Доступ предоставлен для: Guest
Портал Begell Электронная Бибилиотека e-Книги Журналы Справочники и Сборники статей Коллекции
Journal of Flow Visualization and Image Processing
SJR: 0.11 SNIP: 0.312 CiteScore™: 0.1

ISSN Печать: 1065-3090
ISSN Онлайн: 1940-4336

Выпуски:
Том 26, 2019 Том 25, 2018 Том 24, 2017 Том 23, 2016 Том 22, 2015 Том 21, 2014 Том 20, 2013 Том 19, 2012 Том 18, 2011 Том 17, 2010 Том 16, 2009 Том 15, 2008 Том 14, 2007 Том 13, 2006 Том 12, 2005 Том 11, 2004 Том 10, 2003 Том 9, 2002 Том 8, 2001 Том 7, 2000 Том 6, 1999 Том 5, 1998 Том 4, 1997 Том 3, 1996 Том 2, 1995 Том 1, 1993

Journal of Flow Visualization and Image Processing

DOI: 10.1615/JFlowVisImageProc.2012005150
pages 97-111

BLIND FEATURE SELECTION AND EXTRACTION IN A 3D IMAGE CUBE

Muhammad Ahmad
Department of Computer Engineering, Kyung Hee University, South Korea
Syungyoung Lee
Department of Computer Engineering, Kyung Hee University, South Korea
Ihsan Ul Haq
Department of Electronics Engineering, International Islamic University (IIU), Pakistan
Qaisar Mushtaq
Department of Computer Science, National Textile University (NTU), Faisalabad, Pakistan

Краткое описание

As the number of spectral hands of high spectral resolution increases, the ability to detect more detailed classes should also increase, and the classification accuracy should increase as well. As the number of spectral bands becomes large, the limitation on performance imposed by the limited number of observed samples can become severe. A number of techniques for specific feature selection and extraction have been developed to reduce the dimensionality and target detection without the loss of class reparability. This suggests the need for reducing the dimensionality via a preprocessing method that takes into consideration the high dimensional feature space properties. Such reduction should enable the estimation of the feature extraction parameters to be more accurate bu using the technique referred to as the maximum conditional log likelihood estimation. This technique is able to bypass many of the problems of the limitation of small/large numbers of observed samples by making the computations in a lower dimensional space, and optimizing the function called the expectation and maximization. This method leads also to a high dimensional version of the feature selection and extraction algorithm, which requires significantly less computation than the normal procedure. A set of tests with real data evaluates the performance and illustrates the effectiveness of the proposed method. The entire work is done by using MATLAB.


Articles with similar content:

AUTOMATIC ESTIMATION OF SPATIALLY CORRELATED NOISE VARIANCE IN SPECTRAL DOMAIN FOR IMAGES
Telecommunications and Radio Engineering, Vol.73, 2014, issue 6
Benoit Vozel, V. V. Lukin, S. K. Abramov, A. A. Roenko, V. V. Abramova
EVALUATION OF THE RAINBOW VOLUMIC VELOCIMETRY (RVV) PROCESS BY SYNTHETIC IMAGES
Journal of Flow Visualization and Image Processing, Vol.14, 2007, issue 1
C. Cudel, Jean-Pierre Prenel, R. Malfara, Yannick Bailly
THE MULTI-SPECTRAL ENERGY BUNDLE METHOD APPLIED TO LINE-BY-LINE MONTE CARLO COMPUTATIONS
ICHMT DIGITAL LIBRARY ONLINE, Vol.0, 2016, issue
Andre J. Maurente, Yuri S. B. Freitas
BAYESIAN NONPARAMETRIC GENERAL REGRESSION
International Journal for Uncertainty Quantification, Vol.6, 2016, issue 3
Gilberto A. Ortiz, Ka Veng Yuen
DENOISING OF MULTICHANNEL IMAGES WITH REFERENCES
Telecommunications and Radio Engineering, Vol.76, 2017, issue 19
V. V. Lukin, S. K. Abramov, J. T. Astola, Karen O. Egiazarian, V. V. Abramova