Age and Gender Estimation of Unfiltered Faces

Abstract

This paper concerns the estimation of facial attributes-namely, age and gender-from images of faces acquired in challenging, in the wild conditions. This problem has received far less attention than the related problem of face recognition, and in particular, has not enjoyed the same dramatic improvement in capabilities demonstrated by contemporary face recognition systems. Here, we address this problem by making the following contributions. First, in answer to one of the key problems of age estimation research-absence of datawe offer a unique data set of face images, labeled for age and gender, acquired by smart-phones and other mobile devices, and uploaded without manual filtering to online image repositories. We show the images in our collection to be more challenging than those offered by other face-photo benchmarks. Second, we describe the dropout-support vector machine approach used by our system for face attribute estimation, in order to avoid overfitting. This method, inspired by the dropout learning techniques now popular with deep belief networks, is applied here for training support vector machines, to the best of our knowledge, for the first time. Finally, we present a robust face alignment technique, which explicitly considers the uncertainties of facial feature detectors. We report extensive tests analyzing both the difficulty levels of contemporary benchmarks as well as the capabilities of our own system. These show our method to outperform state-of-the-art by a wide margin.Index Terms-Face recognition, identification of persons, support vector machines, neural networks. 1556-6013

Local Deep Neural Networks for gender recognition

“…All the hidden units are ReLU, and the dropout technique has been also applied to the last hidden layer. Eidinger et al (2014) 88.60 LBP+CH+SIFT SVM Fazl-Ersi et al (2014) 91.59…”

“…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).…”

Landmark-Guided Local Deep Neural Networks for Age and Gender Classification

“…There are 26,580 face images from 2284 persons in the Adience dataset [41]. The images are with age and gender labels, which are collected from the Flickr albums and released by their authors under the Creative Commons (CC) license.…”

A Gender Recognition System from Facial Image

“…Some sample images from LFW dataset are given in Figure 3. We have also used a relatively newly resealed adience dataset [6] to evaluate the result of our proposed method. The original dataset contains 26,580 face images of 2,284 different person.…”