Abstract
The paper is devoted to the feature-based recognition of degraded signals acquired by a linear time-invariant system The proposed approach consists of describing signals by features which are invariant with respect to the degradation and recognizing signals in the feature space. Neither impulse response identification nor signal restoration are required. Thanks to this, the new approach is in many applications much more effective than the classical one based on blind deconvolution. Two sets of appropriate blur-invariant features (the first one in time domain, the other one in spectral domain) are introduced in this paper. The proof of their invariance is given and their performance is illustrated by numerical experiments.

This publication has 6 references indexed in Scilit: