The a contrario framework is a statistical formulation of a perception principle that permits one to detect meaningful structures in data. It has been applied to the detection of lines and contours in images, moving objects in video, etc., but no attempt has been made to use it for the detection of faces. The goal of this paper is to show that the a contrario formulation can be adapted to the face detection method described by Viola and Jones in their seminal work. We propose an alternative to the cascade of classifiers proposed by the authors by introducing a stochastic a contrario model for the detections of a single classifier, from which adaptive detection thresholds may be inferred. The result is a single classifier whose detection rates are similar to those of a cascade of classifiers. Moreover, we show how a very short cascade of classifiers can be constructed, which improves the accuracy of a classical cascade, at a much lower computational cost. The results prove the validity of the a contrario approach for face detection and suggest that the same principles might be used to improve the performance of state-of-the-art methods.