PDF, 226 kB

Full text of article: Russian language.

DOI: 10.18287/0134-2452-2014-38-1-154-158

Pages: 154-158.

Abstract:
We consider an algorithm of hyperspectral images thematic classification using conjugacy indicator as a proximity measure. This measure is a generalized spectral angle mapper (SAM) implemented in hyperspectral imagery processing software ENVI. In this case, we use the cosine of an angle between considered vector and subspace, which is spanned by class vectors, instead of the cosine of an angle between considered vector and the mean vector of the class. Paper describes modification of a method based on partitioning of the class into subclasses and based on reduction of vectors to zero mean value. The results of synthetic experiments show higher classification quality than SAM.

Key words:
hyperspecter imagery, classification, specter angle mapper, conjugacy indicator.

References:

1. Schowengerdt, R.A. Remote Sensing: Models and Methods for Image Processing / R.A. Schowengerdt. – М: Academic Press, 2006. – 560 p. – ISBN 978-0-12-369407-2.
2. Chaban, L.N. Modeling and thematic processing of images identical to the imagery from workable and preparing for the space launch hiperspectral remote sensors / L.N. Chaban, G.V. Vecheruk, T.V. Kondranin, S.V. Kudriavtsev, A.A. Nikolenko // Current Problems in Remote Sensing of the Earth from Space. – 2012. – Vol. 9, No. 2. – P. 111-121. – (In Russian).
   
3. ENVI 4.1 User’s Guide – Research System Inc., 2004. – 1150 p.
   
4. De Carvalho, O. A. Spectral correlation mapper (SCM): an improvement on the spectral angle mapper (SAM) / Osmar Abí­lio de Carvalho Jr., and Paulo Roberto Meneses // Summaries of the 9th JPL Airborne Earth Science Workshop, JPL Publication 00-18. – Pasadena, CA: JPL Publication, 2000. – Vol. 9. – 9 p.
   
5. Shafri, H. Z. M. The Performance of Maximum Likelihood, Spectral Angle Mapper, Neural Network and Decision Tree Classifiers in Hyperspectral Image Analysis / Helmi Zulhaidi Mohd Shafri, Suhaili Affendi, and Mansor Shattri // Journal of Computer Science. – 2007. – No. 3(6). – P. 419-423.
   
6. Fursov, V.A. Training in Pattern Recognition from a Small Number / Vladimir A. Fursov // Proc. 15th International Conference on Pattern recognition (ISPR) 2000, Barcelona, Spain. – 2000. – Vol. 2. – P. 119-121.
   
7. Fursov, V.A. Building of Classifiers Based on Conjugation Indices / V. A. Fursov, I. A. Kulagina, and N. E. Kozin // Optical Memory and Neural Networks (Information Optics). – 2007. – Vol. 16, No. 3. – P. 136-143.
   
8. Fursov, V. Building of Classifier Based on Conjugation Indexes / Vladimir Fursov, Irina Kulagina, Nikita Kozin. // Proceedings of The 5-th International Conference on Machine Learning and Data Mining. Leipzig, Germany, 18 - 20 July, 2007. –2007. – P. 231-235.
   
9. Kozin, N.E. Constructing of classifier for face recognition using conjugation indexes / N.E. Kozin, V.A. Fursov // Computer Optics. – 2005. – № 28. – P. 160-163. – (In Russian).
   
10. Fursov, V. Constructing of Classifier for Face Recognition on the Basis of the Conjugation Indexes / Vladimir Fursov, Nikita Kozin // Transactions on Engineering Computing and Technology. – 2006. – Vol. 13. – P. 72-74.
11. Fursov, V. Recognition through Constructing the Eigenface Classifiers using Conjugation Indices / Vladimir Fursov, Nikita Ko­zin // 2007 IEEE International Conference on Advanced Video and Signal based Surveillance London (United Kingdom), 5-7 September 2007. – 2007. – P. 465-469. – ISBN 978-1-4244-1696-7.

---

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20