Show simple item record

dc.contributor.authorAkbaş, C. E.en_US
dc.contributor.authorGünay, O.en_US
dc.contributor.authorTaşdemir K.en_US
dc.contributor.authorÇetin, A. E.en_US
dc.date.accessioned2018-04-12T11:13:52Z
dc.date.available2018-04-12T11:13:52Z
dc.date.issued2017en_US
dc.identifier.issn1863-1703
dc.identifier.urihttp://hdl.handle.net/11693/37453
dc.description.abstractWe propose a new family of vector similarity measures. Each measure is associated with a convex cost function. Given two vectors, we determine the surface normals of the convex function at the vectors. The angle between the two surface normals is the similarity measure. Convex cost function can be the negative entropy function, total variation (TV) function and filtered variation function constructed from wavelets. The convex cost functions need not to be differentiable everywhere. In general, we need to compute the gradient of the cost function to compute the surface normals. If the gradient does not exist at a given vector, it is possible to use the sub-gradients and the normal producing the smallest angle between the two vectors is used to compute the similarity measure. The proposed measures are compared experimentally to other nonlinear similarity measures and the ordinary cosine similarity measure. The TV-based vector product is more energy efficient than the ordinary inner product because it does not require any multiplications.en_US
dc.language.isoEnglishen_US
dc.source.titleSignal, Image and Video Processingen_US
dc.relation.isversionofhttp://dx.doi.org/10.1007/s11760-016-0949-7en_US
dc.subjectConvex cost functionsen_US
dc.subjectCosine similarity measuresen_US
dc.subjectl1 normen_US
dc.titleEnergy efficient cosine similarity measures according to a convex cost functionen_US
dc.typeArticleen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.citation.spage349en_US
dc.citation.epage356en_US
dc.citation.volumeNumber11en_US
dc.citation.issueNumber2en_US
dc.identifier.doi10.1007/s11760-016-0949-7en_US
dc.publisherSpringer Londonen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record