Research Article
BibTex RIS Cite

Meksika şapkası dalgacık görüntü bölütlemesi ve dalgacık entropisi tabanlı akıllı hedef tanıma

Year 2018, Volume: 9 Issue: 1, 13 - 26, 04.04.2018

Abstract

Bu çalışmada, X-band darbeli radar kullanılarak ölçülen gerçek hedef eko sinyallerinin dalga formlarından özellik çıkarımı ve sınıflandırma yapılmıştır. Bu amaçla, radar Hedef Eko (RHE) sinyallerinden elde edilen Zaman-Frekans Gösterimi (ZFG) imgelerinin entropi değerlerini kullanan bir özellik çıkarma mekanizması geliştirilmiştir. Bu özellik çıkarma mekanizması altı adımdan oluşmaktadır. Birinci adımda, yüksek çözünürlüklü radar hedef eko sinyallerinin ZFG imgeleri elde edilmiştir. Bu adımda, yüksek çözünürlüklü radar hedef eko sinyallerinin ZFG imgelerinin elde edilmesi için Meksika şapkası dalgacık skalaogramı kullanılmıştır. Daha sonra bu renkli imgeler gri imgelere dönüştürülmüştür. İkinci adımda, gri ZFG imgeleri Bulanık C-Ortalamalar algoritması kullanılarak bölütlenmiştir. Üçüncü adımda, Canny kenar tespit yöntemi kullanılarak bu gri seviye ZFG imgelerinin kenarları tespit edilmiştir. Dördüncü adımda, merkez kenar değişim yöntemi yardımı ile gri ZFG imgelerinin kenar piksellerinin merkez piksellerine olan uzaklığını temsil eden uzaklık vektörleri elde edilmiştir. Beşinci adımda, elde edilen uzaklık vektörlerinin her biri için bazı entropi değerleri hesaplanmıştır. Bu çalışmanın altıncı adımında, elde edilen özellik vektörünü kullanarak sınıflandırma işlemini gerçekleştirilmiştir. Bu amaçla ilk önce sırasıyla doğrusal sınıflandırıcılar olan K - En yakın Komşuluk (KEK) algoritması ve Bayes Karar Algoritması (BKA) ile sınıflandırma işlemi yapılmıştır ve sırasıyla % 74.92 ve % 79.08’ lik doğru sınıflandırma test başarımları elde edilmiştir. Daha sonra ise sınıflandırıcı olarak Çok Katmanlı ileri beslemeli Yapay Sinir Ağı (YSA) kullanılmıştır. Bu uygulama çalışması sonucunda kullanılan hedef nesneleri için % 88.8’ lik bir doğru sınıflandırma test başarımı elde edilmiştir.

References

  • Addison P. S., Watson J. N., and Feng T., (2002).Low-oscillation complex wavelets, Journal of Sound and Vibration, 254(4), 733-762.
  • Ahern G. J., Delisle Y., etc., (1989).Radar, Lab-Volt Ltd., vol. 1, p.p. 4-7.
  • Akay M., , (1997).Wavelet applications in medicine. IEEE Spectrum, 34, 50–56.
  • Avci E., Turkoglu I., Poyraz M., (2005). Intelligent Target Recognition on Based Wavelet Packet Neural Network, Experts Systems with Applications, 29(1).
  • Avci E. and Coteli R.. (2012)."A new automatic target recognition system based on wavelet extreme learning machine." Expert Systems with Applications 39.16, p. 12340-12348.
  • Bishop C.M., (1996). Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
  • Devaney A. J. and Hisconmez B., (1994). Wavelet signal processing for radar target identification a scale sequential approach, in Proc. SPIE Wavelet Applications, vol. 2242, pp. 389–399.
  • Devaney A. J., Raghavan R., Lev-Ari H., Manolakos E., and Kokar M., (1997). “Automatic Target Detection and Recognition: A Wavelet Based Approach,” Northeastern Univ. Defense Technical Inform. Center, Tech. Rep. AD-A329 696.
  • Etemad K. and Chellapa R., (1998). Separability-Based multiscale basis selection and feature extraction for signal and image classification, IEEE Trans. Image Processing, vol. 7, pp. 1453–1465.
  • Famili A., Wei-Min S., Weber R., and Simoudis E., (1997). “Data preprocessing and intelligent data analysis,” Intell. Data Anal., vol. 1.
  • Kulkarni A. D., (2001). Computer Vision and Fuzzy-Neural Network Systems, Prentice Hall PTR.
  • Lu J., Weaver J.B., D.M. Healy and Y. Xu, (1992).Noise reduction with multiscale edge representation and perceptual criteria, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale analysis, Victoria, BC, October.
  • Lu J., V. Algazi R., and R. Estes R. Jr., (1996). “Comparative study of wavelet image coders,” Opt. Eng., vol. 35, pp. 2605–2619
  • Mallat, S., (1991). Zero-Crossings of a wavelet transform, IEEE Tran. Inform. Theory, vol. 37, pp. 1019–1033.
  • Mallat S., (1998).A Wavelet Tour of Signal Processing, Academic Press, San Diego.
  • Misiti M., Nisiti Y., Oppenheim G., and Poggi J., 1996).Wavelet Toolbox User’s Guide. Natick, MA: MathWorks, Inc.
  • Muzy J. F., Bacry E., Arneodo A., (1992).Multifractal formalism for fractal signals: The structure-function approach versus the wavelet-transform modulus-maxima method, Physical Review E, Vol.47(2), 875-884.
  • Newland D.E., (1999).Ridge and Phase Identification in the Frequency Analysis of Transient Signals by Harmonic Wavelets, Transactions of the ASME, Journal of Vibrations and Acoustics, Vol.121, 149-155.
  • Panapakkam A.,.Balakrishnan S.N., Clair D.D., “Applications ofWavelets to Automatic Target Recognition,” Defense Technical Inform. Center, Tech. Rep. AD-A294 854, (1995).
  • Quiroga R. Q., (1998).Quantitative analysis of EEG signals: Time–frequency methods and Chaos theory. Lu¨beck: Intitute of Physiology, Medical University.
  • Shengqi L., et al., (2015).Multi-view radar target recognition based on multitask compressive sensing, Journal of Electromagnetic Waves and Applications 29(14), p. 1917-1934.
  • Stirman C. and Nachman A., (1991). “Applications of Wavelets to Radar Data Processing,” Defense Technical Inform. Center, Tech. Rep. AD-A239 297.
  • Staszewski W.J., (1998).Identification of non-linear systems using multi-scale ridges and skeletons of the wavelet transform’, Journal of Sound and Vibration, Vol.214(4), 639-658.
  • Strang G. and Nguyen T., (1996).Wavelets and Filter Banks. Wellesley, MA: Wellesley- Cambridge Press.
  • Szu H. H., (1996). Reviewof wavelet transforms for pattern recognition, Proc.SPIE Wavelet Applications III, vol. 2762, pp. 2–22.
  • Turkoglu I., Arslan A., Ilkay E., (2002). An expert system for diagnosis of the heart valve diseases, Expert Systems with Applications 23 pp. 229-236. Turkoglu I., Arslan A., Ilkay E., (2003).An Intelligent system for diagnosis of the heart valve diseases with wavelet packet neaural Networks, Computer in Biology and Medicine 33, pp. 319-331.
  • Wang L., K. Teo K., Lin Z., (2001).Predicting Time with Wavelet Packet Neural Networks, International Joint Conference on Neural Networks, Proceedings of the IJCNN’01, INNS-IEEE, Washington DC, Vol. 3, pp. 1593–1597.
  • Watson J. N., Addison P. S., and Sibbald A., (2000).Temporal filtering of NDT data using wavelet transforms, 14th ASCE Engineering Mechanics Conference.
  • Wei X., et al., (2016). Multiscale kernel sparse coding-based classifier for HRRP radar target recognition, IET Radar, Sonar & Navigation .
  • Yu G., Xiao H., and Fu Q.. (2016)."Least square support vector data description for HRRP-based radar target recognition." Applied Intelligence, 1(8).
  • Zhang Q., Benveniste A., (1992).Wavelet Network, IEEE Trans. Neural Networks 3 (6), 889–898.
Year 2018, Volume: 9 Issue: 1, 13 - 26, 04.04.2018

Abstract

References

  • Addison P. S., Watson J. N., and Feng T., (2002).Low-oscillation complex wavelets, Journal of Sound and Vibration, 254(4), 733-762.
  • Ahern G. J., Delisle Y., etc., (1989).Radar, Lab-Volt Ltd., vol. 1, p.p. 4-7.
  • Akay M., , (1997).Wavelet applications in medicine. IEEE Spectrum, 34, 50–56.
  • Avci E., Turkoglu I., Poyraz M., (2005). Intelligent Target Recognition on Based Wavelet Packet Neural Network, Experts Systems with Applications, 29(1).
  • Avci E. and Coteli R.. (2012)."A new automatic target recognition system based on wavelet extreme learning machine." Expert Systems with Applications 39.16, p. 12340-12348.
  • Bishop C.M., (1996). Neural Networks for Pattern Recognition, Clarendon Press, Oxford.
  • Devaney A. J. and Hisconmez B., (1994). Wavelet signal processing for radar target identification a scale sequential approach, in Proc. SPIE Wavelet Applications, vol. 2242, pp. 389–399.
  • Devaney A. J., Raghavan R., Lev-Ari H., Manolakos E., and Kokar M., (1997). “Automatic Target Detection and Recognition: A Wavelet Based Approach,” Northeastern Univ. Defense Technical Inform. Center, Tech. Rep. AD-A329 696.
  • Etemad K. and Chellapa R., (1998). Separability-Based multiscale basis selection and feature extraction for signal and image classification, IEEE Trans. Image Processing, vol. 7, pp. 1453–1465.
  • Famili A., Wei-Min S., Weber R., and Simoudis E., (1997). “Data preprocessing and intelligent data analysis,” Intell. Data Anal., vol. 1.
  • Kulkarni A. D., (2001). Computer Vision and Fuzzy-Neural Network Systems, Prentice Hall PTR.
  • Lu J., Weaver J.B., D.M. Healy and Y. Xu, (1992).Noise reduction with multiscale edge representation and perceptual criteria, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale analysis, Victoria, BC, October.
  • Lu J., V. Algazi R., and R. Estes R. Jr., (1996). “Comparative study of wavelet image coders,” Opt. Eng., vol. 35, pp. 2605–2619
  • Mallat, S., (1991). Zero-Crossings of a wavelet transform, IEEE Tran. Inform. Theory, vol. 37, pp. 1019–1033.
  • Mallat S., (1998).A Wavelet Tour of Signal Processing, Academic Press, San Diego.
  • Misiti M., Nisiti Y., Oppenheim G., and Poggi J., 1996).Wavelet Toolbox User’s Guide. Natick, MA: MathWorks, Inc.
  • Muzy J. F., Bacry E., Arneodo A., (1992).Multifractal formalism for fractal signals: The structure-function approach versus the wavelet-transform modulus-maxima method, Physical Review E, Vol.47(2), 875-884.
  • Newland D.E., (1999).Ridge and Phase Identification in the Frequency Analysis of Transient Signals by Harmonic Wavelets, Transactions of the ASME, Journal of Vibrations and Acoustics, Vol.121, 149-155.
  • Panapakkam A.,.Balakrishnan S.N., Clair D.D., “Applications ofWavelets to Automatic Target Recognition,” Defense Technical Inform. Center, Tech. Rep. AD-A294 854, (1995).
  • Quiroga R. Q., (1998).Quantitative analysis of EEG signals: Time–frequency methods and Chaos theory. Lu¨beck: Intitute of Physiology, Medical University.
  • Shengqi L., et al., (2015).Multi-view radar target recognition based on multitask compressive sensing, Journal of Electromagnetic Waves and Applications 29(14), p. 1917-1934.
  • Stirman C. and Nachman A., (1991). “Applications of Wavelets to Radar Data Processing,” Defense Technical Inform. Center, Tech. Rep. AD-A239 297.
  • Staszewski W.J., (1998).Identification of non-linear systems using multi-scale ridges and skeletons of the wavelet transform’, Journal of Sound and Vibration, Vol.214(4), 639-658.
  • Strang G. and Nguyen T., (1996).Wavelets and Filter Banks. Wellesley, MA: Wellesley- Cambridge Press.
  • Szu H. H., (1996). Reviewof wavelet transforms for pattern recognition, Proc.SPIE Wavelet Applications III, vol. 2762, pp. 2–22.
  • Turkoglu I., Arslan A., Ilkay E., (2002). An expert system for diagnosis of the heart valve diseases, Expert Systems with Applications 23 pp. 229-236. Turkoglu I., Arslan A., Ilkay E., (2003).An Intelligent system for diagnosis of the heart valve diseases with wavelet packet neaural Networks, Computer in Biology and Medicine 33, pp. 319-331.
  • Wang L., K. Teo K., Lin Z., (2001).Predicting Time with Wavelet Packet Neural Networks, International Joint Conference on Neural Networks, Proceedings of the IJCNN’01, INNS-IEEE, Washington DC, Vol. 3, pp. 1593–1597.
  • Watson J. N., Addison P. S., and Sibbald A., (2000).Temporal filtering of NDT data using wavelet transforms, 14th ASCE Engineering Mechanics Conference.
  • Wei X., et al., (2016). Multiscale kernel sparse coding-based classifier for HRRP radar target recognition, IET Radar, Sonar & Navigation .
  • Yu G., Xiao H., and Fu Q.. (2016)."Least square support vector data description for HRRP-based radar target recognition." Applied Intelligence, 1(8).
  • Zhang Q., Benveniste A., (1992).Wavelet Network, IEEE Trans. Neural Networks 3 (6), 889–898.
There are 31 citations in total.

Details

Primary Language Turkish
Journal Section Articles
Authors

Derya Avcı This is me

Resul Çöteli This is me

Publication Date April 4, 2018
Submission Date December 20, 2016
Published in Issue Year 2018 Volume: 9 Issue: 1

Cite

IEEE D. Avcı and R. Çöteli, “Meksika şapkası dalgacık görüntü bölütlemesi ve dalgacık entropisi tabanlı akıllı hedef tanıma”, DUJE, vol. 9, no. 1, pp. 13–26, 2018.
DUJE tarafından yayınlanan tüm makaleler, Creative Commons Atıf 4.0 Uluslararası Lisansı ile lisanslanmıştır. Bu, orijinal eser ve kaynağın uygun şekilde belirtilmesi koşuluyla, herkesin eseri kopyalamasına, yeniden dağıtmasına, yeniden düzenlemesine, iletmesine ve uyarlamasına izin verir. 24456