Gender and Age Classification from Facial Images Using Deep Learning
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Computer Science
Date of Award
Summer 2016
Abstract
Gender and age classification from faces in digital images has become an active domain of research due to the myriad possible real-world applications in which it is essential to tailor a service to meet the needs of customers or viewers in an age appropriate and gender relevant manner. In view of the business demand and research endeavors in gender and age classification from facial images, we present to application developers and researchers in these fields a detailed comparative scientific analysis of the effects of different neural network architectures, different regularization techniques, and different cost functions on the performance of deep learning models for gender and age classification. Our experiments demonstrate the superior performance of convolutional neural networks in the tasks of gender classification. Our age classification experiments lay the ground work for future research on the effect of the use of different cost functions on the age classification performance of deep learning models.
Advisor
Sang C. Suh
Subject Categories
Computer Sciences | Data Science | Physical Sciences and Mathematics
Recommended Citation
Gharana, Dhiraj, "Gender and Age Classification from Facial Images Using Deep Learning" (2016). Electronic Theses & Dissertations. 781.
https://digitalcommons.tamuc.edu/etd/781
