International Archives of the Photogrammetry, Remote Sensin g and Spatial Information Sciences, Vol XXXV, Part B2. Istanbul 2004 
      
August 
Figure 6: Three level region classification results using 
thresholding method. 
i ^ 
May August 
Figure 3: Two level region classification results using 
thresholding method. The black areas represent water. 
   
   
4, 
Au 
^: 
   
oust August 
Figure 4: Two level region classification results using FCM Figure 7: Three level region classification results using 
method. The black areas represent water. FCM method. 
     
   
  
May August 
  
  
    
  
Figure 5: Two level region classification results using August 
decision tree method. The black areas represent water. Figure 8: Three level region classification results using the 
decision tree method. 
6. CONCLUSION 
In this paper, several classification methods are first presented 
and the results are compared. We then introduce the definition 
of “layer” and how to create it. Based on the “layer”, a multiple 
level change detection algorithm is proposed, which gives the 
details of the changes in each region and is demonstrated to be 
an easy, effective and reliable method. Experimental results are 
provided using RADARSAT images. 
       
/ ; : HY 
(a) layer of land (b) layer of (c) layer of deep 
(May) shallow water water (May) 
(May) 
776 
  
  
Interna 
(Augus 
Figure 
using t 
(a) chaı 
Figure! 
shallow 
additioi 
Refere 
1 AT 
20 
im 
Ph 
(C: 
mu