M-RWTL: Learning Signal-Matched Rational Wavelet Transform in Lifting Framework
This work addresses the need for adaptive signal-matched transforms in applications with limited data, offering an invertible and modular learning framework.
The paper proposes M-RWTL, a method to learn a rational wavelet transform from a single signal without requiring large training data, by extending the lifting framework from dyadic to rational wavelets. It achieves better signal reconstruction in compressed sensing compared to standard wavelet transforms.
Transform learning is being extensively applied in several applications because of its ability to adapt to a class of signals of interest. Often, a transform is learned using a large amount of training data, while only limited data may be available in many applications. Motivated with this, we propose wavelet transform learning in the lifting framework for a given signal. Significant contributions of this work are: 1) the existing theory of lifting framework of the dyadic wavelet is extended to more generic rational wavelet design, where dyadic is a special case and 2) the proposed work allows to learn rational wavelet transform from a given signal and does not require large training data. Since it is a signal-matched design, the proposed methodology is called Signal-Matched Rational Wavelet Transform Learning in the Lifting Framework (M-RWTL). The proposed M-RWTL method inherits all the advantages of lifting, i.e., the learned rational wavelet transform is always invertible, method is modular, and the corresponding M-RWTL system can also incorporate nonlinear filters, if required. This may enhance the use of RWT in applications which is so far restricted. M-RWTL is observed to perform better compared to standard wavelet transforms in the applications of compressed sensing based signal reconstruction.