Share Email Print

Proceedings Paper

The face hallucinating two-step framework using hallucinated high-resolution residual
Author(s): H. M. M. Naleer; Yao Lu; Yaozu An
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In video surveillance, the attention human faces are frequently of small size. Image hallucination is an imperative factor disturbing the face classification by human and computer. In this paper, we propose a two-step face hallucination framework by means of training data sets which have a small quantity of low and high resolution images. In the first step, the global face is constructed based on optimal weights of training images. In the second step, a local residual compensation method bases on position patch via residual training face image data sets. Moreover, the hallucinated highresolution residual image which is obtained by the identical process can be subsequent for the local face. Finally, the hallucinated high-resolution residual image is appended with the input low-resolution face image which is interpolated to the high-resolution image dimension by an upsampling factor. Experiments fully demonstrate that our framework is very flexible and accomplishs good performance via small training data sets.

Paper Details

Date Published: 8 July 2011
PDF: 5 pages
Proc. SPIE 8009, Third International Conference on Digital Image Processing (ICDIP 2011), 80090A (8 July 2011); doi: 10.1117/12.896076
Show Author Affiliations
H. M. M. Naleer, Beijing Institute of Technology (China)
South Eastern Univ. of Sri Lanka (Sri Lanka)
Yao Lu, Beijing Institute of Technology (China)
Yaozu An, Beijing Institute of Technology (China)

Published in SPIE Proceedings Vol. 8009:
Third International Conference on Digital Image Processing (ICDIP 2011)
Ting Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?