m“ QE à un 
> < 
  
  
  
       
  
   
  
  
$ 
m a 
* — 
< a 
$9 Ec 
3 8. 
8 ^ 
> x 
E 
do 
X 
3 
3 : 
€ = 
5 ; 
5 
“8 Linear WFE (evel 
^ Linear WFE (level 4); 
^ Linear WFE (levet 5): 
^ Nonlinear WFE : 
2 5 10 18 20 25 30 
  
Number of Feature 
Figure 4. Comparison of classification accuracies between WFE 
methods 
4.2 Experiment II: Comparison of Classification Results 
between Wavelet-based Feature Extraction Methods 
The purpose of the experiment II is to compare the performance 
between wavelet-based feature extraction (WFE) methods. In 
linear WFE, we use Daubechies 3 wavelet as basis function and 
decompose signal from level 3 to level 5. The numbers of 
features in different linear WFE methods are thirty, eighteen 
and eleven respectively. 
Figure 4 shows the classification accuracies between WFE 
methods. First of all, the results of linear and nonlinear WFE 
methods are similar, and the best accuracies of linear WFE 
(level 3), linear WFE (level 4), linear WFE (level 5) and 
nonlinear WFE are 8596, 86.67%, 89.33 and 83.33%. In 
addition, the classification accuracies increase slightly in linear 
WFE, when the level of decomposition increases. 
4.3 Experiment III: Comparison of Classification Results 
between Wavelet-Based and HHT-Based Feature 
Extraction Methods 
In experiment III, the purpose is to compare the performance 
between  wavelet-based and HHT-based methods. The 
classification accuracies with different methods are showed in 
Figure 5. First of all, the classification accuracies of WFE 
methods and HHT-based methods are all conformed to Hughes 
phenomenon that classification accuracy increases at first and 
then declines as the number of feature grows. 
Compared with the results of different methods, linear and 
nonlinear WFE have similar classification results which have 
been metioned in section 4.2. Also, the results of unsupervised 
HHT-based method are similar to WFE methods but the 
accuracies decrease obviously when the number of feature is 
more than ten. Finally, supervised HHT-based feature 
extraction can achieve better classification results than any 
other methods. 
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012 
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia 
  
   
  
  
  
  
  
  
® NIB ©. 
g PES oL 
8 NN & e 
& : 1s B 
5 e? 
8 - 
o e 99 
E » s 
$ : / Um 
$055 * / 
Q Pm 
05k | 
adsl B ioc9 9 HHT-Based FE (supervised) |: 
88 Linear WFE 
3 Nonlinear WFE 
5 10 15 20 25 30 
Number of Feature 
Figure 5. Comparison of classification accuracies between 
wavelet-based and HHT-based feature extraction methods 
5. CONCLUSION 
In this study, two feature extraction methods using Hilbert- 
Huang transform were proposed to extract useful features for 
hyperspectral image classification. The results of HHT-based 
methods are compared with wavelet-based feature extraction 
methods. 
According the experiments, the results of unsupervised HHT- 
based methods are similar to the result of WFE which is 
implemented in this study, but the accuracies of unsupervised 
HHT-based method are unstable when the feature increases. 
Subsequently, when computing the separability of different 
classes with training samples, supervised HHT-based method 
can have better result than unsupervised HHT-based method 
and can reach 90% classification accuracy with six or seven 
features. Furthermore, it also has superior classification 
accuracies than linear and nonlinear WFE. By extracting 
features from Hilbert spectrum, we can not only reduce the 
dimensionality of hyperspectral image but also get a small 
number of salient features for classification. Therefore, Hilbert- 
Huang is an appropriate and effective tool for hyperspectral 
image analysis. 
In the future, the effectiveness of HHT-based methods still 
could be improved. In addition, the objects in the experiments 
are mainly the minerals. It is another object to investigate that 
HHT-based feature extraction methods proposed in this study 
are suitable and have similar/better results than WFE methods 
for other kind of material objects such as metropolitan area of 
vegetation area. 
REFERENCES 
AVIRIS Airborne Visible/Infrared Imaging Spectrometer, 2011. 
AVIRIS Data - Ordering Free AVIRIS Standard Data Products. 
http://aviris.jpl.nasa.gov/data/free data.html (14 Jul. 2011). 
Bellman, R., 1961. Adaptive Control Processes: A Guided Tour, 
Princeton University Press. 
Fukunaga, K., 1990. Introduction to Statistical Pattern 
Recognition, Second edition, San Diego: Academic Press, Inc.