Show simple item record

dc.contributor.authorErdoğmuş, Nesli
dc.contributor.authorVanoni, Matthias
dc.contributor.authorMarcel, Sebastien
dc.date.accessioned2017-04-26T13:16:45Z
dc.date.available2017-04-26T13:16:45Z
dc.date.issued2014
dc.identifier.citationErdoğmuş, N., Vanoni, M., and Marcel, S. (2014, September 22-24). Within- and cross- database evaluations for face gender classification via befit protocols. Paper presented at the 16th IEEE International Workshop on Multimedia Signal Processing. doi:10.1109/MMSP.2014.6958797en_US
dc.identifier.ismn9781479958962
dc.identifier.urihttp://doi.org/10.1109/MMSP.2014.6958797
dc.identifier.urihttp://hdl.handle.net/11147/5412
dc.description16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014; Jakarta; Indonesia; 22 September 2014 through 24 September 2014en_US
dc.description.abstractWith its wide range of applicability, gender classification is an important task in face image analysis and it has drawn a great interest from the pattern recognition community. In this paper, we aim to deal with this problem using Local Binary Pattern Histogram Sequences as feature vectors in general. Differently from what has been done in similar studies, the algorithm parameters used in cropping and feature extraction steps are selected after an extensive grid search using BANCA and MOBIO databases. The final system which is evaluated on FERET, MORPH-II and LFW with gender balanced and imbalanced training sets is shown to achieve commensurate and better results compared to other state-of-the-art performances on those databases. The system is additionally tested for cross-database training in order to assess its accuracy in real world conditions. For LFW and MORPH-II, BeFIT protocols are used. © 2014 IEEE.en_US
dc.description.sponsorshipSwiss National Science Foundation under National Centre of Competence in Research (NCCR) on IM2; Scientific and Technological Research Council of Turkey (TUBITAK) on 2236en_US
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.relation.isversionof10.1109/MMSP.2014.6958797en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectLocal Binary Pattern Histogram Sequencesen_US
dc.subjectBeFIT protocolsen_US
dc.subjectDatabase experimentsen_US
dc.subjectGender classificationen_US
dc.titleWithin- and cross- database evaluations for face gender classification via befit protocolsen_US
dc.typeconferenceObjecten_US
dc.contributor.authorIDTR248937en_US
dc.contributor.institutionauthorErdoğmuş, Nesli
dc.relation.journal16th IEEE International Workshop on Multimedia Signal Processingen_US
dc.contributor.departmentİYTE, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.identifier.scopusSCOPUS:2-s2.0-84914141914
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record