Please use this identifier to cite or link to this item:
Title: Gender recognition from face images with trainable COSFIRE filters
Authors: Azzopardi, George
Greco, Antonio
Vento, Mario
Keywords: Human face recognition (Computer science)
Image processing
Computer vision
Issue Date: 2016-08
Publisher: Institute of Electrical and Electronics Engineers Inc.
Citation: Azzopardi, G., Greco, A., & Vento, M. (2016). Gender recognition from face images with trainable COSFIRE filters. 13th International Conference on Advanced Video and Signal-Based Surveillance(AVSS) 2016, Colorado, US. 235-241.
Abstract: Gender recognition from face images is an important application in the fields of security, retail advertising and marketing. We propose a novel descriptor based on COSFIRE filters for gender recognition. A COSFIRE filter is trainable, in that its selectivity is determined in an automatic configuration process that analyses a given prototype pattern of interest. We demonstrate the effectiveness of the proposed approach on a new dataset called GENDER-FERET with 474 training and 472 test samples and achieve an accuracy rate of 93.7%. It also outperforms an approach that relies on handcrafted features and an ensemble of classifiers. Furthermore, we perform another experiment by using the images of the Labeled Faces in the Wild (LFW) dataset to train our classifier and the test images of the GENDERFERET dataset for evaluation. This experiment demonstrates the generalization ability of the proposed approach and it also outperforms two commercial libraries, namely Face++ and Luxand.
Appears in Collections:Scholarly Works - FacICTAI

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.85 MBAdobe PDFView/Open Request a copy

Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.