Hallucinating multiple occluded face images of different resolutions

被引:15
作者
Jia, Kui [1 ]
Gong, Shaogang [1 ]
机构
[1] Queen Mary Univ London, Dept Comp Sci, London E1 4NS, England
基金
英国工程与自然科学研究理事会;
关键词
super-resolution (hallucination); Bayesian framework; image alignment;
D O I
10.1016/j.patrec.2006.02.009
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Learning-based super-resolution has recently been proposed for enhancing human face images, known as "face hallucination". In this paper, we propose a novel algorithm to super-resolve face images given multiple partially occluded inputs at different lower resolutions. By integrating hierarchical patch-wise alignment and inter-frame constraints into a Bayesian framework, we can probabilistically align multiple input images at different resolutions and recursively infer the high-resolution face image. We address the problem of fusing partial imagery information through multiple frames and discuss the new algorithm's effectiveness when encountering occluded low-resolution face images. We show promising results compared to those of existing face hallucination methods from both simulated facial database and live video sequences. (c) 2006 Elsevier B.V. All rights reserved.
引用
收藏
页码:1768 / 1775
页数:8
相关论文
共 14 条
[1]  
Baker S., 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), P83, DOI 10.1109/AFGR.2000.840616
[2]  
Baker S, 2000, PROC CVPR IEEE, P372, DOI 10.1109/CVPR.2000.854852
[3]  
BISHOP CM, 2003, P ART INT STAT SOC A
[4]  
Capel D, 2001, PROC CVPR IEEE, P627
[5]  
De Bonet JS, 1998, ADV NEUR IN, V10, P773
[6]  
Dedeoglu G, 2004, PROC CVPR IEEE, P151
[7]   Restoration of a single superresolution image from several blurred, noisy, and undersampled measured images [J].
Elad, M ;
Feuer, A .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1997, 6 (12) :1646-1658
[8]  
FREEMAN W, 1999, 7 INT C COMP VIS, P1182
[9]   Joint MAP registration and high-resolution image estimation using a sequence of undersampled images [J].
Hardie, RC ;
Barnard, KJ ;
Armstrong, EE .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 1997, 6 (12) :1621-1633
[10]   IMPROVING RESOLUTION BY IMAGE REGISTRATION [J].
IRANI, M ;
PELEG, S .
CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING, 1991, 53 (03) :231-239