No Cover Image

Book Chapter 265 views 46 downloads

Combining Stacked Denoising Autoencoders and Random Forests for Face Detection / Jingjing Deng; Xianghua Xie; Michael Edwards

Advanced Concepts for Intelligent Vision Systems, Volume: 10016, Pages: 349 - 360

Swansea University Author: Xie, Xianghua

DOI (Published version): 10.1007/978-3-319-48680-2_31

Abstract

In this work, we propose a novel method that uses stacked denoising autoencoders (SdA) for feature extraction and random forests (RF) for object-background classification in a classical cascading framework. This architecture allows much simpler neural network structures, resulting in efficient train...

Full description

Published in: Advanced Concepts for Intelligent Vision Systems
ISBN: 978-3-319-48679-6 978-3-319-48680-2
Published: 2016
URI: https://cronfa.swan.ac.uk/Record/cronfa32104
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: In this work, we propose a novel method that uses stacked denoising autoencoders (SdA) for feature extraction and random forests (RF) for object-background classification in a classical cascading framework. This architecture allows much simpler neural network structures, resulting in efficient training and detection. The proposed face detector was evaluated on two publicly available datasets and produced promising results.
Keywords: Deep Learning, Neural Network, Random Forests, Autoencoder, Face Detection, Machine Learning, Computer Vision
College: College of Science
Start Page: 349
End Page: 360