An Evaluation of Local Feature Encodings for Shape Retrieval

dc.contributor.authorTasse, Flora Ponjouen_US
dc.contributor.authorKosinka, Jirien_US
dc.contributor.authorDodgson, Neil A.en_US
dc.contributor.editorA. Ferreira and A. Giachetti and D. Giorgien_US
dc.date.accessioned2016-05-04T16:04:58Z
dc.date.available2016-05-04T16:04:58Z
dc.date.issued2016en_US
dc.description.abstractLocal features are successfully used in 3D shape retrieval by encoding features descriptors into global shape signatures. Previous 3D retrieval systems use different encoding methods, such as histogram encoding and Fisher encodings, making it difficult to evaluate one encoding technique against another. We perform a comparative analysis of four recent encoding methods when used in shape retrieval. The analysis shows that Vector of Locally Aggregated Descriptors (VLAD) encoding is the best method of the four tested, since it offers the best trade-off between precision and computational cost.en_US
dc.description.sectionheadersFull Papersen_US
dc.description.seriesinformationEurographics Workshop on 3D Object Retrievalen_US
dc.identifier.doi10.2312/3dor.20161085en_US
dc.identifier.isbn978-3-03868-004-8en_US
dc.identifier.issn1997-0471en_US
dc.identifier.pages35-39en_US
dc.identifier.urihttps://doi.org/10.2312/3dor.20161085en_US
dc.publisherThe Eurographics Associationen_US
dc.titleAn Evaluation of Local Feature Encodings for Shape Retrievalen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
035-039.pdf
Size:
941.95 KB
Format:
Adobe Portable Document Format
Collections