Swin transformer network leveraging multi-dimensional features for defect depth prediction

• Published in: Infrared physics & technology 2024-06, Vol.139, p.105288, Article 105288
• Main Authors: Zhang, Siyan, Omer, Akam M., Tao, Ning, Sfarra, Stefano, Zhang, Hai, Maldague, Xavier, Zhang, Cunlin, Meng, Jianqiao, Duan, Yuxia
• Format: Article
• Language: English
• Subjects: Depth prediction; Hilbert encoding; Infrared thermography; Multi-dimensional features; Swin transformer
• ISSN: 1350-4495; 1879-0275
• DOI: 10.1016/j.infrared.2024.105288

•Innovatively integrates multi-dimensional features (temperature, temperature change rate, time-frequency spectrum) to enhance defect depth prediction in pulsed infrared thermography.•Utilizes Hilbert encoding for 2D matrices creation and mask-based augmentation for synthetic defect data generation.•Achieves superior defect depth prediction by employing a Swin transformer network with shifted windows and multi-head self-attention, outperforming existing architectures. This study introduces a novel method for accurately predicting defect depth in pulsed infrared thermography. The core innovation of this study lies in the utilization of multi-dimensional features to enhance the accuracy of depth prediction. By integrating temperature, temperature change rate, and time-frequency spectrum into a comprehensive feature set, we aim to capture a more detailed understanding of defect characteristics, thereby facilitating more precise predictions. Additionally, we employ the Hilbert encoding method to obtain two-dimensional matrices and utilize mask-based augmentation to generate synthetic defect data matrices. Subsequently, the generated matrices are fed input into a Swin transformer network configured with shifted windows and multi-head self-attention. In comparison to existing high-performing architectures, our method leveraging multi-dimensional features, demonstrates superior performance, especially in defect depth prediction for non-planar samples. This work paves the way for more accurate and efficient defect depth prediction in various infrared thermography applications.