Archetypes and principal components of an IR image sequence

In the last years, the principal component analysis (PCA) has been used in the thermal NDT/E (TNDT/E) field as a useful tool for signal enhancement and feature extraction. Even though many efforts were addressed to understand the meaning of the principal components, no apparent connections have been found with the thermal processes involved in the test. In this paper, PCA is compared with another matrix factorization method called archetypal analysis (AA). Contrary to PCA, AA does not imply any transformation of the original reference system and moreover the archetypes are intrinsically related to the experimental data. The main drawback is that AA is heavy in terms of computational time. To accelerate the convergence, the pixel purity index (PPI) algorithm is used. Results of PCA and AA applied to thermogram sequences are presented and discussed.