Finding optimal neural networks for land use classification

被引：40
|
作者：
Bischof, H [1 ]
Leonardis, A
机构：
[1] Vienna Tech Univ, Pattern Recognit & Image Proc Grp, A-1040 Vienna, Austria
[2] Univ Ljubljana, Fac Comp & Informat Sci, Ljubljana, Slovenia
来源：
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 1998年 / 36卷 / 01期
关键词：
Gaussian maximum likelihood classifier; land use classification; minimum description length (MDL); multilayer perceptron; optimizing neural networks;
D O I：
10.1109/36.655348
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
In this communications, we present a fully automatic and computationally efficient algorithm based on the minimum description length principle (MDL) for optimizing multilayer perceptron (MLP) classifiers. We demonstrate our method on the problem of multispectral Landsat image classification. We compare our results with a hand-designed MLP and a Gaussian maximum likelihood classifier, in which our method produces better classification accuracy with a smaller number of hidden units.
引用
收藏
页码：337 / 341
页数：5
相关论文
共 50 条
  • [1] Granular neural networks for land use classification
    Vasilakos, A
    Stathakis, D
    SOFT COMPUTING, 2005, 9 (05) : 332 - 340
  • [2] Granular neural networks for land use classification
    Athanassios Vasilakos
    Demetris Stathakis
    Soft Computing, 2005, 9 : 332 - 340
  • [3] Land-Use Classification Using Convolutional Neural Networks
    A. M. Stepchenko
    Automatic Control and Computer Sciences, 2021, 55 : 358 - 367
  • [4] The use of backpropagating artificial neural networks in land cover classification
    Kavzoglu, T
    Mather, PM
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (23) : 4907 - 4938
  • [5] Land-Use Classification Using Convolutional Neural Networks
    Stepchenko, A. M.
    AUTOMATIC CONTROL AND COMPUTER SCIENCES, 2021, 55 (04) : 358 - 367
  • [6] A Framework for Evaluating Land Use and Land Cover Classification Using Convolutional Neural Networks
    Carranza-Garcia, Manuel
    Garcia-Gutierrez, Jorge
    Riquelme, Jose C.
    REMOTE SENSING, 2019, 11 (03)
  • [7] Land Use and Land Cover Classification Using Recurrent Neural Networks with Shared Layered Architecture
    Vignesh, T.
    Thyagharajan, K. K.
    Jeyavathana, R. Beaulah
    Kanimozhi, K., V
    2021 INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND INFORMATICS (ICCCI), 2021,
  • [8] Optimal design of neural networks for land-cover classification from multispectral imagery
    Silván-Cárdenas, JL
    IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING IX, 2004, 5238 : 420 - 431
  • [9] Land use/cover classification through multiresolution segmentation and object oriented neural networks classification
    Rocha, Jorge
    Tenedorio, Jose A.
    Encarnacao, Sara
    Morgado, Paulo
    REMOTE SENSING FOR ENVIRONMENTAL MONITORING, GIS APPLICATIONS AND GEOLOGY VI, 2006, 6366
  • [10] Satellite image land use classification in the south of France with the aid of neural networks
    Canty, MJ
    Kappas, M
    Klaus, D
    Poth, A
    Voss, M
    PHYSICAL MEASUREMENTS AND SIGNATURES IN REMOTE SENSING, VOLS 1 AND 2, 1997, : 691 - 696
12345