A fast and accurate face detector based on neural networks

Abstract

ÐDetecting faces in images with complex backgrounds is a difficult task. Our approach, which obtains state of the art results, is based on a new neural network model: the Constrained Generative Model (CGM). Generative, since the goal of the learning process is to evaluate the probability that the model has generated the input data, and constrained since some counterexamples are used to increase the quality of the estimation performed by the model. To detect side view faces and to decrease the number of false alarms, a conditional mixture of networks is used. To decrease the computational time cost, a fast search algorithm is proposed. The level of performance reached, in terms of detection accuracy and processing time, allows to apply this detector to a real world application: the indexation of images and videos.

A survey on face detection in the wild: Past, present and future

“…Early representative methods included the detectors in [142,143]. In [144] an approach based on a neural network model, the so-called constrained generative model (CGM), was proposed. CGM is an auto-associative, fully connected multilayer perceptron (MLP) with three large layers of weights, trained to perform nonlinear dimensionality reduction in order to build a generative model for faces.…”

Robust Object Detection via Soft Cascade

“…It is often used implicitly by prefiltering obvious non-faces based on various heuristic criteria, such as the presence of skin tone [7] or intensity variance [10]. Féraud et al [1] propose a four stage cascade that includes a motion filter, color filter, a neural network and a PCA-based classifier. Heisele et al [2] propose a cascade of coarse-to-fine SVM-based classifiers.…”

Robust Algorithm for Face Detection in Color Images

“…Several teams already implemented an adaptation of the skin color [17]; nevertheless, they postulate that the camera is correctly calibrated and thus use a color skin signature which is known a priori [14] and progressively refined during the sequence.…”

“…In the first approach a representative database is generated from which a classifier will learn what is a face (Neural Networks, Support Vector Machine, Principal Component AnalysisEigenfaces...). These system are sometimes remarkably robust [14] [15] but too complex to be carried out in real time. In the second approach three levels of analysis can be distinguished.…”