Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/5412
Title: Within- and cross- database evaluations for face gender classification via befit protocols
Authors: Erdoğmuş, Nesli
Vanoni, Matthias
Marcel, Sebastien
Keywords: Local Binary Pattern Histogram Sequences
BeFIT protocols
Database experiments
Gender classification
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Erdoğmuş, 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.2014.6958797
Abstract: With 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.
Description: 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014; Jakarta; Indonesia; 22 September 2014 through 24 September 2014
URI: http://doi.org/10.1109/MMSP.2014.6958797
http://hdl.handle.net/11147/5412
ISMN: 9781479958962
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
5412.pdfConference Paper627.86 kBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

5
checked on Oct 1, 2022

Page view(s)

86
checked on Oct 3, 2022

Download(s)

126
checked on Oct 3, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.