Independent component analysis and neural approaches to the extraction of features from NDT/NDE

The problem of extracting relevant information about a defective specimen from external noninvasive measurements is hardly solvable without exploiting recent advances in signal processing. The usual two-step NDT/NDE problem (detection and reconstruction of the defect) can indeed be interpreted as a pattern recognition most in which the feature extraction aspect is by far the most interesting from the scientific viewpoint Various relevant feature extraction techniques are compared in this work aiming to finding the most advantageous mapping that reduces the dimensionality of the input patterns while presenting the relevant information content about the defect. The preprocessing analysis is also shown to yield peculiar advantages with respect to mere noise filtering of raw data