A new learning model based on autoassociative neural networks is developped and applied to face detection. To extend the de(cid:173) tection ability in orientation and to decrease the number of false alarms, different combinations of networks are tested: ensemble, conditional ensemble and conditional mixture of networks. The use of a conditional mixture of networks allows to obtain state of the art results on different benchmark face databases. Our purpose is to classify an extracted window x from an image as a face (x E V) or non-face (x EN). The set of all possible windows is E V uN, with V n N 0. Since collecting a representative set of non-face examples is impossible, face detection by a statistical model is a difficult task.

A new learning model based on autoassociative neural networks is developped and applied to face detection. To extend the detection ability in orientation and to decrease the number of false alarms, different combinations of networks are tested: ensemble, conditional ensemble and conditional mixture of networks. The use of a conditional mixture of networks allows to obtain state of the art results on different benchmark face databases. The set of all possible windows is E V uN, with V n N 0. Since collecting a representative set of non-face examples is impossible, face detection by a statistical model is a difficult task. An autoassociative network, using five layers of neurons, is able to perform a nonlinear dimensionnality reduction [Kramer, 1991].

A new learning model based on autoassociative neural networks is developped and applied to face detection. To extend the detection ability in orientation and to decrease the number of false alarms, different combinations of networks are tested: ensemble, conditional ensemble and conditional mixture of networks. The use of a conditional mixture of networks allows to obtain state of the art results on different benchmark face databases. The set of all possible windows is E V uN, with V n N 0. Since collecting a representative set of non-face examples is impossible, face detection by a statistical model is a difficult task. An autoassociative network, using five layers of neurons, is able to perform a nonlinear dimensionnality reduction [Kramer, 1991].

To extend the detection abilityin orientation and to decrease the number of false alarms, different combinations of networks are tested: ensemble, conditional ensemble and conditional mixture of networks. The use of a conditional mixture of networks allows to obtain state of the art results on different benchmark face databases.