Defect Feature Extraction in Eddy Current Testing Based on Convolutional Sparse Coding

Abstract

In eddy current testing (ECT), feature extraction methods play an important role in the detection and classification of defects. Convolutional sparse coding (CSC) has gained attentions in recent years as this can provide a versatile framework in the description of signal and rich options for effective discrimination and classification algorithms. In this paper, we propose a feature extraction method which for the first time applies the CSC model for ECT. The local dictionary in the model is trained using signal segments corresponding to scans of defects. The proposed algorithm has achieved 98% accuracy in terms of the recovery of the location of defect signal segments. The recovered coefficients are adopted as unique features which eventually correspond to the profiles of the defect.