Show simple item record  

dc.contributor.authorMayo, Michael
dc.contributor.authorZhang, Edmond Yiwen
dc.coverage.spatialConference held at Christchurch, New Zealanden_NZ
dc.date.accessioned2009-05-21T01:45:00Z
dc.date.available2009-05-21T01:45:00Z
dc.date.issued2008
dc.identifier.citationMayo, M. & Zhang, E. (2008). Improving face gender classification by adding deliberately misaligned faces to the training data. In Proceeding of 23rd International Conference Image and Vision Computing New Zealand 2008 (IVCNZ 2008).en
dc.identifier.urihttps://hdl.handle.net/10289/2172
dc.description.abstractA novel method of face gender classifier construction is proposed and evaluated. Previously, researchers have assumed that a computationally expensive face alignment step (in which the face image is transformed so that facial landmarks such as the eyes, nose, chin, etc, are in uniform locations in the image) is required in order to maximize the accuracy of predictions on new face images. We, however, argue that this step is not necessary, and that machine learning classifiers can be made robust to face misalignments by automatically expanding the training data with examples of faces that have been deliberately misaligned (for example, translated or rotated). To test our hypothesis, we evaluate this automatic training dataset expansion method with two types of image classifier, the first based on weak features such as Local Binary Pattern histograms, and the second based on SIFT keypoints. Using a benchmark face gender classification dataset recently proposed in the literature, we obtain a state-of-the-art accuracy of 92.5%, thus validating our approach.en
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherIEEE Pressen_NZ
dc.relation.urihttp://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4762066en
dc.rights©2008 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.en
dc.subjectcomputer scienceen
dc.subjectgender classificationen
dc.subjectface detectionen
dc.subjectface alignmenten
dc.subjectface classificationen
dc.subjectSpatial Pyramiden
dc.subjectLocal Binary Patternen
dc.subjectSIFT keypointsen
dc.subjectSupport Vector Machinesen
dc.subjectimage classificationen
dc.subjectMachine learningen
dc.titleImproving face gender classification by adding deliberately misaligned faces to the training dataen
dc.typeConference Contributionen
dc.identifier.doi10.1109/IVCNZ.2008.4762066en
dc.relation.isPartOfImage and Vision Computing New Zealand, 23rd International Conferenceen_NZ
pubs.begin-page1en_NZ
pubs.elements-id18468
pubs.end-page5en_NZ
pubs.finish-date2008-11-28en_NZ
pubs.place-of-publicationdoi: 10.1109/IVCNZ.2008.4762066en_NZ
pubs.start-date2008-11-26en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record