Classification of Hyperspectral Images Using Conventional Neural Networks

被引：5
|
作者：
Kozik, V., I [1 ]
Nezhevenko, E. S. [1 ]
机构：
[1] Russian Acad Sci, Inst Automat & Electrometry, Siberian Branch, Novosibirsk 630090, Russia
来源：
OPTOELECTRONICS INSTRUMENTATION AND DATA PROCESSING | 2021年 / 57卷 / 02期
关键词：
classification; hyperspectral imaging; principal components; convolutional neural networks; learning;
D O I：
10.3103/S8756699021020102
中图分类号：
O4 [物理学];
学科分类号：
0702 ;
摘要：
We show that for the classification of fragments of a hyperspectral image, it is very effective to first transform its spectral features into principal components and then to recognize it using a convolutional neural network trained on a sample composed of fragments of this image. High percentage of correct classification was obtained when working with a large-format hyperspectral image while some of the classes of the hyperspectral image are very close to each other and, accordingly, are difficult to distinguish by hyperspectra. We investigate the dependence of the correct classification on the change in the size of the fragments from which the training and validation samples are composed and on the parameters of the convolutional neural network.
引用
收藏
页码：123 / 131
页数：9
相关论文
共 50 条
  • [1] Classification of Hyperspectral Images Using Conventional Neural Networks
    V. I. Kozik
    E. S. Nezhevenko
    Optoelectronics, Instrumentation and Data Processing, 2021, 57 : 123 - 131
  • [2] Hyperspectral Image Classification with Convolutional Neural Networks
    Slavkovikj, Viktor
    Verstockt, Steven
    De Neve, Wesley
    Van Hoecke, Sofie
    Van de Walle, Rik
    MM'15: PROCEEDINGS OF THE 2015 ACM MULTIMEDIA CONFERENCE, 2015, : 1159 - 1162
  • [3] Pixel-Based Classification of Hyperspectral Images Using Convolutional Neural Networks
    Syed Aamer Hussain
    Ali Tahir
    Junaid Aziz Khan
    Ahmad Salman
    PFG – Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2019, 87 : 33 - 45
  • [4] Pixel-Based Classification of Hyperspectral Images Using Convolutional Neural Networks
    Hussain, Syed Aamer
    Tahir, Ali
    Khan, Junaid Aziz
    Salman, Ahmad
    PFG-JOURNAL OF PHOTOGRAMMETRY REMOTE SENSING AND GEOINFORMATION SCIENCE, 2019, 87 (1-2): : 33 - 45
  • [5] Classification of hyperspectral imagery with neural networks: comparison to conventional tools
    Erzsébet Merényi
    William H Farrand
    James V Taranik
    Timothy B Minor
    EURASIP Journal on Advances in Signal Processing, 2014
  • [6] Classification of hyperspectral imagery with neural networks: comparison to conventional tools
    Merenyi, Erzsebet
    Farrand, William H.
    Taranik, James V.
    Minor, Timothy B.
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2014,
  • [7] Classification of hyperspectral images with convolutional neural networks and probabilistic relaxation
    Gao, Qishuo
    Lim, Samsung
    COMPUTER VISION AND IMAGE UNDERSTANDING, 2019, 188
  • [8] Smart feature extraction and classification of hyperspectral images based on convolutional neural networks
    Hamouda, Maissa
    Ettabaa, Karim Saheb
    Bouhlel, Med Salim
    IET IMAGE PROCESSING, 2020, 14 (10) : 1999 - 2005
  • [9] Hyperspectral fruit and vegetable classification using convolutional neural networks
    Steinbrener, Jan
    Posch, Konstantin
    Leitner, Raimund
    COMPUTERS AND ELECTRONICS IN AGRICULTURE, 2019, 162 : 364 - 372
  • [10] SUPERRESOLUTION OF HYPERSPECTRAL IMAGES USING BACKPROPAGATION NEURAL NETWORKS
    Mianji, Fereidoun A.
    Zhang, Ye
    Babakhani, Asad
    PROCEEDINGS OF INDS '09: SECOND INTERNATIONAL WORKSHOP ON NONLINEAR DYNAMICS AND SYNCHRONIZATION 2009, 2009, 4 : 168 - +
12345