Better Kohonen Neural Network in Radar Images Compression
Naval University, Śmidowicza 69, Gdynia, Poland
e-mail: T.Praczyk@amw.gdynia.pl
Received:
Rec. 1 September 2005
DOI: 10.12921/cmst.2006.12.02.157-164
OAI: oai:lib.psnc.pl:624
Abstract:
Maritime radar image may be a basis for a perspective ship position fixing system. Images obtained from navigational radars possess usually great amount of information. Using all of these information is usually practically impossible. It is necessary to compress information imbedded in each image to the size acceptable from the practical point of view. Such an effect may be obtained by application of feature extraction methods. This article presents one of such methods that is based on capabilities of modified self-organizing Kohonen neural network.
Key words:
References:
[1] Y. Freund, H. Seung, E. Shamir and N. Tihsby, Selective sampling using the query by committee algorithm, Machine Learning, 28, 133-168 (1997).
[2] B. Fritzke, A growing neural gas network learns topologies, Advances in Neural Information Processing Systems, MIT Press, Cambridge, (1995).
[3] J. Korbicz, A. Obuchowicz, D. Uciński, Artificial neural networks, AOW PLJ, Warsaw (1994) (In Polish).
[4] G. Kuchariew, Processing and analysis of digital images, Szczecin Univ. of Technology, Szczecin (1999) (In Polish).
[5] S. Osowski, Neural networks in algorithmic sense, WNT, Warsaw (1996) (In Polish).
[6] T. Praczyk, Radar images compression for the need of a positioning coastal system and an assessment of this process, Annual of Navigation, no. 8, Gdynia (2004).
[7] T. Praczyk, The method of extraction of characteristic points from the radar image of the sea shore for the needs of positioning system, Annual of Navigation, no. 8, Gdynia (2004).
[8] T. Praczyk, Kohonen neural network in radar images compression, Scientific Bulletin no. 1, 2003, Naval University of Gdynia, Gdynia (2003).
[9] T. Praczyk, GRNN in radar images compression, Scientific Bulletin no. 3, 2003, Naval University of Gdynia, Gdynia (2003).
[10] W. Skarbek, Methods of digital images representation, AOW PLJ, Warsaw (1993) (In Polish).
[11] A. Stateczny, Comparative navigation, Gdańsk Scientific Society, Gdańsk (2001) (In Polish).
[12] A. Stateczny and T. Praczyk, Artificial neural networks in radar image compression, Iternational Radar Symposium IRS, 2003, Drezno (2003).
[13] R. Tadeusiewicz and M. Flesiński, Imane recognition, PWN, Warszawa (1991) (In Polish).
Maritime radar image may be a basis for a perspective ship position fixing system. Images obtained from navigational radars possess usually great amount of information. Using all of these information is usually practically impossible. It is necessary to compress information imbedded in each image to the size acceptable from the practical point of view. Such an effect may be obtained by application of feature extraction methods. This article presents one of such methods that is based on capabilities of modified self-organizing Kohonen neural network.
Key words:
References:
[1] Y. Freund, H. Seung, E. Shamir and N. Tihsby, Selective sampling using the query by committee algorithm, Machine Learning, 28, 133-168 (1997).
[2] B. Fritzke, A growing neural gas network learns topologies, Advances in Neural Information Processing Systems, MIT Press, Cambridge, (1995).
[3] J. Korbicz, A. Obuchowicz, D. Uciński, Artificial neural networks, AOW PLJ, Warsaw (1994) (In Polish).
[4] G. Kuchariew, Processing and analysis of digital images, Szczecin Univ. of Technology, Szczecin (1999) (In Polish).
[5] S. Osowski, Neural networks in algorithmic sense, WNT, Warsaw (1996) (In Polish).
[6] T. Praczyk, Radar images compression for the need of a positioning coastal system and an assessment of this process, Annual of Navigation, no. 8, Gdynia (2004).
[7] T. Praczyk, The method of extraction of characteristic points from the radar image of the sea shore for the needs of positioning system, Annual of Navigation, no. 8, Gdynia (2004).
[8] T. Praczyk, Kohonen neural network in radar images compression, Scientific Bulletin no. 1, 2003, Naval University of Gdynia, Gdynia (2003).
[9] T. Praczyk, GRNN in radar images compression, Scientific Bulletin no. 3, 2003, Naval University of Gdynia, Gdynia (2003).
[10] W. Skarbek, Methods of digital images representation, AOW PLJ, Warsaw (1993) (In Polish).
[11] A. Stateczny, Comparative navigation, Gdańsk Scientific Society, Gdańsk (2001) (In Polish).
[12] A. Stateczny and T. Praczyk, Artificial neural networks in radar image compression, Iternational Radar Symposium IRS, 2003, Drezno (2003).
[13] R. Tadeusiewicz and M. Flesiński, Imane recognition, PWN, Warszawa (1991) (In Polish).