期刊
PLOS ONE
卷 13, 期 1, 页码 -出版社
PUBLIC LIBRARY SCIENCE
DOI: 10.1371/journal.pone.0192011
关键词
-
资金
- Brazilian National Council for Scientific and Technological Development [141308/2014-1, 131488/2015-5, 311751/2013-0, 309115/2014-0]
- Coordination for the Improvement of Higher Education Personnel [23038.002884/2013-38]
- Sao Paulo Research Foundation [2014/13533-0]
Works requiring taxonomic knowledge face several challenges, such as arduous identification of many taxa and an insufficient number of taxonomists to identify a great deal of collected organisms. Machine learning tools, particularly convolutional neural networks (CNNs), are then welcome to automatically generate high-performance classifiers from available data. Supported by the image datasets available at the largest online database on ant biology, the AntWeb (www.antweb.org), we propose here an ensemble of CNNs to identify ant genera directly from the head, profile and dorsal perspectives of ant images. Transfer learning is also considered to improve the individual performance of the CNN classifiers. The performance achieved by the classifiers is diverse enough to promote a reduction in the overall classification error when they are combined in an ensemble, achieving an accuracy rate of over 80% on top-1 classification and an accuracy of over 90% on top-3 classification.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据