Robust binary neural networks based 3D Face detection and accurate face registration

DOI

10.1080/18756891.2013.802873How to use a DOI?

Keywords

3D Face, Facial Feature Extraction, Face Registration, Binary Neural Networks, Correlation Matrix Memories, Iterative Closest Point

Abstract

In this paper, we propose a facial feature localization algorithm based on a binary neural network technique - k-Nearest Neighbour Advanced Uncertain Reasoning Architecture (kNN AURA) to encode, train and match the feature patterns to accurate identify the nose tip in 3D. Based on the results of the 3D nose tip localization, the main face area is detected and cropped from the original 3D image. Then we present a novel framework to implement the 3D face registration by several integrated phases. First we use Principal Component Analysis (PCA) to roughly correct the server misalignment. Then we exploit the symmetric of human face to reduce the misalignment about and axis. In order to reduce the effect of facial expression variations, the expression-invariant region is segmented. Using Iterative Closest Point (ICP) algorithms, the expression-invariant region of faces can be aligned according to a standard face model, the misalignment about is then eventually corrected. Our experiments performed on the FRGC v2 database which contains pose and expression variations show that our approach outperforms the current state-of-the-art techniques both in the nose tip localization and face registration.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - JOUR
AU  - Quan Ju
PY  - 2013
DA  - 2013/07/01
TI  - Robust binary neural networks based 3D Face detection and accurate face registration
JO  - International Journal of Computational Intelligence Systems
SP  - 669
EP  - 683
VL  - 6
IS  - 4
SN  - 1875-6883
UR  - https://doi.org/10.1080/18756891.2013.802873
DO  - 10.1080/18756891.2013.802873
ID  - Ju2013
ER  -