IMAGE FUSION BASED ON EXTENSIONS OF INDEPENDENT COMPONENT
ANALYSIS
Mi Chen d ' *, Yingchun Fu b , Deren Li c , Qianqing Qin c
a College of Education Technology, Capital Normal University, Beijing 100037,China - (mierc@hotmail.com)
b College of Geography Science, South China Normal University, Guangzhou, 510631,China - (fyc226@163.com)
c State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan
University, 129 Luoyu Road, Wuhan, China, 430079
- (drli@whu.edu.cn,qqqin@lmars.whu.edu)
Commission VII, WG VII/6
KEY WORDS: image processing, integration, image understanding, fusion, land cover
ABSTRACT:
Remote sensing image fusion can effectively improve the accuracy of image classification. This paper proposes an image fusion
algorithm based on extensions of independent component analysis (ICA) and multi-classifier system. Firstly a novel method of
fusing panchromatic and multi-spectral remote sensing images is developed by contourlet transform which can offer a much richer
set of directions and shapes than wavelet. As ICA not only can effectively remove the correlation of multi-spectral images, but also
can realize sparse coding of images and capture the essential edge structures and textures of images, then using features extracted
from the extension of ICA domain coefficients of the fused image, different classifiers corresponding to different image features are
chosen in parallel style and the support vector machines are trained to classify the whole fused image as stack part in the proposed
multi-classifier system. Experimental results show that the proposed algorithm can effectively improve the accuracy of image
classification.
1. INTRODUCTION
Image fusion has received significant attention in remote
sensing. It can be defined as the process of combining two or
more source images from the same scene into a composite
image with extend information content by using a certain
algorithms. The fused image may provide increased
interpretation capabilities and more reliable results since data
with different characteristics. The process of image information
fusion can be performed at signal, feature, and symbol levels
depending on the representation format at which image
information is processed. (Ranchin, 2003).
The objective of image fusion is to improve the accuracy of the
objective recognition and classification, which can support the
decision making. The existing research results show that by
fusing the panchromatic and multi-spectral images to gain the
high spatial resolution multi-spectral fusion remote sensing
images can effectively improve the accuracy of image
classification. Besides fusing different classification results
from different single feature sources at decision level can also
be an effective way to improve the classification results.
This paper proposes an image fusion algorithm of remote
sensing images based on extensions of independent component
analysis (ICA) and multi-classifier system. Firstly a novel
method of fusing panchromatic and multi-spectral remote
sensing images is developed by contourlet transform. Then
using different features extracted from the extension of ICA
domain coefficients of the fused images, a parallel and stack
multi-feature and multi-classifier decision level image fusion
algorithm is presented. The remainder of the paper is organized
as follows. Section 2 recalls the concept of contourlet transform.
Section 3 introduces the foundations and extensions of ICA.
Section 4 highlights the algorithm of the decision fusion
algorithm based on extension of ICA and multi-feature and
multi-classifier system. Experiments results and comparisons
are presented and discussed in Section 5. Conclusions are
drawn in Section 6.
2. CONTOURLET TRANSFORM
The contourlet transform (M.N.Do, 2002) is an extension of the
wavelet transformation in two dimensions using multi-scale and
directional filter banks. The contourlet expansion of images
consists of basis images oriented at various directions in
multiple scales, with flexible aspect ratios. Thus the contourlet
transform not only retains the multi-scale and time-frequency
localization properties of wavelets, but also it offers a high
degree of directionality and anisotropy. The contoulet transform
is implemented in two stages: the subband decomposition stage
and the directional decomposition stage.
Recently developed contourlet transform can offer a much
richer set of directions and shapes, and thus it is more effective
than wavelet in capturing smooth contours and geometric
structures in images. This paper proposes a novel method of
fusing panchromatic and multi-spectral remote sensing images
based on contourlet transform.
Corresponding author.