Image Segmentation based on discrete Krawtchouk Moment and Quantum Neural Network

Abstract

A new image segmentation method based on discrete Krawtchouk moments and Quantum neural networks is presented. The Krawtchouk moments in certain local window of each pixel in the image are computed and input to quantum neural network . Quantum neural networks, which use multilevel transfer function, have the inherent fuzzy characteristics. The point accommodates to the connatural uncertainty of fractional image data in image segmentation procession. Experiments confirm that the performance of our proposed methods is more accurate and has less iterative time in comparison with the traditional segmentation methods based on Legendre moments and BP neutral networks.