2018年2月20日
Automatic estimation of deterioration level on transmission towers via deep extreme learning machine based on local receptive field
Proceedings - International Conference on Image Processing, ICIP
- ,
- ,
- ,
- 巻
- 2017-
- 号
- 開始ページ
- 2379
- 終了ページ
- 2383
- 記述言語
- 英語
- 掲載種別
- 研究論文(国際会議プロシーディングス)
- DOI
- 10.1109/ICIP.2017.8296708
- 出版者・発行元
- IEEE Computer Society
This paper presents an automatic estimation method of deterioration levels on transmission towers via Deep Extreme Learning Machine based on Local Receptive Field (DELM-LRF). Although Convolutional Neural Network (CNN) requires a large number of training images, it is difficult to prepare a sufficient number of training images of transmission towers. Thus, we generate a novel estimation method which enables training from a small number of training images. Specifically, we automatically extract image features based on Local Receptive Field (LRF) which combines convolution and pooling without using hand-craft features and estimate deterioration levels via Deep Extreme Learning Machine (DELM), which is a part of efficient deep learning methods. The derivation of DELM-LRF is the biggest contribution of this paper, and it can be trained from less training images compared to CNN. Experimental results show the effectiveness of DELM-LRF for the estimation of deterioration levels on transmission towers. Consequently, the proposed method makes it possible to approach challenging tasks with high expertise having difficulty in preparing enough images.
- リンク情報
-
- DOI
- https://doi.org/10.1109/ICIP.2017.8296708
- DBLP
- https://dblp.uni-trier.de/rec/conf/icip/MaedaTOH17
- Web of Science
- https://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=JSTA_CEL&SrcApp=J_Gate_JST&DestLinkType=FullRecord&KeyUT=WOS:000428410702101&DestApp=WOS_CPL
- URL
- http://dblp.uni-trier.de/db/conf/icip/icip2017.html#conf/icip/MaedaTOH17
- Scopus
- https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85045308560&origin=inward
- Scopus Citedby
- https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85045308560&origin=inward
- ID情報
-
- DOI : 10.1109/ICIP.2017.8296708
- ISSN : 1522-4880
- DBLP ID : conf/icip/MaedaTOH17
- SCOPUS ID : 85045308560
- Web of Science ID : WOS:000428410702101