Document Type

Oral Presentation

Location

Ellensburg

Event Website

http://digitalcommons.cwu.edu/source/

Start Date

18-5-2016

End Date

19-5-2016

Keywords

Deep learning, gender classification

Abstract

Building software that can visually and accurately perceive gender from face images is an important step in making more intelligent machines. Several approaches to this problem have been suggested in the literature. We evaluate Histogram of Oriented Gradients, Dual Tree Complex Wavelet Transform (DTCWT) Principal Component Analysis (PCA) with Support Vector Machines (SVM) and compare them to Convolutional Neural Networks for this task. We train and test our classifiers with two benchmarks containing thousands of facial images. As expected, convolutional neural networks had the best performance while the performance of DTCWT varied most depending on the dataset used

Faculty Mentor(s)

Dr. Razvan Andonie

Department/Program

Computational Science

Share

COinS
 
May 18th, 12:00 AM May 19th, 12:00 AM

Automatic classification of perceived gender from face images

Ellensburg

Building software that can visually and accurately perceive gender from face images is an important step in making more intelligent machines. Several approaches to this problem have been suggested in the literature. We evaluate Histogram of Oriented Gradients, Dual Tree Complex Wavelet Transform (DTCWT) Principal Component Analysis (PCA) with Support Vector Machines (SVM) and compare them to Convolutional Neural Networks for this task. We train and test our classifiers with two benchmarks containing thousands of facial images. As expected, convolutional neural networks had the best performance while the performance of DTCWT varied most depending on the dataset used

http://digitalcommons.cwu.edu/source/2016/cos/2