Show simple item record

dc.contributor.authorNunez-Iglesias, J
dc.contributor.authorKennedy, R
dc.contributor.authorParag, T
dc.contributor.authorShi, J
dc.contributor.authorChklovskii, DB
dc.date.accessioned2020-12-18T03:34:22Z
dc.date.available2020-12-18T03:34:22Z
dc.date.issued2013
dc.identifierpii: PONE-D-13-08935
dc.identifier.citationNunez-Iglesias, J., Kennedy, R., Parag, T., Shi, J. & Chklovskii, D. B. (2013). Machine learning of hierarchical clustering to segment 2D and 3D images.. PLoS One, 8 (8), pp.e71715-. https://doi.org/10.1371/journal.pone.0071715.
dc.identifier.issn1932-6203
dc.identifier.urihttp://hdl.handle.net/11343/255826
dc.description.abstractWe aim to improve segmentation through the use of machine learning tools during region agglomeration. We propose an active learning approach for performing hierarchical agglomerative segmentation from superpixels. Our method combines multiple features at all scales of the agglomerative process, works for data with an arbitrary number of dimensions, and scales to very large datasets. We advocate the use of variation of information to measure segmentation accuracy, particularly in 3D electron microscopy (EM) images of neural tissue, and using this metric demonstrate an improvement over competing algorithms in EM and natural images.
dc.languageeng
dc.publisherPublic Library of Science (PLoS)
dc.rights.urihttps://creativecommons.org/licenses/by/4.0
dc.titleMachine learning of hierarchical clustering to segment 2D and 3D images.
dc.typeJournal Article
dc.identifier.doi10.1371/journal.pone.0071715
melbourne.affiliation.departmentMedicine Dentistry & Health Sciences
melbourne.source.titlePLoS One
melbourne.source.volume8
melbourne.source.issue8
melbourne.source.pagese71715-
dc.rights.licenseCC BY
melbourne.elementsid1308779
melbourne.openaccess.pmchttp://www.ncbi.nlm.nih.gov/pmc/articles/PMC3748125
melbourne.contributor.authorNunez-Iglesias, Juan
dc.identifier.eissn1932-6203
melbourne.accessrightsOpen Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record