Defect shape detection and defect reconstruction in active thermography by means of two-dimensional convolutional neural network as well as spatiotemporal convolutional LSTM network

A neural network (NN) for semantic segmentation (U-Net) was used for the detection of crack-type defects from thermography sequences. For this task, data sequences of forged steel parts were acquir...

[1]  Luc Van Gool,et al.  The Pascal Visual Object Classes Challenge: A Retrospective , 2014, International Journal of Computer Vision.

[2]  Andreas Mandelis,et al.  Application of a generalized methodology for quantitative thermal diffusivity depth profile reconstruction in manufactured inhomogeneous steel-based materials , 1998 .

[3]  Andreas Mandelis,et al.  Generalized methodology for thermal diffusivity depth profile reconstruction in semi‐infinite and finitely thick inhomogeneous solids , 1996 .

[4]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[5]  Patrice Y. Simard,et al.  Best practices for convolutional neural networks applied to visual document analysis , 2003, Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings..

[6]  M. Omar,et al.  Experimentally validated defect depth estimation using artificial neural network in pulsed thermography , 2019, Infrared Physics & Technology.

[7]  Udo Netzelmann,et al.  A defect shape reconstruction algorithm for pulsed thermography , 2007 .

[8]  Sebastian Dudzik,et al.  Two-stage neural algorithm for defect detection and characterization uses an active thermography , 2015 .

[9]  Clemente Ibarra-Castanedo,et al.  Automated defect classification in infrared thermography based on a neural network , 2019, NDT & E International.

[10]  D. Almond,et al.  A quantitative analysis of pulsed video thermography , 1991 .

[11]  D. P. Almond,et al.  An artificial neural network interpreter for transient thermography image data , 1997 .

[12]  Sergey Lugin,et al.  Algorithms for efficient and quantitative non-destructive testing by pulsed thermography , 2007 .

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Xavier Maldague,et al.  Defect characterization in pulsed thermography: a statistical method compared with Kohonen and Perceptron neural networks , 2000 .

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.