An Efficient Concrete Bridge Disease Identification System Based on Sample Database

As complex and varied concrete structures and their disease characteristics, it is difficult to extract a stable identification feature. Interpretation of the ground penetrating radar(GPR) scanned image is mostly based on experts experiences. Thus we designed an efficient concrete bridge disease identification system based on sample database(CBDI). The CBDI is based on principal component analysis the radar scanned image to extract features and minimum Euclidean distance classifier to defects classification. After a great deal of analysis on typical defects of the image feature and the establishment of a typical defects sample database, the technical difficulty of dealing with the diversity reflection features of one defect interface was solved.