Optimization of bilinear interpolation based on ant colony algorithm

Abstract

This paper proposes a novel method optimizing the bilinear interpolation using Ant Colony Algorithm (ACA). The isotropous-assignment of the old-pixels' average-value to an unknown point (or pixel), in bilinear interpolation, is responsible for many artifacts which corrupt the resulting image features, edges in particular. To correct, we apply the ant colony algorithm to find a reasonable value from all the directions in the neighborhoods of the unknown point. The experimental results show better immanent image features than bilinear interpolation. © 2012 Springer-Verlag.