Rule based segmentation and subject identification using fiducial features and subspace projection methods

dc.citation.epage75en_US
dc.citation.issueNumber4en_US
dc.citation.spage68en_US
dc.citation.volumeNumber2en_US
dc.contributor.authorInce, E. A.en_US
dc.contributor.authorAli, S. A.en_US
dc.date.accessioned2016-02-08T10:14:03Z
dc.date.available2016-02-08T10:14:03Z
dc.date.issued2007en_US
dc.departmentComputer Technology and Information Systemsen_US
dc.description.abstractThis paper describes a framework for carrying out face recognition on a subset of standard color FERET database using two different subspace projection methods, namely PCA and Fisherfaces. At first, a rule based skin region segmentation algorithm is discussed and then details about eye localization and geometric normalization are given. The work achieves scale and rotation invariance by fixing the inter ocular distance to a selected value and by setting the direction of the eye-to-eye axis. Furthermore, the work also tries to avoid the small sample space (S3) problem by increasing the number of shots per subject through the use of one duplicate set per subject. Finally, performance analysis for the normalized global faces, the individual extracted features and for a multiple component combination are provided using a nearest neighbour classifier with Euclidean and/or Cosine distance metrics.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T10:14:03Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2007en
dc.identifier.issn1796-203X
dc.identifier.urihttp://hdl.handle.net/11693/23446
dc.language.isoEnglishen_US
dc.publisherAcademy Publisheren_US
dc.source.titleJournal of Computersen_US
dc.subjectColor FERET databaseen_US
dc.subjectFeature extractionen_US
dc.subjectGeometric normalizationen_US
dc.subjectSkin color segmentationen_US
dc.subjectSubspace analysis methodsen_US
dc.subjectDistance metricsen_US
dc.subjectEuclideanen_US
dc.subjectEye localizationen_US
dc.subjectFERET databaseen_US
dc.subjectFisher-facesen_US
dc.subjectGeometric normalizationen_US
dc.subjectMultiple componentsen_US
dc.subjectNearest-neighbour classifieren_US
dc.subjectNumber of shotsen_US
dc.subjectPerformance analysisen_US
dc.subjectRegion segmentationen_US
dc.subjectRule baseden_US
dc.subjectScale and rotationen_US
dc.subjectSkin-color segmentationen_US
dc.subjectSmall samplesen_US
dc.subjectSubject identificationen_US
dc.subjectSubspace analysisen_US
dc.subjectSubspace projection methodsen_US
dc.subjectFeature extractionen_US
dc.subjectFace recognitionen_US
dc.titleRule based segmentation and subject identification using fiducial features and subspace projection methodsen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Rule based segmentation and subject identification using fiducial features and subspace projection methods.pdf
Size:
619 KB
Format:
Adobe Portable Document Format
Description:
Full printable version