DocumentCode :
3003774
Title :
Image hallucination with feature enhancement
Author :
Zhiwei Xiong ; Xiaoyan Sun ; Feng Wu
Author_Institution :
Univ. of Sci. & Technol. of China, Hefei, China
fYear :
2009
fDate :
20-25 June 2009
Firstpage :
2074
Lastpage :
2081
Abstract :
Example-based super-resolution recovers missing high frequencies in a magnified image by learning the correspondence between co-occurrence examples at two different resolution levels. As high-resolution examples usually contain more details and are of higher dimensionality in comparison with low-resolution ones, the mapping from low-resolution to high-resolution is an ill-posed problem. Rather than imposing more complicated mapping constraints, we propose to improve the mapping accuracy by enhancing low-resolution examples in terms of mapped features, e.g., derivatives and primitives. A feature enhancement method is presented through a combination of interpolation with prefiltering and non-blind sparse prior deblurring. By enhancing low-resolution examples, unique feature information carried by high-resolution examples is decreased. This regularization reduces the intrinsic dimensionality disparity between two different resolution examples and thus improves the feature mapping accuracy. Experiments demonstrate our super-resolution scheme with feature enhancement produces high quality results both perceptually and quantitatively.
Keywords :
image enhancement; image resolution; image restoration; interpolation; feature enhancement; feature mapping accuracy; ill-posed problem; image hallucination; interpolation; intrinsic dimensionality disparity; magnified image; mapping constraints; nonblind sparse prior deblurring; prefiltering; resolution levels; Asia; Frequency; Image databases; Image generation; Image resolution; Interpolation; Neural networks; Spatial databases; Sun; Visual databases;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on
Conference_Location :
Miami, FL
ISSN :
1063-6919
Print_ISBN :
978-1-4244-3992-8
Type :
conf
DOI :
10.1109/CVPR.2009.5206630
Filename :
5206630
Link To Document :
بازگشت