Measuring Heterogeneous Thermal Patterns in Infrared-Based Diagnostic Systems Using Sparse Low-Rank Matrix Approximation: Comparative Study

ActiveU and passive thermographies are two efficient techniques extensively used to measure heterogeneous thermal patterns, leading to subsurface defects for diagnostic evaluations. This study conducts a comparative analysis on low-rank matrix approximation methods in thermography with applications of semi-, convex-, and sparse-nonnegative matrix factorization (NMF) methods for detecting subsurface thermal patterns. These methods inherit the advantages of principal component thermography (PCT) and sparse PCT and tackle negative bases in sparse PCT with nonnegative constraints and exhibit clustering property in processing data. The practicality and efficiency of these methods are demonstrated by the experimental results for subsurface defect detection in three specimens and preserving thermal heterogeneity for distinguishing breast abnormality in breast cancer screening data set (accuracy of 74.1%, 75.9%, and 77.8%).

[1]  D. Donoho.  For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution , 2006 .

[2]  Wai Lok Woo,et al.  Ensemble Joint Sparse Low-Rank Matrix Decomposition for Thermography Diagnosis System , 2021, IEEE Transactions on Industrial Electronics.

[3]  P. Paatero,et al.  Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values† , 1994 .

[4]  L. Finesso,et al.  Matrix factorization methods: Application to thermal NDT/E , 2006 .

[5]  Sergey Ioffe,et al.  Improved Consistent Sampling, Weighted Minhash and L1 Sketching , 2010, 2010 IEEE International Conference on Data Mining.

[6]  Xavier Maldague,et al.  A study of defect depth using neural networks in pulsed phase thermography: modelling, noise, experiments , 1998 .

[7]  Stefano Sfarra,et al.  Thermography data fusion and nonnegative matrix factorization for the evaluation of cultural heritage objects and buildings , 2018, Journal of Thermal Analysis and Calorimetry.

[8]  Prabhu Babu,et al.  Sparse Reconstruction-Based Thermal Imaging for Defect Detection , 2019, IEEE Transactions on Instrumentation and Measurement.

[9]  Aura Conci,et al.  A New Database for Breast Research with Infrared Image , 2014 .

[10]  Yuan Yao,et al.  Sparse Principal Component Thermography for Subsurface Defect Detection in Composite Products , 2018, IEEE Transactions on Industrial Informatics.

[11]  Denis Laurendeau,et al.  Incremental Low Rank Noise Reduction for Robust Infrared Tracking of Body Temperature during Medical Imaging , 2019, Electronics.

[12]  Jianbo Wu,et al.  Comparison Study of Different Features for Pocket Length Quantification of Angular Defects Using Eddy Current Pulsed Thermography , 2019, IEEE Transactions on Instrumentation and Measurement.

[13]  Liang Cheng,et al.  Transient Thermal Behavior of Eddy-Current Pulsed Thermography for Nondestructive Evaluation of Composites , 2013, IEEE Transactions on Instrumentation and Measurement.

[14]  S. Kandlikar,et al.  Clinical Infrared Imaging in the Prone Position for Breast Cancer Screening—Initial Screening and Digital Model Validation , 2020, Journal of Engineering and Science in Medical Diagnostics and Therapy.

[15]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[16]  Xavier Maldague,et al.  Low-rank sparse principal component thermography (sparse-PCT): Comparative assessment on detection of subsurface defects , 2019, Infrared Physics & Technology.

[17]  Hongwei Liu,et al.  Solving non-negative matrix factorization by alternating least squares with a modified strategy , 2013, Data Mining and Knowledge Discovery.

[18]  Chih-Jen Lin,et al.  Projected Gradient Methods for Nonnegative Matrix Factorization , 2007, Neural Computation.

[19]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[20]  Yunze He,et al.  Unsupervised Sparse Pattern Diagnostic of Defects With Inductive Thermography Imaging System , 2016, IEEE Transactions on Industrial Informatics.

[21]  Clemente Ibarra-Castanedo,et al.  Defect depth retrieval from pulsed phase thermographic data on Plexiglas and aluminum samples , 2004, SPIE Defense + Commercial Sensing.

[22]  Hyunsoo Kim,et al.  Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method , 2008, SIAM J. Matrix Anal. Appl..

[23]  William P. Winfree,et al.  Fixed eigenvector analysis of thermographic NDE data , 2011, Defense + Commercial Sensing.

[24]  Satish G. Kandlikar,et al.  Infrared imaging technology for breast cancer detection – Current status, protocols and new directions , 2017 .

[25]  H. H. Pennes.  Analysis of tissue and arterial blood temperatures in the resting human forearm. , 1948, Journal of applied physiology.

[26]  C. Ibarra-Castanedo,et al.  More than Fifty Shades of Grey: Quantitative Characterization of Defects and Interpretation Using SNR and CNR , 2018, Journal of Nondestructive Evaluation.

[27]  Stefano Sfarra,et al.  Comparative analysis on Thermal Non-Destructive Testing Imagery applying Candid Covariance-Free Incremental Principal Component Thermography (CCIPCT) , 2017 .

[28]  Nik Rajic,et al.  Principal component thermography for flaw contrast enhancement and flaw depth characterisation in composite structures , 2002 .

[29]  Chris H. Q. Ding,et al.  Convex and Semi-Nonnegative Matrix Factorizations , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Infrared Imaging Does Not Predict the Presence of Malignancy in Patients with Suspicious Radiologic Breast Abnormalities , 2014, The breast journal.

[31]  Martin Johnston,et al.  Variational Bayesian Subgroup Adaptive Sparse Component Extraction for Diagnostic Imaging System , 2018, IEEE Transactions on Industrial Electronics.

[32]  Application of Sparse Non-Negative Matrix Factorization in infrared non-destructive testing , 2019, Proceedings of QIRT Asia 2019.