Face hallucination through ensemble learning

A learning-based face hallucination system is proposed, in which given a low-resolution facial image, a corresponding high-resolution image is automatically obtained. This study proposes an ensemble of image feature representations, including various local patch- or block-based representations, a one-dimensional vector image representation, a two-dimensional matrix image representation, and a global matrix image representation. For each feature representation, a regression function is constructed to synthesize a high-resolution image from the low-resolution input image. The synthesis process is conducted in a layer-by-layer fashion, where each layer composes several regression functions. The output from one layer is then served as the input to the following layer. The experimental results show that the proposed framework is capable of synthesizing high-resolution images from low-resolution input images with a wide variety of facial poses, geometry misalignments and facial expressions even when such images are not included within the original training dataset.