Debonding Defect Detection of CFRP Based on Thermal Signal Reconstructed Region Growing Algorithm

In this paper, the fusion of seeded region growing and thermal signal reconstruction algorithm has been proposed to solve the problem of low resolution of defect detection. The algorithm can significantly enhance the contrast ration between defects and sound areas, and realize the accurate positioning of defects. In order to objectively and quantitatively evaluate the detection performance of different algorithms, the event based F-score is computed to measure the detection results.