Determining Age and Gender from Face Images by Deep Learning and Random Forests

Abstract

Recently due to the rise of social platforms more and more people start focusing on the analysis of human's face Age and gender are two of the facial attributes that plays fundamental roles in social interactions Although the performance of classifying age and gender in constrained face images is fine and almost saturated the tasks of uncontrolled images remain challenging In this thesis a two-stage classifier is proposed First a deep convolutional neural network (CNN) pretrained on a massive dataset for face identification is used as the initial model The model is then fine-tuned on smaller datasets Instead of directly performing classification the model acts as a feature extractor After obtaining the feature random forest is applied for the final classification The method is evaluated on the Adience benchmark for age and gender estimation and on the Labeled Faces in the Wild (LFW) dataset for gender estimation It shows that our method outperforms the methods that use only CNN for classification

Date of Award	2018 Jul 25
Original language	English
Supervisor	Shen-Chuan Tai (Supervisor)