Please use this identifier to cite or link to this item:
https://open.uns.ac.rs/handle/123456789/26705
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Brkljač, Branko | en_US |
dc.contributor.author | Panić, Marko | en_US |
dc.contributor.author | Ćulibrk, Dubravko | en_US |
dc.contributor.author | Crnojević, Vladimir | en_US |
dc.contributor.author | Ačanski, Jelena | en_US |
dc.contributor.author | Vujić, Ante | en_US |
dc.date.accessioned | 2020-12-13T21:01:59Z | - |
dc.date.available | 2020-12-13T21:01:59Z | - |
dc.date.issued | 2012 | - |
dc.identifier.uri | https://open.uns.ac.rs/handle/123456789/26705 | - |
dc.description.abstract | An novel approach to automatic hoverfly species discrimination based on detection and extraction of vein junctions in wing venation patterns of insects is presented in the paper. The dataset used in our experiments consists of high resolution microscopic wing images of several hoverfly species collected over a relatively long period of time at different geographic locations. Junctions are detected using histograms of oriented gradients and local binary patterns features. The features are used to train an SVM classifier to detect junctions in wing images. Once the junctions are identified they are used to extract simple statistics concerning the distances of these points from the centroid. Such simple features can be used to achieve automatic discrimination of four selected hoverfly species, using a Multi Layer Perceptron (MLP) neural network classifier. The proposed approach achieves classification accuracy of environ 71%. | en_US |
dc.language.iso | en | en_US |
dc.relation.ispartof | 1st International Conference on Pattern Recognition Applications and Methods , Vilamoura, Algarve, Portugal, 2012 | en_US |
dc.source | CRIS UNS | - |
dc.source.uri | http://cris.uns.ac.rs | - |
dc.subject | Species Discrimination : Wing Venation : Junctions Detection : Support Vector Machine : HOG : LBP. | en_US |
dc.title | Automatic Hoverfly Species Discrimination | en_US |
dc.type | Conference Paper | en_US |
dc.identifier.doi | 10.5220/0003756601080115 | - |
dc.identifier.url | https://www.cris.uns.ac.rs/record.jsf?recordId=67461&source=BEOPEN&language=en | - |
dc.description.version | Unknown | en_US |
dc.identifier.externalcrisreference | (BISIS)67461 | - |
item.fulltext | No Fulltext | - |
item.grantfulltext | none | - |
crisitem.author.dept | Departman za energetiku, elektroniku i telekomunikacije | - |
crisitem.author.dept | Institut BioSense | - |
crisitem.author.dept | Departman za industrijsko inženjerstvo i menadžment | - |
crisitem.author.dept | Institut BioSense | - |
crisitem.author.dept | Institut BioSense | - |
crisitem.author.dept | Departman za biologiju i ekologiju | - |
crisitem.author.orcid | 0000-0002-7993-6826 | - |
crisitem.author.orcid | 0000-0001-7144-378X | - |
crisitem.author.orcid | 0000-0003-1745-6410 | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
crisitem.author.parentorg | Univerzitet u Novom Sadu | - |
crisitem.author.parentorg | Fakultet tehničkih nauka | - |
crisitem.author.parentorg | Univerzitet u Novom Sadu | - |
crisitem.author.parentorg | Univerzitet u Novom Sadu | - |
crisitem.author.parentorg | Prirodno-matematički fakultet | - |
Appears in Collections: | FTN Publikacije/Publications |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.