Neural network cascade for facial feature localization

Authors:
Thibaud Senechal;Lionel Prevost;Shehzad Muhammad Hanif
Affiliations:
ISIR, CNRS UMR7222, Universite Pierre and Marie Curie-Paris 6, Paris Cedex 5, France;ISIR, CNRS UMR7222, Universite Pierre and Marie Curie-Paris 6, Paris Cedex 5, France;ISIR, CNRS UMR7222, Universite Pierre and Marie Curie-Paris 6, Paris Cedex 5, France
Venue:
ANNPR'10 Proceedings of the 4th IAPR TC3 conference on Artificial Neural Networks in Pattern Recognition
Year:
2010

Citing 8
Cited 1

Active shape models—their training and application

Computer Vision and Image Understanding
Automatic Analysis of Facial Expressions: The State of the Art

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Face Detection Using the Hausdorff Distance

AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Face recognition: A literature survey

ACM Computing Surveys (CSUR)
Robust Real-Time Face Detection

International Journal of Computer Vision
Active Appearance Models Revisited

International Journal of Computer Vision
Real-time facial feature localization by combining space displacement neural networks

Pattern Recognition Letters

Multi-Kernel Appearance Model

Image and Vision Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present here a complete system for the localization of facial features in frontal face images. In the first step, face detection is performed using Viola S Jones state of art algorithm. Then, a cascade of neural networks localizes precisely 28 facial features. The first network performs a coarse detection of three areas in the image corresponding roughly to left and right eyes and mouths. Then, three local networks localize, in these areas, 9 key points per eye and 10 key points on the mouth. Thorough experiments on 3500 images from standard databases (Feret, BioID) show the detector accuracy, its generalization ability and speed.