DSpace@nitr >
National Institue of Technology- Rourkela >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/2080/1765

Full metadata record

DC FieldValueLanguage
contributor.authorKumari, S-
contributor.authorBakshi, S-
contributor.authorMajhi, B-
date.accessioned2012-10-09T11:10:28Z-
date.available2012-10-09T11:10:28Z-
date.issued2012-04-
identifier.citationInternational Conference on Modelling Optimization and Computing (ICMOC 2012)en
identifier.urihttp://hdl.handle.net/2080/1765-
descriptionCopyright belongs to Elsevieren
description.abstractIn recent years, the research over emerging trends of biometric has grabbed a lot of attention. Periocular biometric is one such field. Researchers have made attempts to extract computationally intensive local features from high quality periocular images. In contrast, this paper proposes a novel approach of extracting global features from periocular region of poor quality grayscale images for gender classification. Global gender features are extracted using independent component analysis and are evaluated using conventional neural network techniques, and further their performance is compared. All relevant experiments are held on periocular region cropped from FERET face database. The results exhibit promising classification accuracy establishing the fact that the approach can work in fusion with existing facial gender classification systems to help in improving its accuracy.en
format.extent415540 bytes-
format.mimetypeapplication/pdf-
language.isoen-
publisherElsevieren
subjectPeriocular biometricen
subjectGender Classificationen
subjectICAen
subjectBPNNen
subjectRBFNNen
subjectPNNen
titlePeriocular Gender Classification using Global ICA Features for Poor Quality Imagesen
typeArticleen
Appears in Collections:Conference Papers

Files in This Item:

File Description SizeFormat
dspace_Periocular Gender Classification using Global ICA Features for Poor Quality Images.pdf405KbAdobe PDFView/Open

Show simple item record

All items in DSpace are protected by copyright, with all rights reserved.

 

Powered by DSpace Feedback