A hybrid face detector based on an asymmetrical adaboost cascade detector and a wavelet-Bayesian-detector

Authors:
Rodrigo Verschae;Javier Ruiz del Solar
Affiliations:
Department of Electrical Engineering, Universidad de Chile;Department of Electrical Engineering, Universidad de Chile
Venue:
IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Year:
2003

Citing 7
Cited 7

Organization of face and object recognition in modular neural network models

Neural Networks - Special issue on organisation of computation in brain-like systems
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Predictive Modular Neural Networks: Applications to Time Series

Predictive Modular Neural Networks: Applications to Time Series
Facial Expression Recognition Using a Neural Network

Proceedings of the Eleventh International Florida Artificial Intelligence Research Society Conference
Stable Neural Attractors Formation: Learning Rules and Network Dynamics

Neural Processing Letters
Fine Discrimination of Faces can be Performed Rapidly

Journal of Cognitive Neuroscience
Generalization properties of modular networks: implementing the parity function

IEEE Transactions on Neural Networks

Computer aided detection via asymmetric cascade of sparse hyperplane classifiers

Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
Face detection in gray scale images using locally linear embeddings

Computer Vision and Image Understanding
Hybrid-boost learning for multi-pose face detection and facial expression recognition

Pattern Recognition
A Regularized Framework for Feature Selection in Face Detection and Authentication

International Journal of Computer Vision
Face and iris localization using templates designed by particle swarm optimization

Pattern Recognition Letters
On the image content of a web segment: Chile as a case study

Journal of Web Engineering
Analyzing the human-robot interaction abilities of a general-purpose social robot in different naturalistic environments

RoboCup 2009

Quantified Score

Hi-index	0.00

Visualization

Abstract

Biologically inspired receptive fields arc used to process input facial expressions in a modular network architecture. Local receptive fields constructed with a modified Hcbbian rule (CBA) arc used to reduce the dimensionality of input images while preserve some topological structure. In a second stage, specialized modules trained with backpropagation classify the data into the different expression categories. Thus, the neural net architecture includes 4 layers of neurons, that we train and test with images from the Yale Faces Database. A generalization rate of 82.9% on unseen faces is obtained and the results are compared to values obtained with a PCA learning rule at the initial stage.