Boosting Sex Identification Performance

Abstract

Abstract. This paper presents a method based on AdaBoost to identify the sex of a person from a low resolution grayscale picture of their face. The method described here is implemented in a system that will process well over 10 9 images. The goal of this work is to create an efficient system that is both simple to implement and maintain; the methods described here are extremely fast and have straightforward implementations. We achieve 80% accuracy in sex identification with less than 10 pixel comparisons and 90% accuracy with less than 50 pixel comparisons. The best classifiers published to date use Support Vector Machines; we match their accuracies with as few as 500 comparison operations on a 20×20 pixel image. The AdaBoost based classifiers presented here achieve over 93% accuracy; these match or surpass the accuracies of the SVM-based classifiers, and yield performance that is 50 times faster.

Local Deep Neural Networks for gender recognition

“…The handcrafted features found in the literature for gender recognition can be as simple as the raw pixels (Moghaddam and Yang (2002)) or pixel differences (Baluja and Rowley (2007)). Sometimes, simple features are pooled together as in (Kumar et al (2009)), where image intensities in RGB and HSV color spaces, edge magnitudes, and gradient directions were combined.…”

“…For instance, the AdaBoost and the SVM algorithms have been widely used in the literature (Baluja and Rowley (2007); Shan (2012); Eidinger et al (2014)). In this spirit, an excellent comparison of gender recognition techniques using different methods can be found in Dago-Casas et al (2011).…”

Robust gender recognition by exploiting facial attributes dependencies

“…Gender is perhaps the most widely studied facial demographic attribute in the Computer Vision field (Moghaddam and Yang, 2002;Baluja and Rowley, 2007;Mäkinen and Raisamo, 2008;Bekios-Calfa et al, 2011). The state-ofthe-art recognition rate for the Color FERET database (Phillips et al, 2000) involving frontal faces with frontal illumination and 5 fold cross-validation is around 93% using either a Support Vector Machine with Radial Basis function (Moghaddam and Yang, 2002), pair-wise comparison of pixel values within a boosting framework (Baluja and Rowley, 2007) or linear discriminant techniques (Bekios-Calfa et al, 2011).…”

“…The state-ofthe-art recognition rate for the Color FERET database (Phillips et al, 2000) involving frontal faces with frontal illumination and 5 fold cross-validation is around 93% using either a Support Vector Machine with Radial Basis function (Moghaddam and Yang, 2002), pair-wise comparison of pixel values within a boosting framework (Baluja and Rowley, 2007) or linear discriminant techniques (Bekios-Calfa et al, 2011). This performance drops significantly if classifiers are trained and tested on different databases.…”

Can Gender Be Predicted from Near-Infrared Face Images?

“…In the realm of biometrics, gender is viewed as a soft biometric trait that can be used to index databases or enhance the recognition accuracy of primary traits such as face [6]. Predicting gender based on human faces has been extensively studied in the literature [14,1]. Two popular methods are due to Moghaddam et al [14] who utilize a support vector machine (SVM) for gender classification of thumbnail face images, and Baluja et al [1] who present the use of Adaboost for predicting gender.…”