Convolutional Neural Networks Applied to Human Face Classification

Convolutional neural network models have covered a broad scope of computer vision applications, achieving competitive performance with minimal domain knowledge. In this work, we apply such a model to a task designed to deter automated systems. We trained a convolutional neural network to distinguish...

Full description

Saved in:
Bibliographic Details
Published in2012 Eleventh International Conference on Machine Learning and Applications Vol. 2; pp. 580 - 583
Main Author Cheung, B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2012
Subjects
Avatars
captcha
convolutional neural networks
deep learning
Face
face recognition
Humans
Learning systems
Machine learning
Mathematical model
Support vector machines
Online AccessGet full text
ISBN1467346519
9781467346511
DOI10.1109/ICMLA.2012.177

Cover

More Information
Summary:Convolutional neural network models have covered a broad scope of computer vision applications, achieving competitive performance with minimal domain knowledge. In this work, we apply such a model to a task designed to deter automated systems. We trained a convolutional neural network to distinguish between images of human faces from computer generated avatars as part of the ICMLA 2012 Face Recognition Challenge. The network achieved a classification accuracy of 99% on the Avatar CAPTCHA dataset. Furthermore, we demonstrated the potential of utilizing support vector machines on the same problem and achieved equally competitive performance.
ISBN:1467346519
9781467346511
DOI:10.1109/ICMLA.2012.177