.J., Oh K.W.
University at Buffalo, US
Keywords: corrosion detection, multispectral imaging, post-processing
This research focuses on the implementation of an enhanced corrosion detection algorithm using multispectral imaging techniques and post-processing image filters. Utilizing various combinations of light filters with image enhancement software, we are able to increase the performance of a pixel-wise corrosion detection algorithm in both recall and precision, increasing the F1-Score of rust pixels detected from 0.33 to 0.60. Identification and quantification of corrosion was applied to applications relating to material characterization and automotive diagnostics.
Journal: TechConnect Briefs
Volume: TechConnect Briefs 2021
Published: October 18, 2021
Pages: 35 - 38
Industry sector: Advanced Materials & Manufacturing
Topics: Advanced Materials for Engineering Applications, Materials Characterization & Imaging
ISBN: 978-0-578-99550-2