Structured iterative alternating sparse matrix decomposition for thermal imaging diagnostic system

Abstract

In this paper, we propose a structured iterative alternating sparse matrix decomposition to efficiently decompose the input multidimensional data from active thermography into the sum of a lowrank matrix, a sparse matrix, and a noise matrix. In particular, the sparse matrix is further factorized into a pattern constructed dictionary matrix and a coefficient matrix. The estimation of the dictionary matrix and coefficient matrix is based on integrating the vertex component analysis with the framework of the alternating direction method of multipliers. In addition, the joint structure sparsity and nonnegative constraint are emphasized as part of the learning strategy. In order to verify the effectiveness and robustness of the proposed method, experimental studies have been carried out by applying the proposed method to thermal imaging diagnostic system for carbon fiber reinforced plastics(CFRP) defects detections. The validation study has been conducted by comparing the proposed method with the current state-of-the-art algorithms. The results indicate that the proposed method significantly improves the contrast ratio between the defective regions and the non-defective regions.

Instrumental Configuration of Electromagnetic Thermography and Optical Thermography

“…Figure 6(b) illustrates the new configuration of human-computer interaction interface which is developed using C#. After setting the parameters on the touch screen, the excitation source sends signals to the halogen lamps, and the IR camera records the heating and cooling stages of the specimen, which are stored in the form of video and processed by the tensor decomposition [12] algorithms and deep learning methods.…”

Defect Detection and Depth Estimation in CFRP Through Phase of Transient Response of Flash Thermography

“…This scheme also consists of a Sequence-PCA layer in the learning process which leads to extra semantic information. Authors in [18] have proposed a structured iterative alternating sparse matrix decomposition framework, which allows the abnormal patterns to be extracted automatically for flaw contrast enhancement. In [19], some deep learning-based methods have been reported for defect detection.…”

Multiscale Analysis of Solar Loading Thermographic Signals for Wall Structure Inspection

“…This laborious part can be overcome by the use of thermographic image processing that is a necessary step to highlight the interested features [9][10][11][12][13][14][15]. Among these techniques, principal component thermography (PCT) [16] is popular because of its capability in data compression, noise reduction, and feature extraction.…”