Abstract
Face recognition performance by computers has been shown to be more accurate than that of humans. However, a bias with soft-biometrics features has been detected. This bias reduces recognition performance when gender is used. Feature selection for gender classification from face images is a difficult problem since faces contain symmetrical and redundant features. We argue that traditional methods, based on mutual information using pairs of features to estimate the relevance and redundancy among features, fail to select the right set of features in cases where there are strong spatial correlations among features, which is the case with facial images. In this paper, a new method is proposed fusing a filter and a wrapper to measure the relationships among image features, and to select feature clusters based on mutual information for gender classification. We applied this method on nine face datasets using an SVM classifier. We were able to achieve 98.2% correct gender classification in the testing partition using the UND, 95.56% with the Morph II, 98.33% on the LFW, and 98.66% on celebA databases. We validated the results using a cross-test with three different datasets: COFW, Adience, and Image of Groups, that were not used to define the parameters of our method. Additionally, the method was tested with a Random Forest. All the results achieved are better than those previously published on the same databases, and with a significantly smaller number of total features.
Highlights
Face recognition (FR) has grown to become a prominent biometric technique for identity authentication and has been widely applied in many areas, such as airports, public security, and daily life [51].The National Institute of Standards and Technology (NIST) has run multiple facial recognition tests since 1993
We reported an extension of the use of feature selection based on computed Mutual Information (MI ) between pairs of features, or between features and classes, that reached the highest classification performance published at that time on the FERET database with 99.13% accuracy using 18,900 features, and on the UND database with 94.01% accuracy using 14,200 features
CONTRIBUTION In this paper, we propose a fusion of hybrid filter/wrapper method based on a relief method [38], [39] that employs weighted MI using the relationships among neighbor images applied to gender classification
Summary
1https://www.nist.gov/programs-projects/face-recognition-vendor-testfrvt-ongoing features [12], [13], [40], [61]. We briefly introduce some basic concepts and notions from information theory that are used in the proposed feature selection method. A. FEATURE SELECTION Feature selection involves selecting features from a dataset in order to improve classification accuracy and decrease computation complexity [29]. It is similar to feature extraction which involves the creation of feature vectors from the original dataset via manipulating data space. The latter technique may be considered a ‘‘superset’’ of feature selection [17], [29]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
