Design of Image Matched Non-Separable Wavelet using Convolutional Neural Network

TL;DR

This paper introduces a CNN-based method for designing image-matched non-separable wavelets tailored to specific images, enhancing applications like classification and segmentation through perfect reconstruction.

Contribution

It presents a novel CNN-based approach for designing two-channel non-separable wavelets matched to a given image, using a quinqunx lattice structure and a loss function for perfect reconstruction.

Findings

Effective wavelet design for specific images demonstrated

Achieved perfect reconstruction in simulations

Applicable to various image processing tasks

Abstract

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.