https://scholars.lib.ntu.edu.tw/handle/123456789/496986
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hsu, H.-W. | en_US |
dc.contributor.author | Lee, Y.-C. | en_US |
dc.contributor.author | Ding, J.-J. | en_US |
dc.contributor.author | Chang, R.Y. | en_US |
dc.contributor.author | JIAN-JIUN DING | en_US |
dc.creator | Hsu, H.-W.;Lee, Y.-C.;Ding, J.-J.;Chang, R.Y. | - |
dc.date.accessioned | 2020-06-04T07:43:54Z | - |
dc.date.available | 2020-06-04T07:43:54Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | https://scholars.lib.ntu.edu.tw/handle/123456789/496986 | - |
dc.description.abstract | Dolphin identification is important for wildlife conservation. Since identifying dolphins from thousands of images manually takes tremendous time, it is important to develop an automatic dolphin identification algorithm. In this paper, a high accurate deep learning based dolphin identification algorithm is proposed. We presented an advanced approach, called hybrid saliency method, for feature extraction and efficiently integrate several well-known techniques to make dolphins distinguishable. With the proposed techniques, we can avoid the background part (e.g.The sea water) to affect the identification results, which is usually a problem of most convolutional neural network based methods. Simulations show that the proposed algorithm can well identify a dolphin in most cases and it can achieve the accuracy rate of 85% even if there are 40 dolphins to be distinguished. © 2018 IEEE. | - |
dc.relation.ispartof | 2018 IEEE Asia Pacific Conference on Circuits and Systems, APCCAS 2018 | - |
dc.subject | computer vision; convolutional neural networks; marine vertebrate; photo-identification; saliency map | - |
dc.subject.classification | [SDGs]SDG14 | - |
dc.subject.other | Computer vision; Conservation; Convolution; Dolphins (structures); Image processing; Neural networks; Seawater; Accuracy rate; Convolutional neural network; Identification algorithms; marine vertebrate; Photo identification; Saliency detection; Saliency map; Wildlife conservation; Deep learning | - |
dc.title | Dolphin Recognition with Adaptive Hybrid Saliency Detection for Deep Learning Based on DenseNet Recognition | en_US |
dc.type | conference paper | en |
dc.identifier.doi | 10.1109/APCCAS.2018.8605718 | - |
dc.identifier.scopus | 2-s2.0-85062232093 | - |
dc.identifier.url | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062232093&doi=10.1109%2fAPCCAS.2018.8605718&partnerID=40&md5=8e334357ff724bad9ae9975fb5f37258 | - |
dc.relation.pages | 455-458 | - |
item.openairetype | conference paper | - |
item.openairecristype | http://purl.org/coar/resource_type/c_5794 | - |
item.fulltext | no fulltext | - |
item.grantfulltext | none | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | Communication Engineering | - |
crisitem.author.dept | Electrical Engineering | - |
crisitem.author.orcid | 0000-0003-4510-2273 | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
crisitem.author.parentorg | College of Electrical Engineering and Computer Science | - |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.