Biostatistics Research Today is a free monthly online journal that collates and summarizes the latest research about Biostatistics, including details on statistics, uncertainty, probability, modeling.

Generalized face super-resolution.

Jia K, Gong S

Shenzhen Institute of Advanced Integration Technology, Chinese Academy of Sciences/Chinese Academy of Hong Kong, Shenzhen, China. chrisjia@dcs.qmul.ac.uk

Existing learning-based face super-resolution (hallucination) techniques generate high-resolution images of a single facial modality (i.e., at a fixed expression, pose and illumination) given one or set of low-resolution face images as probe. Here, we present a generalized approach based on a hierarchical tensor (multilinear) space representation for hallucinating high-resolution face images across multiple modalities, achieving generalization to variations in expression and pose. In particular, we formulate a unified tensor which can be reduced to two parts: a global image-based tensor for modeling the mappings among different facial modalities, and a local patch-based multiresolution tensor for incorporating high-resolution image details. For realistic hallucination of unregistered low-resolution faces contained in raw images, we develop an automatic face alignment algorithm capable of pixel-wise alignment by iteratively warping the probing face to its projection in the space of training face images. Our experiments show not only performance superiority over existing benchmark face super-resolution techniques on single modal face hallucination, but also novelty of our approach in coping with multimodal hallucination and its robustness in automatic alignment under practical imaging conditions.

Published 16 May 2008 in IEEE Trans Image Process, 17(6): 873-86.
Full-text of this article is available online (may require subscription).

© 2005-2008 Biostatistics Research Today. All Rights Reserved.