Bio-Inspired Hybrid Framework for Multi-view Face Detection

N McCarroll, Ammar Belatreche, Jim Harkin, Y Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Reliable face detection in completely uncontrolled settings still remains a challenging task. This paper introduces a novel hybrid learning strategy that achieves robust in-plane and out-of-plane multi-view face detection through the enhanced implementation of the hierarchical bio-inspired HMAX framework using spiking neurons. Through multiple training trials, separate pools of neurons are trained on different face poses to extract features through feed-forward unsupervised STDP. The trained neurons are then processed by an additional STDP mechanism to generate a streamlined repository of broadly tuned multi-view neurons. After unsupervised feature extraction, supervised feature selection is implemented within the hybrid framework to reduce false positives. The hybrid system achieves robust invariant detection of in-plane and out-of-plane rotated faces that compares favourably with state-of-the-art face detection systems.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages232-239
Number of pages8
Publication statusPublished - 1 Nov 2015
Event22nd International Conference on Neural Information Processing (ICONIP2015) -
Duration: 1 Nov 2015 → …

Conference

Conference22nd International Conference on Neural Information Processing (ICONIP2015)
Period1/11/15 → …

Fingerprint

Face recognition
Neurons
Feature extraction
Hybrid systems

Keywords

  • Spiking neural networks
  • face detection
  • pose estimation
  • multi-view

Cite this

McCarroll, N., Belatreche, A., Harkin, J., & Li, Y. (2015). Bio-Inspired Hybrid Framework for Multi-view Face Detection. In Unknown Host Publication (pp. 232-239)
McCarroll, N ; Belatreche, Ammar ; Harkin, Jim ; Li, Y. / Bio-Inspired Hybrid Framework for Multi-view Face Detection. Unknown Host Publication. 2015. pp. 232-239
@inproceedings{eb252a1872754dc7ba5254a8cef0a597,
title = "Bio-Inspired Hybrid Framework for Multi-view Face Detection",
abstract = "Reliable face detection in completely uncontrolled settings still remains a challenging task. This paper introduces a novel hybrid learning strategy that achieves robust in-plane and out-of-plane multi-view face detection through the enhanced implementation of the hierarchical bio-inspired HMAX framework using spiking neurons. Through multiple training trials, separate pools of neurons are trained on different face poses to extract features through feed-forward unsupervised STDP. The trained neurons are then processed by an additional STDP mechanism to generate a streamlined repository of broadly tuned multi-view neurons. After unsupervised feature extraction, supervised feature selection is implemented within the hybrid framework to reduce false positives. The hybrid system achieves robust invariant detection of in-plane and out-of-plane rotated faces that compares favourably with state-of-the-art face detection systems.",
keywords = "Spiking neural networks, face detection, pose estimation, multi-view",
author = "N McCarroll and Ammar Belatreche and Jim Harkin and Y Li",
year = "2015",
month = "11",
day = "1",
language = "English",
pages = "232--239",
booktitle = "Unknown Host Publication",

}

McCarroll, N, Belatreche, A, Harkin, J & Li, Y 2015, Bio-Inspired Hybrid Framework for Multi-view Face Detection. in Unknown Host Publication. pp. 232-239, 22nd International Conference on Neural Information Processing (ICONIP2015), 1/11/15.

Bio-Inspired Hybrid Framework for Multi-view Face Detection. / McCarroll, N; Belatreche, Ammar; Harkin, Jim; Li, Y.

Unknown Host Publication. 2015. p. 232-239.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bio-Inspired Hybrid Framework for Multi-view Face Detection

AU - McCarroll, N

AU - Belatreche, Ammar

AU - Harkin, Jim

AU - Li, Y

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Reliable face detection in completely uncontrolled settings still remains a challenging task. This paper introduces a novel hybrid learning strategy that achieves robust in-plane and out-of-plane multi-view face detection through the enhanced implementation of the hierarchical bio-inspired HMAX framework using spiking neurons. Through multiple training trials, separate pools of neurons are trained on different face poses to extract features through feed-forward unsupervised STDP. The trained neurons are then processed by an additional STDP mechanism to generate a streamlined repository of broadly tuned multi-view neurons. After unsupervised feature extraction, supervised feature selection is implemented within the hybrid framework to reduce false positives. The hybrid system achieves robust invariant detection of in-plane and out-of-plane rotated faces that compares favourably with state-of-the-art face detection systems.

AB - Reliable face detection in completely uncontrolled settings still remains a challenging task. This paper introduces a novel hybrid learning strategy that achieves robust in-plane and out-of-plane multi-view face detection through the enhanced implementation of the hierarchical bio-inspired HMAX framework using spiking neurons. Through multiple training trials, separate pools of neurons are trained on different face poses to extract features through feed-forward unsupervised STDP. The trained neurons are then processed by an additional STDP mechanism to generate a streamlined repository of broadly tuned multi-view neurons. After unsupervised feature extraction, supervised feature selection is implemented within the hybrid framework to reduce false positives. The hybrid system achieves robust invariant detection of in-plane and out-of-plane rotated faces that compares favourably with state-of-the-art face detection systems.

KW - Spiking neural networks

KW - face detection

KW - pose estimation

KW - multi-view

M3 - Conference contribution

SP - 232

EP - 239

BT - Unknown Host Publication

ER -

McCarroll N, Belatreche A, Harkin J, Li Y. Bio-Inspired Hybrid Framework for Multi-view Face Detection. In Unknown Host Publication. 2015. p. 232-239