Supervised dictionary learning supported classifier with feature fusion scheme to noninvasively detect TRISO-particle defects

Abstract

This paper presents a novel method to support analyzing TRISO-particle failure rate by exploiting X-ray phase contrast imaging (PCI) modality to nondestructively visualize inter-defects and supervised dictionary learning to automatically distinguish cracked particles. Histogram of oriented gradient (HOG) operator was combined with local binary pattern histogram Fourier (LBP-HF) descriptor by canonical correlation analysis (CCA) method in order to extract crack features more significantly. Label consistent K-singular value decomposition (LC K-SVD) dictionary learning followed to encode features with more discriminability and learn a dictionary capable of excluding noise and intra-class variability to enforce recognition, with comparatively high recognition accuracy.