A New Application for Gabor Filters in Face-Based
Gender Classification
Ebrahim Al-Wajih
and Moataz Ahmed
Information and Computer Science Department, King
Fahd University of Petroleum and Minerals, KSA
Abstract:Human
face is one of the most important biometrics as it contains information such as
gender, race, and age. Identifying the gender based on human face images is a
challenging problem that has been extensively studied due to its various relevant
applications. Several approaches were used to address this problem by
specifying suitable features. In this study, we present an extension of feature
extraction technique based on statistical aggregation and Gabor filters. We
extract statistical features from the image of a face after applying Gabor
filters; subsequently, we use seven classifiers to investigate the performance
of the selected features. Experiments show that the accuracy achieved using the
proposed features is comparable to accuracies reported in recent studies. We
used seven classifiers to investigate the performance of our proposed features.
Experiments reveal that k-Nearest Neighbors algorithm (k-NN), K-Star classifier
(K*), and Rotation Forest offer the best accuracies.
Keywords: Gabor
filters, gender recognition, statistical features, PCA.
Received September 25, 2017; accepted May 3,
2018
https://doi.org/10.34028/iajit/17/2/5