Research Article
BibTex RIS Cite

Hiperspektral Görüntülerin Sınıflandırılmasında Farklı Boyut İndirgeme Yöntemlerinin Karşılaştırılması

Year 2021, Volume: 9 Issue: 1, 159 - 165, 29.01.2021
https://doi.org/10.21541/apjes.737192

Abstract

Günümüzde gittikçe önem kazanan uzaktan algılamada, araştırmacılar çeşitli spektral imzalar arasındaki ilişkileri bulmak için dünyanın yüzeyini temsil eden yüksek boyutlu verileri kullanırlar. Özellikle görüntüler, farklı malzemelerin özelliklerini yansıtan yüzlerce yüksek çözünürlüklü banttan oluşabilirler. Bununla birlikte, yüksek boyutlu uzayda çok sayıda farklı bantların bulunması, bu özelliklerin yorumlanmasını zorlaştırabilmektedir. Uzaktan algılama verilerinin ön-işlemesi için boyutsallık problemine bağlı olarak çeşitli zorluklar ile karşılaşılmaktadır. Bu alanda ortaya çıkan araştırmalar, bunun zor bir problem olduğunu ve tüm sorunlara tek bir çözüm olmadığını ortaya koymaktadır. Bununla birlikte, son çalışmalar katmanlı uzay öğrenme tekniklerinin hiperspektral görüntülerin ön işlemesinde çok önemli bir çözüm olduğunu göstermektedir. Bu çalışmada, en güncel katmanlı uzay yerleştirme yöntemlerinin hiperspektral veriler üzerindeki performansı karşılaştırmalı olarak analiz edilmiştir. Her bir yöntemin bu alanda en çok kullanılan iki farklı veri seti kullanılarak boyut indirgeme uygulaması gerçekleştirilmiş ve en yakın komşu (1NN) sınıflandırması ile performansı doğrulanmıştır. Elde edilen sonuçlara göre karşılaştırılan katmanlı uzay yerleştirme yöntemlerinin hiperspektral verilerin sınıflandırılmasında sınıf bazlı farklılıklar olsa da başarılı sonuçlar verdiği görülmektedir. Ayrıca her bir yöntemin çalışma zamanı grafik olarak sunulmuş ve hangi yöntemin daha hızlı çalıştığı sebepleriyle birlikte açıklanmıştır.

References

  • K. Pearson, “On lines and planes of closest fit to systems of points in space,” Philosophical Magazine, vol. 2, no. 11, pp. 559-572, 1901.
  • H. Hotelling, “Analysis of a complex of statistical variables into principal components,” Journal of Educational Psychology, vol. 24, pp. 417-441, 1933.
  • I. T. Joliiffe, “Principal component analysis in regression analysis,” Springer, vol. 2, pp. 129-155, 1986.
  • A. M. Martinez and A.C. Kak, “Pca versus lda,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 228-223, 2001.
  • W. Torgerson, “Multidimensional scaling I: theory and method,” Psychometrika, vol. 17, pp. 401-419, 1952.
  • M. Sugiyama, “Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis,” Journal of Machine Learning Research, vol. 8, pp. 1027-1061, 2007.
  • M. Sugiyama, T. Ide, S. Nakajima and J. Sese, “Semi-supervised local fisher discriminant analysis for dimensionality reduction,” Machine Learning, vol. 78, no. 1-2, pp. 35-61, 2010.
  • S. Roweis and L. K. Saul, “Nonlinear dimensionality reduction by locally linear embedding,” Science, vol. 290, pp. 2323-2326, 2000.
  • J. B. Tenenbaum, V. De Silva and J. Langford, “A global geometric framework for nonlinear dimensionality reduction,” Science, vol. 290, pp. 2319-2323, 2000.
  • M. Belkin and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Computation, vol. 15, no. 6, pp. 1373-1396, 2003.
  • Z. Zhag and H. Zha, “Principal manifolds and nonlinear dimensionality reduction via tangent space alignment,” SIAM Journal on Scientific Computing, vol. 26, no. 1, pp. 313-338, 2004.
  • L. Song, A. Smola, K. Borgwardt and A. Gretton, “Colored maxium variance unfolding,” Advances in Neural Information Processing Systems, vol. 21, pp. 1385-1392, 2008.
  • T. Kohonen and T. Honkela, “Kohonen network,” Scholarpedia, vol. 2, no. 1, pp. 1568, 2007.
  • G. Hinton and S. Roweis, “Stochastic neighbor embedding,” Advances in Neural Information Processing System, vol. 15, pp. 857-864, 2002.
  • L. V. D. Maaten and G. Hinton, “Visualizing data using t-sne,” Journal of Machine Learning Research, vol. 9, pp. 2579-2605, 2008.
  • D. Lunga and O. Ersoy, “Spherical stochastic neighbor embedding of hyperspectral data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 51, no. 2, pp. 857-871, 2013.
  • D. Lunga and O. Ersoy, “Multidimensional artificial field embedding with spatial sensitivity,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 2, pp. 1518-1532, 2014.
  • C. M. Bachmann, T. L. Ainsworth and R. A. Fusina, “Exploiting manifold geometry in hyperspectral imagery,” IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 3, pp. 441-454, 2005.
  • H. Huang and Y. Huang, “Improved discriminant sparsity neighborhood preserving embedding for hyperspectral image classification,” Neurocomputing, vol. 136, no. 1, pp. 224-234, 2014.
  • H. Huang, F. Luo, J. Liu and Y. Yang, “Dimensionality reduction of hyperspectral images based on sparse discriminant manifold embedding,” ISPRS Journal of Photogrammetry Remote Sensing, vol. 106, pp. 42-54, 2015.
  • C. Ozcan and O. Ersoy, “Enhanced multidimensional field embedding method by potential fields for hyperspectral image classification and visualization,” Electronics Letters, vol. 54, no. 12, pp. 756-758, 2018.
  • J. Cohen, “A coefficient of agreement for nominal scales,” Educational and Psychological Measurement, vol. 20, no. 1, pp. 37-46, 1960.

Comparison of Different Dimension Reduction Methods in Classification of Hyperspectral Images

Year 2021, Volume: 9 Issue: 1, 159 - 165, 29.01.2021
https://doi.org/10.21541/apjes.737192

Abstract

In remote sensing, which is becoming increasingly important today, researchers use high-dimensional data representing the surface of the earth to find relationships between various spectral signatures. In particular, images can consist of hundreds of high-resolution bands that reflect the properties of different materials. However, the presence of a large number of different bands in high-dimensional space can make interpretation of these features difficult. Various difficulties are encountered due to dimensionality problem for pre-processing of remote sensing data. Research in this area reveals that this is a difficult problem and not a single solution to all problems. However, recent studies show that manifold learning techniques are a very important solution in the preprocessing of hyperspectral images. In this study, the performance of the state-of-the-art manifold embedding methods on hyperspectral data is analyzed comparatively. The dimension reduction application of each method has been carried out by using two different data sets that are used most in this field and their performance have been verified by the nearest neighbor (1NN) classification. Even though there are class-based differences in the classification of hyperspectral data, it is seen that manifold embedding methods, which are compared according to the obtained results, yield successful results. In addition, the runtime of each method is presented graphically and explained along with the reasons for which method works faster.

References

  • K. Pearson, “On lines and planes of closest fit to systems of points in space,” Philosophical Magazine, vol. 2, no. 11, pp. 559-572, 1901.
  • H. Hotelling, “Analysis of a complex of statistical variables into principal components,” Journal of Educational Psychology, vol. 24, pp. 417-441, 1933.
  • I. T. Joliiffe, “Principal component analysis in regression analysis,” Springer, vol. 2, pp. 129-155, 1986.
  • A. M. Martinez and A.C. Kak, “Pca versus lda,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 228-223, 2001.
  • W. Torgerson, “Multidimensional scaling I: theory and method,” Psychometrika, vol. 17, pp. 401-419, 1952.
  • M. Sugiyama, “Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis,” Journal of Machine Learning Research, vol. 8, pp. 1027-1061, 2007.
  • M. Sugiyama, T. Ide, S. Nakajima and J. Sese, “Semi-supervised local fisher discriminant analysis for dimensionality reduction,” Machine Learning, vol. 78, no. 1-2, pp. 35-61, 2010.
  • S. Roweis and L. K. Saul, “Nonlinear dimensionality reduction by locally linear embedding,” Science, vol. 290, pp. 2323-2326, 2000.
  • J. B. Tenenbaum, V. De Silva and J. Langford, “A global geometric framework for nonlinear dimensionality reduction,” Science, vol. 290, pp. 2319-2323, 2000.
  • M. Belkin and P. Niyogi, “Laplacian eigenmaps for dimensionality reduction and data representation,” Neural Computation, vol. 15, no. 6, pp. 1373-1396, 2003.
  • Z. Zhag and H. Zha, “Principal manifolds and nonlinear dimensionality reduction via tangent space alignment,” SIAM Journal on Scientific Computing, vol. 26, no. 1, pp. 313-338, 2004.
  • L. Song, A. Smola, K. Borgwardt and A. Gretton, “Colored maxium variance unfolding,” Advances in Neural Information Processing Systems, vol. 21, pp. 1385-1392, 2008.
  • T. Kohonen and T. Honkela, “Kohonen network,” Scholarpedia, vol. 2, no. 1, pp. 1568, 2007.
  • G. Hinton and S. Roweis, “Stochastic neighbor embedding,” Advances in Neural Information Processing System, vol. 15, pp. 857-864, 2002.
  • L. V. D. Maaten and G. Hinton, “Visualizing data using t-sne,” Journal of Machine Learning Research, vol. 9, pp. 2579-2605, 2008.
  • D. Lunga and O. Ersoy, “Spherical stochastic neighbor embedding of hyperspectral data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 51, no. 2, pp. 857-871, 2013.
  • D. Lunga and O. Ersoy, “Multidimensional artificial field embedding with spatial sensitivity,” IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 2, pp. 1518-1532, 2014.
  • C. M. Bachmann, T. L. Ainsworth and R. A. Fusina, “Exploiting manifold geometry in hyperspectral imagery,” IEEE Transactions on Geoscience and Remote Sensing, vol. 43, no. 3, pp. 441-454, 2005.
  • H. Huang and Y. Huang, “Improved discriminant sparsity neighborhood preserving embedding for hyperspectral image classification,” Neurocomputing, vol. 136, no. 1, pp. 224-234, 2014.
  • H. Huang, F. Luo, J. Liu and Y. Yang, “Dimensionality reduction of hyperspectral images based on sparse discriminant manifold embedding,” ISPRS Journal of Photogrammetry Remote Sensing, vol. 106, pp. 42-54, 2015.
  • C. Ozcan and O. Ersoy, “Enhanced multidimensional field embedding method by potential fields for hyperspectral image classification and visualization,” Electronics Letters, vol. 54, no. 12, pp. 756-758, 2018.
  • J. Cohen, “A coefficient of agreement for nominal scales,” Educational and Psychological Measurement, vol. 20, no. 1, pp. 37-46, 1960.
There are 22 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Mehmet Zahid Yıldırım 0000-0003-2248-3683

Caner Özcan 0000-0002-2854-4005

Okan Ersoy 0000-0002-7626-0584

Publication Date January 29, 2021
Submission Date May 14, 2020
Published in Issue Year 2021 Volume: 9 Issue: 1

Cite

IEEE M. Z. Yıldırım, C. Özcan, and O. Ersoy, “Hiperspektral Görüntülerin Sınıflandırılmasında Farklı Boyut İndirgeme Yöntemlerinin Karşılaştırılması”, APJES, vol. 9, no. 1, pp. 159–165, 2021, doi: 10.21541/apjes.737192.