A Novel Wavelet Filtering Method in SAR Image Classification by Neural Networks
This paper presents a method for classification of Synthetic Aperture Radar (SAR) images , based on the joint exploitation of a novel Wavelet Filtering Algorithm  and Neural Networks . An illustrative example is presented that shows how the use of the proposed technique of Wavelet Filtering allows both to mitigate negative effects of multiplicative noise (speckle) and to classify the considered image without resolution decrease. The proposed Wavelet Filtering, applied on the image, provides four images (an approximation image and three detail images); detail images have the same resolution as original image. The use of Wavelet Filtering (WF) on the detail images jointly to a Multilayer Feedforward Network allows us to reduce some of typical drawbacks of the SAR classification problems, and thus to have a more efficient tool with respect to the traditional approach. The proposed method is tested on a real SAR image, and it is compared with traditional approaches based on MLP use, and on FFT-2Dfiltering-MLP technique.
KeywordsInput Image Synthetic Aperture Radar High Pass Synthetic Aperture Radar Image Detail Image
Unable to display preview. Download preview PDF.
- A. Farina, F. Vinelli, “A Center of Excellence for SAR Signal Processing”, Alenia Technologies, Vol.1, No. 1, 1994Google Scholar
- N. Hess Nielsen, M.V. Wickerhauser, “Wavelets and Time-Frequency Analysis”, Proceedings of the IEEE, Vol.84, No. 4, pp.523–529Google Scholar
- Neural Networks, Special Issue on Automatic Target Recognition, Pergamon, Vol.8, No.7/8, 1995Google Scholar
- F.C. Morabito, G. Simone, “A Comparison of Feature Extraction Techniques for Remotely Sensed SAR Images Classification”, Proceedings of International Conference on Systems, Signals, Control, Computers (SSCC), Vol.2, pp. 107–110, Durban (South Africa), Sept. 1998Google Scholar
- A. Farina, F.C. Morabito, G. Simone, “Automated Lineament Detection in SAR Images based on the joint use of Wavelet and Hough Transforms”, accepted for publication Radar’ 99 International Conference, Brest (France), May 1999Google Scholar
- S. Barbarossa, L. Parodi, “SAR Image Classification by Wavelets”, Proc. of IEEE International Radar Conference, 1995, pp. 462–467Google Scholar
- M. Ceccarelli, A. Farina, A. Petrosino, R. Vaccaro, F. Vinelli, “SAR Image Segmentation using Textural Information and Neural Classifiers”, L’Onde Electrique, Vol.74, No.3, May 1994, pp.24–28.Google Scholar