Image Restoration Using a Multilayered Quantum Backpropagation Neural Network

Abstract

The problem of image restoration in presence of blur and noise has been a very important problem in the domain of digital image processing and computer vision. A quantum inspired back propagation neural network (QBPNN) architecture based on quantum gates (single qubit rotation gates and two qubit controlled-not gates) has been used and its back propagation learning formulae have been proposed in this article for the task of restoration of images from noisy and blurred perspectives. The superiority of the QBPNN architecture is clearly demonstrated in terms of convergence rate and speed as compared to the classical multilayer perceptron (MLP).