Face DetectNet: face detection via fully-convolutional network
Lapko A.V., Lapko V.A.

 

Institute of Computational Modeling of the Siberian Branch of the Russian Academy of Sciences, Russia, Krasnoyarsk,

Reshetnev Siberian State University of Science and Technology, Russia, Krasnoyarsk

 PDF

Abstract:
The paper deals with a new method of testing hypotheses for the distribution of multidimensional remote sensing spectral data. The proposed technique is based on the use of nonparametric algorithms for pattern recognition. Testing the hypothesis of the identity of two laws of distributions of multidimensional random variables is replaced by testing a hypothesis stating that the pattern recognition error equals 0.5. The application of this technique allows doing without the decomposition of the random variable domain into multidimensional intervals, which is typical for the Pearson criterion. Its effectiveness is confirmed by the results of testing the hypotheses of the distribution of spectral data of remote sensing in forestry. The analysis of the distribution laws for the following types of forestry is carried out: dark coniferous forest, damaged and dry forest stands. The initial information was obtained from the southern Siberia remote sensing data  using six spectral channels of Landsat. The results of the research form a basis for a set of significant spectral features when dealing with forest  condition monitoring.

Keywords:
testing a statistical hypothesis, multivariate random variables, pattern recognition, kernel density estimation, selecting bandwidth, spectral data, remote sensing, forest conditions.

Citation:
Lapko AV, Lapko VA. A technique for testing hypotheses for distributions of multidimensional spectral data using a nonparametric pattern recognition algorithm. Computer Optics 2019; 43(2): 238-244. DOI: 10.18287/2412-6179-2019-43-2-238-244.

References:

  1. Afanasyev AA, Zamyatin AV. Hybrid methods for automatic landscape change detection in noisy data environment. Computer Optics 2017; 41(3): 431-440. DOI: 10.18287/2412- 6179-2017-41-3-431-440.
  2. Vasin YuG, Yasakov YuV. Distributed database management system for integrated processing of spatial data in a GIS. Computer Optics 2016; 40(6): 919-928. DOI: 10.18287/2412- 6179-2016-40-6-919-928.
  3. Pugachev VS. Probability theory and mathematical statistics: textbook [In Russian]. Moscow: “Fizmatlit” Publisher; 2002.
  4. Lapko AV, Lapko VA. Nonparametric algorithms of pattern recognition in the problem of testing a statistical hypothesis on identity of two distribution laws of random variables. Optoelectronics, Instrumentation and Data Processing 2010; 46(6): 545-550. DOI: 10.3103/S8756699011060069.
  5. Lapko AV, Lapko VA. Comparison of empirical and theoretical distribution functions of a random variable on the basis of a nonparametric classifier. Optoelectronics, Instrumentation and Data Processing 2012; 48(1): 37-41. DOI: 10.3103/S8756699012010050.
  6. Lapko AV, Lapko VA. Analysis of asymptotic properties of nonparametric estimate of the equation of the separation surface in a two-alternative problem of pattern recognition. Optoelectronics, Instrumentation and Data Processing 2010; 46(3): 243-247. DOI: 10.3103/S8756699010030064.
  7. Lapko AV, Lapko VA, Sokolov MI, Chentsov SV. Nonparametric classification systems [In Russian]. Novosibirsk: “Nauka” Publisher; 2000.
  8. Fukunaga K. Introduction to statistical pattern recognition. San Diego: Academic Press; 1990.
  9. Theodoridis S, Koutroumbas K. Pattern recognition. Burlington, MA: Academic Press; 2009.
  10. Webb AR, Copsey KD. Statistical pattern recognition. Chichester: John Wiley & Sons, 2011.
  11. Parzen E. On estimation of a probability density function and mode. Ann Math Statistic 1962; 33(3): 1065-1076. DOI: 10.1214/aoms/1177704472.
  12. Epanechnikov VA. Nonparametric estimation of multidimensional probability density [In Russian]. Theory of Probability and its Applications 1969; 14(1): 156-161.
  13. Lapko AV, Lapko VA. Regression estimate of the multidimensional probability density and its properties. Optoelectronics, Instrumentation and Data Processing 2014; 50(2): 148-153. DOI: 10.3103/S875669901402006X.
  14. Lapko AV, Lapko VA. Nonparametric estimate of a parzen-type probability density with an implicitly specified form of the kernel. Measurement Techniques 2016; 59(6): 571-576. DOI: 10.1007/s11018-016-1010-5.
  15. Sheather SJ. Density estimation. Statistical Science 2004; 19(4): 588-597. DOI: 10.1214/088342304000000297.
  16. Scott DW. Multivariate density estimation: Theory, practice, and visualization. New Jersey: John Wiley & Sons, Inc; 2015.
  17. Chen S. Optimal bandwidth selection for kernel density functionals estimation. Journal of Probability and Statistics 2015; 2015(1): 1-21. DOI: 10.1155/2015/242683.
  18. Borrajo MI, González-Manteiga W, Martínez-Miranda MD. Bandwidth selection for kernel density estimation with length-biased data. Journal of Nonparametric Statistics 2017; 29(3): 636-668. DOI: 10.1080/10485252.2017.1339309.
  19. Lapko AV, Lapko VA. Fast algorithm for choosing kernel function blur coefficients in a nonparametric probability density estimate. Measurement Techniques 2018; 61(6): 540-545. DOI: 10.1007/s11018-018-1463-9.
  20. Sharakshaneh АS, Zheleznov IG, Ivnitskij VА. Complex system [In Russian]. Moscow: “Vysshaya shkola” Publisher; 1977.
  21. Kharuk VI, Im ST, Petrov IA, Dvinskaya ML, Fedotova EV, Ranson KJ. Fir decline and mortality in the southern siberian mountains. Regional Environmental Change 2017; 17(3): 803-812. DOI 10.1007/s10113-016-1073-5.
© 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