Multi-feature vision transformer for automatic defect detection and quantification in composites using thermography

Abstract

This paper proposes a novel multi-feature vision transformer model for automatic defect detection and quantification in composites using thermography. Firstly, a sampling strategy for infrared data is proposed to address the issues of data class overlap and imbalance. Secondly, multiple feature fusion is employed to aggregate various important infrared features that exhibit strong correlations with defects. Furthermore, a multi-feature vision transformer (VIT) model that leverages self-attention mechanisms to capture global context and long-range dependencies in the composite images is developed. Experiments are performed to verify the effectiveness of the proposed method. The results show that the proposed method has excellent performance in terms of both accuracy and generalization capability.