Information Engineering (IE) Volume 3, 2014 www.se ipub.org/ie
67
A Study on Spectral Super-resolution of
Hyperspectral Imagery based on
Redundant Dictionary
Ying Wu*
1
, Suyu Wang
2
, Yibin Hou
3
School of Software Engineering, Beijing Univ ersity of Technology, Beijing, China
*1
wylemmon@163.com;
2
suyuwang@bjut.edu.cn;
3
yhou@bjut.edu.cn
Abstract
With the wide a pplication of hypers pe c tra l ima gery, the
re solution re quire d is hig her and highe r. W ithout increasing
the equipment cost, a s pe c tra l s upe r -resolution method
based on redundant dictionary is presented in this pape r to
improve the s pectral resolution of hype rspectral image ry.
The re dundant dictionary base d over-comple te signa l s parse
decomposition theory is applied to the super resolution of
hypers pe c tra l image ry. By s pa rse de compos ing of the
spectrum curve corresponding to each pixel along the
dire ction of spectral dime ns io n, s upe r -resolution is a pplie d
to the comple te spectral curve of each pixe l, which ca n
e ns ure the consis tency of their s pectral characteris tics during
the process of super-resolution restoration, while the
spectral resolution of the hype rspectral image ry is improve d
e ffective ly.
Keywords
Hyperspectral Imag ery; Sparse Decomposition; Redundant
Dict ionary; Super-reso lut ion Restoration
Introduction
Hyperspectral imagery is a two-dimensional image
group obtained when the multi-spectrally im a gi n g
spectrometer images on the same surface feature. It
comprises tens to hundreds of consecutive and
segmental spectral information, and it has a high
spectral resolution (Liguo Wang, Chunhui Zhao,
2014). With the improved spectral resolution, it is
accompanied by the increase of the cost of the
equipment when obtaining the hyperspectral imagery.
Therefore, under conditions of constant cost, t h e
super-resolution restoration method which is using
the mathematical methods and signal theory to obtain
the high-resolution images has become the hot topic in
the field of improving image resolution.
The super-resolution image restoration is a method
that rebuilds a high-resolution image at the same
scene through a piece or pieces of low-resolution
images and removes noise in the original
low-resolution image (Xuefeng Yang, 2011). For
hypersepctral imagery, super-resolution algorithm is
designed for two kinds of resolutions—spat ial
resolution and spectral resolution. There are extensive
studies on the spatial resolution in recent times, and
relatively less attention to spectral ones. At present,
the non-mean interpolation method is the most
intuitive way in the s up er -resolution restoration st udy
on the spectral super-resolution of hyperspectral
imagery. But due to ignoring the error introduced by
the interpolation process, the non-mean interpolation
method cannot guarantee the optimum of the entire
restoration algorithm (Xuefen Wang, Yi Yang, Jian
Cui, 2011).
In the analysis of hyperspectral imagery, Chunmei
Zhang et al (2006) noted that, in the over-complete
decomposition of the image, the design of atoms t o
form a redundant dictionary should reflect the
impor tant char acter ist ics of the original image as
possible. Adam S. Charles (2011) establishes a
comprehensive feature information dictionary using
the method which training the actual hyperspectral
imagery pixel based on unsupervised learning to build
redundant dictionary. This method could get more
and more effective feature information. The a b ov e
results show that the sparse representation based on
redundant dictionary could describe the feature
information in hyperspectral imagery better. For this
reason, a super-resolution restoration method b a sed
on redundant dictionary is presented in this paper. In
this method, the establishment of the high and low
resolution redundant dictionary is the core. The
method can be summarized as follows. First, establish
the training sample library with spectral curve of high
and low resolution corresponding pixel. Then, learn to
get a pair of over-complete low and high resolution
redundant dictionary by constraining the high and