Smart image processing for steel bridge corrosion inspection

Abstract

Image recognition has been widely utilized in scientific research and prevalently adopted in industries. Application in infrastructure condition assessment includes defect recognition on steel bridge painting and underground sewer systems. Nevertheless, there is still no robust method to overcome the non-uniform illumination problem. The non-uniform illumination problem is arisen from the shades, shadows, and the highlights on a rust image. Although, K-Means, which is a kind of clustering methods according to the differences of each pixel, is recognized as one of the best rust defect recognition methods, it cannot recognize the non-uniform illuminated images and the mild rust color well. Also, there is lack of an automated color image recognition system in this field. The purpose of this research is to attempt to resolve the problems of non-uniform illumination and mild rust color as well as to automate the recognition system.