Improving the accuracy of  classification of multispectral Images using an anisotropic diffusion neural network algorithm

Zeaieanfirouzabadi, Parviz; Tavakkoli Sabour, Mohammdad; Torkamani Asl, Behnaz

doi:10.66224/jgst.15.3.91

[Home ] [Archive]

[ فارسی ]

Journal of Geomatics Science and Technology

Main Menu

Home

Browse

Journal Info

Guide for Authors

Submit Manuscript

Articles archive

For Reviewers

Contact us

Site Facilities

Reviewers

Search in website

Receive site information

Volume 15, Issue 3 (3-2026)

JGST 2026, 15(3): 91-104

Back to browse issues page

Improving the accuracy of classification of multispectral Images using an anisotropic diffusion neural network algorithm

Parviz Zeaieanfirouzabadi ^*

, Mohammdad Tavakkoli Sabour

, Behnaz Torkamani Asl

Abstract: (225 Views)

Classification of remote sensing images for the interpretation and preparation of thematic maps is one of the most important topics in the science of remote sensing. Given the importance of this process in extracting information from multispectral satellite images, the present study aims to improve the accuracy of satellite image classification by utilizing the Anisotropic Diffusion Neural Network (ADNN) algorithm along with texture information obtained from wavelet transformation. This method modifies the pixel values of the input image with a sequential weighted average based on neighboring pixels in the input bands. In other words, this algorithm acts as a spatially and temporally variable low-pass filter. The mentioned algorithm transfers the input multispectral image to five levels of scale/resolution. This algorithm can simultaneously process the spectral information of the image and the texture details obtained from the wavelet transformation in a multi-scale representation. In this study, Landsat 8 Level 2 and Sentinel 2 images from the Miandoab area in West Azerbaijan province were used. After extracting different levels of images through the ADNN algorithm, the classification of the resulting images into four classes (soil, water, vegetation, and residential area) was carried out using the Support Vector Machine (SVM) algorithm. Additionally, to evaluate the performance of the images obtained from the ADNN algorithm on the original image, classification using the Artificial Neural Network (ANN) method was also conducted. Finally, by selecting the best level, unsupervised classification using FCM (Fuzzy C-means clustering) was applied to the selected image.

The results of this research indicate that the highest Kappa classification in Landsat 8 image belongs to the Level 2 image of the ADFN algorithm with an accuracy of 86%, which shows a higher accuracy compared to the classification of the Level 2 image with an Artificial Neural Network (ANN) with a Kappa of 0.83. Additionally, this algorithm also showed similar performance in the Sentinel 2 sensor image with a Kappa of 0.83 at Level 2. It should be noted that the use of this algorithm in remote sensing image classification has not been significantly addressed in internal and external articles. For instance, in previous studies, only wavelet transformation and neural network based on anisotropic diffusion were used for change detection. Also, the Superpixel Segmentation algorithm based on anisotropic diffusion (ADS) has been introduced to improve the boundary accuracy of superpixels and correct boundary deviations in complex remote sensing images. So far, the accuracy of this algorithm has not been compared in similar studies. This confirms the innovation of this research in applying the Anisotropic Diffusion Neural Network (ADNN) algorithm to improve the classification accuracy of satellite images.

Article number: 6

Keywords: Unsupervised classification, Anisotropic diffusion neural network, Multispectral Images, Multi-Level classification, Remote Sensning

Full-Text [PDF 2395 kb] (76 Downloads)

Type of Study: Research | Subject: Photo&RS
Received: 2022/08/27 | Accepted: 2026/03/16

References

1. A. Ehsani, and M. Shakeryari, " Determining the optimal method of land use classification and mapping by comparing artificial neural network algorithms and support vector machines using satellite data (Case study: Hamoon International Wetland)", Environmental Science and Technology, Volume 20, 2018 [Persian].

2. S. Nixon, Mark, and S. Aguado Alberto, " Feature Extraction and Image Processing", Academic Press, Elsevier Ltd., 2000.

3. D. Lu, , and Q. Weng, "A survey of image classification methods and techniques for improving classification performance", International Journal of Remote Sensing",28(5),823-87,2007, https://doi.org/10.1080/01431160600746456 [DOI:10.1080/01431160600746456.]

4. K. Zhang, Y. Chen, W. Wang, Y. Wu, B. Wang, and Y. Yan, "A method for remote sensing image classification by combining Pixel Neighborhood Similarity and optimal feature combination", Geocarto International, VOL. 38, NO. 1, 2158948, 2023, https://doi.org/10.1080/10106049.2022.2158948 [DOI:10.1080/10106049.2022.2158948.]

5. M. Pasternak, and K.Pawluszek-Filipiak, "The Evaluation of Spectral Vegetation Indexes and Redundancy Reduction on the Accuracy of Crop Type Detection", Appl. Sci., 12, 5067, 2022, https://doi.org/10.3390/app12105067 [DOI:10.3390/ app12105067.]

6. P. Zeaieanfirouzabadi, and M. Salahian, , " Introducing Shape Descriptors of Spectral Reflectance Curve (DSRC) for Improving Image Classification Accuracy", ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., X-5/W2-2025, 725-731, 2025, https://doi.org/10.5194/isprs-annals-X-5-W2-2025-725-2025 [DOI:10.5194/isprs-annals-X-5-W2-2025-725-2025, 2025.]

7. J. Bendiktsson, E. Swain, and O. Ersoy, , "Neural network approaches versus statistical methods on classification of multisource remote sensing data". IEEE Transactions on Geoscience and Remote Sensing, 28, 540-552, 1990 [DOI:10.1109/TGRS.1990.572944]

8. G. Carpenter, and S. Grossberg, "A massively parallel architecture for a self-organizing neural pattern recognition machine", Computer Vision, Graphics, and Image Processing, 37, 54-115, 1987. [DOI:10.1016/S0734-189X(87)80014-2]

9. G. Carpenter, and S. Grossberg, "ART2: Self-organization of a stable category recognition codes for analog input patterns", Applied Optics, 26, 4919-4930, 1987. [DOI:10.1364/AO.26.004919]

10. G.Carpenter, and S.Grossberg, "ART3: Hierarchical search using chemical transmitters in self-organizing patter recognition architectures", Neural Networks, 3(2), 129-152, 1990. [DOI:10.1016/0893-6080(90)90085-Y]

11. G. Carpenter, and S. Grossberg, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system", Neural Networks, 4, 759-771, 1991. [DOI:10.1016/0893-6080(91)90056-B]

12. G. Carpenter, S. Grossberg, and D.Rosen, "Fuzzy-ART: An adaptative resonance algorithm for rapid, stable classification of analog patterns", International Conference on Neural Networks, pp. 416, Seattle, WA, USA, 1991.

13. J. Favela, J. Torres, H. Hidalgo, and R. Granillo, " Loadbalancing for the neural network classification of remote sensing data in an heterogeneous network of workstations", Proc. 7th International Conference on Parallel and Distributed Processing, pp. 302-307, Las Vegas, NA, USA, 1994.

14. S. Grossberg, "Studies of Mind and Brain. Boston", Reidel, MA: D., 1982. [DOI:10.1007/978-94-009-7758-7]

15. Y. Hara, R. Atkins, S. Yueh, , R. Shin, and J. Kong, "Application of neural networks to radar image classification". IEEE Transactions on Geoscience and Remote Sensing, 32(1), 10-l09, 1994. [DOI:10.1109/36.285193]

16. E. Heermann, and N. Khazenie, "Classification of multi-spectral remote sensing data using a back-propagation neural network", IEEE Transactions on Geoscience and Remote Sensing, 30(1),81-8, 1992. [DOI:10.1109/36.124218]

17. G. Hepner," Artificial neural network classification using a minimal training set: comparison to conventional supervised classification", Photogrametric Engineering and Remote Sensing, 56(4), 469-473, 1990.

18. Y. Pao, " Pattern Recognition and Neural Networks", Addison-Wesley, Reading, MA, 1989.

19. J. Richards, " Remote Sensing Digital Image Analysis", Springer-Vedag, New York, NY, 1986. [DOI:10.1007/978-3-662-02462-1]

20. J. Tones, "Application of Remote Sensing for the recognition of geomorphic units in the Colorado River Delta", M.Sc. Thesis, Universidad Autonoma de Baja California, Mexico, 1994 [in Spanish].

21. Y.Wang, R. Niu, and X. Yu, "Anisotropic Diffusion for Hyperspectral Imagery Enhancement. " IEEE Sens J., 10(3):469-77, 2010. [DOI:10.1109/JSEN.2009.2037800]

22. R.A. Fernandesl, and M.E. Jernigan," Unsupervised Segmentation of Multi-Level Multispectral Images", Neural Networks for Signal Processing II Proceedings of the 1992 IEEE Workshop. pp. 363-372, 1992. [DOI:10.1109/NNSP.1992.253676]

23. J. Daryaei, "Digital Change Detection Using Multi-scale Wavelet Transformation & Neural Network", MSC Thesis. In International Institute for Aerospace survey and Earth Sciences(ITC) , 2003.

24. H. Richmond, "PCI Geomatics User's Guide. " Ontario, Canada, 2008.

25. P. Perona, and J. Malik, "Scale-space and edge detection using anisotropic diffusion. " IEEE Trans Pattern Anal Mach Intell., 12(7):629-39, 1990 [DOI:10.1109/34.56205]

26. A.P. Witkin, "Scale-Space Filtering", International Joint Conference on Artificial Intelligence, 2, 1019-1021, 1983.

27. J. Canny,"A Computational Approach to Edge Detection. " , IEEE Trans Pattern Anal Mach Intell, 1986. [DOI:10.1109/TPAMI.1986.4767851]

28. M. Lenone, , G. Mercier. and L. Hubert-Moy, "Nonlinear filtering of hyperspectral images with anisotropic diffusion". IEEE International Geoscience and Remote Sensing Symposium, 2018.

29. K. Pope, and S.T. Actone," Modified mean curvature motion for multispectral anistropic diffusion", IEEE Southwest Symposium on Image Analysis and Interpretation, 1998.

30. Y. Wang, L. Zhang. and P. LI, " Nonlinear multispectral anisotropic diffusion filters for remote sensed images based on MDL and morphology", IEEE International Geoscience and Remote Sensing Symposium, 2005.

31. B. Smolka, and R. Lukac, "On the combined forward and backward anisotropic diffusion scheme for the multispectral image enhancement" , The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2002. [DOI:10.1007/3-540-45479-9_8]

32. Z. Guo, J. Sun., D. Zhang. and B. Wu, "Adaptive Perona-Malik Model Based on the Variable Exponent for Image Denoising", IEEE Transactions on Image Processing. a Publication of the IEEE Signal Processing Society. 2012 Mar;21(3):958-967. DOI: 10.1109/tip.2011.2169272. PMID: 21947525, 2011. [DOI:10.1109/TIP.2011.2169272]

33. G. Wright, "Feature Selection For Texture Discrimination", M.A.Sc. Thesis, Department of Systems Design, University of Waterloo, Canada, 1988

34. S. Mallat, "A Theory of Multiresolution Signal Decomposition: the Wavelet Representation" , IEEE Trans. PAMI, Vol. II, No. 7, pp. 572-693,1989. [DOI:10.1109/34.192463]

Send email to the article author

Add your comments about this article

‎ 10.66224/jgst.15.3.91

Mendeley

Zotero

RefWorks

Zeaieanfirouzabadi P, Tavakkoli Sabour M, Torkamani Asl B. Improving the accuracy of classification of multispectral Images using an anisotropic diffusion neural network algorithm. JGST 2026; 15 (3) : 6
URL: http://jgst.issgeac.ir/article-1-1108-en.html

Rights and permissions
	This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Volume 15, Issue 3 (3-2026)

Back to browse issues page