Abstract
Recently, it has become difficult to keep the skill level of bridge maintenance engineers due to the retirement of experienced engineers. Hence, the daily inspection for bridges cannot be performed accurately and efficiently in order to detect damages early and take appropriate measures. This study attempts to develop a support system for decision making of the damage assessment of bridges based on the pattern recognition considering the exception extraction. In this system, the exception extraction with one-class SVM removes some data that may cause the decrease of generalization capability of pattern recognition from the database. Therefore, it is guessed that the accuracy and confidence of recognized result are improved. Numerical examples applying digital images of RC slab of bridges with cracks are presented to demonstrate the practical utility of the approach of this study.
