Stepwise reconstruction of high-resolution facial image based on interpolated morphable face model

Abstract

This paper proposes a new method for reconstructing a high-resolution facial image from a low-resolution facial image using stepwise reconstruction based on the interpolated morphable face model. First, we defined an interpolated morphable face model that an interpolated face is composed of a low-resolution face, its interpolated high-resolution face from a low-resolution one, and its original high-resolution one. We also proposed a stepwise reconstruction method for preventing over reconstruction caused by direct reconstruction of a high-resolution image from a low-resolution facial image. The encouraging results show that our proposed method can be used to improve the performance of face recognition systems, specifically in resolution enhancement of facial images captured on visual surveillance systems.