KOPRI Repository

Convolutional Neural Network Based Image Classification: A CaseStudy in the Polar Regions

Metadata Downloads
Title
Convolutional Neural Network Based Image Classification: A CaseStudy in the Polar Regions
Other Titles
Convolutional Neural Network Based Image Classification: A CaseStudy in the Polar Regions
Authors
Chi, Junhwa
Kim, Hyun-cheol
Issue Date
2017
Citation
Chi, Junhwa, Kim, Hyun-cheol. 2017. Convolutional Neural Network Based Image Classification: A CaseStudy in the Polar Regions. Asia Data Week 2017. 제주 롯데호텔. 2017.11.20~2017.11.24.
Abstract
Along with recent advances in hardware, techniques, optimisation skills, and sufficient data, deep learning (DL) has recently become a new trend in the machine learning community because of its potential for learning representations of data better using multiple layers instead of shallow architectures. Among diverse approaches in DL, this study focuses on convolutional neural network (CNN), which is powerful for image classification, to identify landcover types in optical remote sensing (RS) images. Two applications in the Polar regions are demonstrated: 1) sea ice type classification and 2) vegetation classification. To evaluate the performance of CNN, traditional classifiers such as k-nearest neighbor and support vector machine are tested. In both cases, CNN significantly outperforms the traditional methods. Thousands of hidden features in deep layers developed by CNN properly remedy the limitations of the optical RS data, and play an important role in improving classification accuracy and generating thematic maps.
URI
http://repository.kopri.re.kr/handle/201206/8253
Conference Name
Asia Data Week 2017
Conference Place
제주 롯데호텔
Conference Date
2017.11.20~2017.11.24
Files in This Item
General Conditions
      ROMEO Green
    Can archive pre-print and post-print or publisher's version/PDF
      ROMEO Blue
    Can archive post-print (ie final draft post-refereeing) or publisher's version/PDF
      ROMEO Yellow
    Can archive pre-print (ie pre-refereeing)
      ROMEO White
    Archiving not formally supported

    qrcode

    Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

    Browse