Color restoration of images through high order zeroing neural networks

¹ Department of Economics, Division of Mathematics-Informatics and Statistics-Econometrics, National and Kapodistrian University of Athens, Sofokleous 1 Street, Athens, 10559, Greece
² Laboratory “Hybrid Methods of Modelling and Optimization in Complex Systems”, Siberian Federal University, Prosp. Svobodny 79, Krasnoyarsk, 660041, Russia

^* Corresponding author: spirmour@econ.uoa.gr

Abstract

One of the fundamental tasks in pattern recognition is color image restoration. Every color image has three channels in the RGB color space, in contrast to grayscale images. The restoration of color images is typically far more challenging than that of grayscale images because of the internal relationships among the three channels. Given that the color image restoration can be represented as a dynamic problem with quaternion matrices, a new high order zeroing neural network (HZNN) model is developed to tackle this issue. Specifically, the time-varying quaternion matrix linear equations can be solved using the HZNN design, which is a member of the family of zeroing neural network (ZNN) models that correlate to hyperpower iterative techniques. In a realistic color image restoration application, the HZNN design outperforms the ZNN design, although both approaches work amazingly well.