Naushad Ahmad Ansari

Naushad Ansari, Anubha Gupta

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.

Naushad Ansari, Anubha Gupta, Rahul Duggal

Image-matched nonseparable wavelets can find potential use in many applications including image classification, segmen- tation, compressive sensing, etc. This paper proposes a novel design methodology that utilizes convolutional neural net- work (CNN) to design two-channel non-separable wavelet matched to a given image. The design is proposed on quin- cunx lattice. The loss function of the convolutional neural network is setup with total squared error between the given input image to CNN and the reconstructed image at the output of CNN, leading to perfect reconstruction at the end of train- ing. Simulation results have been shown on some standard images.