Statistical analysis of IR thermographic sequences by PCA

S. Marinetti, E. Grinzato, P. G. Bison, E. Bozzi, M. Chimenti, G. Pieri, O. Salvetti

Condensed Matter Physics  Error analysis  Data compression  and Optics  Electronic  Learning and measuring  Optical and Magnetic Materials  Atomic and Molecular Physics  Algorithms  Cameras  Feature extraction  Eigenvalues and eigenfunctions  Principal Component Analysis  IR image sequence  Principal component analysis 

Automatic processing of IR sequences is a desirable target in Thermal Non Destructive Evaluation (TNDE) of materials. Unfortunately this task is made difficult by the presence of many undesired signals that corrupt the useful information detected by the IR camera. In this paper the Principal Component Analysis (PCA) is used to process IR image sequences to extract features and reduce redundancy by projecting the original data onto a system of orthogonal components. As a thermographic sequence contains information both in space and time, the way of applying PCA to these data cannot be straightforwardly borrowed from typical applications of PCA where the information is mainly spatial (e.g. Remote Sensing, Face Recognition). This peculiarity has been analysed and the results are reported. Finally, in addition to the use of PCA as an unsupervised method, its use in a 'learning and measuring' configuration is considered.

Source: Infrared physics & technology 46 (2004): 85–91. doi:10.1016/j.infrared.2004.03.012

Publisher: Pergamon,, Exeter , Regno Unito

Metrics