Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/1961
Title: Comparison of Three Different Cnn Architectures for Age Classification
Authors: Aydoğdu, Mehmet Fatih
Çelik, Vakkas
Demirci, Muhammed Fatih
Keywords: Face recognition
Estimation
Age classification
Publisher: IEEE
Source: Aydogdu, M. F., Celik, V., & Demirci, M. F. (2017, January). Comparison of three different cnn architectures for age classification. In 2017 IEEE 11th International Conference on Semantic Computing (ICSC) (pp. 372-377). IEEE.
Abstract: As one of the powerful tools of machine learning, Convolutional Neural Network (CNN) architectures are used to solve complex problems like image recognition, video analysis and natural language processing. In this paper, three different CNN architectures for age classification using face images are compared. The Morph dataset containing over 55k images is used in experiments and success of a 6-layer CNN and 2 variants of ResNet with different depths are compared. The images in the dataset are divided into 6 different age classes. While 80% of the images are used in training of the networks, the rest of the 20% is used for testing. The performance of the networks are compared according to two different criteria namely, the ability to make the estimation pointing the exact age classes of test images and the ability to make the estimation pointing the exact age classes or at most neighboring classes of the images. According to the performance results obtained, with 6-layer network, it is possible to estimate the exact or neighboring classes of the images with less than 5% error. It is shown that for a 6 class age classification problem 6-layer network is more successful than the deeper ResNet counterparts since 6-layer network is less susceptible to overfitting for this problem.
Description: 11th IEEE International Conference on Semantic Computing (2017 : San Diego, CA)
URI: https://ieeexplore.ieee.org/document/7889565/
https://hdl.handle.net/20.500.11851/1961
ISBN: 978-1-5090-4284-5
ISSN: 2325-6516
Appears in Collections:Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record



CORE Recommender

SCOPUSTM   
Citations

9
checked on Dec 21, 2024

WEB OF SCIENCETM
Citations

15
checked on Nov 9, 2024

Page view(s)

90
checked on Dec 16, 2024

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.