Evaluation of corrosion on steel surface using image processing

Igarashi, Takahiro  ; Sugawara, Yu*; Otani, Kyohei   ; Aoyama, Takahito   

Using two types of image processing techniques without machine learning, edge extraction processing and keypoint extraction processing, progressively corroded regions under rust layer from images of corroded steel surfaces was extracted. We found that there is a relatively good correlation between the keypoint strength obtained from the keypoint extraction processing for HSL transformed and histogram flattened corroded surface photographs and the corrosion depth after removing rust removal.