Open Access

Change detection in synthetic aperture radar images using spatial fuzzy clustering based on the similarity matrix

Tushar Zanke

Tushar Zanke

Department of Instrumentation Engineering, Vishwakarma Institute of TechnologyPune, India
Search for this author on
Sciendo|Google Scholar
Zanke, Tushar
, 
Stuti Jagtap

Stuti Jagtap

Department of Instrumentation Engineering, Vishwakarma Institute of TechnologyPune, India
Search for this author on
Sciendo|Google Scholar
Jagtap, Stuti
, 
Samrudhi Wath

Samrudhi Wath

Department of Instrumentation Engineering, Vishwakarma Institute of TechnologyPune, India
Search for this author on
Sciendo|Google Scholar
Wath, Samrudhi
, 
Snehashish Mulgir

Snehashish Mulgir

Department of Instrumentation Engineering, Vishwakarma Institute of TechnologyPune, India
Search for this author on
Sciendo|Google Scholar
Mulgir, Snehashish
 and 
Archana Chaudhari

Archana Chaudhari

Department of Instrumentation Engineering, Vishwakarma Institute of TechnologyPune, India
Search for this author on
Sciendo|Google Scholar
Chaudhari, Archana
  
Jul 19, 2025
Change detection in synthetic aperture radar images using spatial fuzzy clustering based on the similarity matrix's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Article Category: Research Article
Published Online: Jul 19, 2025
Received: Mar 07, 2025
DOI: https://doi.org/10.2478/ijssis-2025-0026
Keywords
© 2025 Tushar Zanke et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1:

Illustration of CNN model architecture. CNN, convolutional neural network.
Illustration of CNN model architecture. CNN, convolutional neural network.

Figure 2:

Illustration of the average pooling operation with a 2 × 2 filter and stride.
Illustration of the average pooling operation with a 2 × 2 filter and stride.

Figure 3:

Flowchart of the proposed method. CNN, convolutional neural network; SFCM, spatial fuzzy clustering membership.
Flowchart of the proposed method. CNN, convolutional neural network; SFCM, spatial fuzzy clustering membership.

Figure 4:

Output of model training.
Output of model training.

Figure 5:

SAR1 image before change.
SAR1 image before change.

Figure 6:

SAR2 image after change.
SAR2 image after change.

Figure 7:

Pre-classification of SAR1 & SAR2 using space matrix calculation and SFCM. SFCM, spatial fuzzy clustering membership.
Pre-classification of SAR1 & SAR2 using space matrix calculation and SFCM. SFCM, spatial fuzzy clustering membership.

Figure 8:

Final change detection output.
Final change detection output.

Comparison with state-of-the-art methods

Methods Accuracy (%)
Proposed method 98.53
FCM [20] 91.29
PCAKM [20] 90.45
MRFFCM [20] 91.27
NR-ELM [21] 88.93
DBN [21] 87.22
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Engineering, Introductions and Overviews, Engineering, other
Journal RSS Feed