Application of Radial Basis Function Interpolation for Content Aware Image Retargeting

Abstract

Several imaging and graphics applications usually require the resizing/retargeting of the spatial resolution of a given image. In real time applications, the retargeting process is expected to be computationally fast and free of any visually disturbing structural distortions. Accordingly, several content-aware retargeting methods, which resize images while preserving important image structures, have been introduced. However, it has also been shown that finding a single method that can be effectively applicable in all types of situation is very challenging. Specifically, many of the existing methods are not capable of avoiding visible structural distortions during high level of image squeezing or stretching processes. The distortions become even more evident with the presence of numerous high frequency contents. Accordingly, we have proposed a new and efficient image retargeting method which is based on Radial Basis Function (RBF) interpolation. We have introduced a novel pre-processing step and modifications to the generic form of the RBF interpolation technique for a better structural as well as size preservation of important image regions. The method is finally evaluated with respect to prior retargeting methods and leads to improved performances, both in terms of quality and complexity measures.