International Journal of Computer Vision

, Volume 41, Issue 1–2, pp 85–107

Coarse-to-Fine Face Detection

  • Francois Fleuret
  • Donald Geman


We study visual selection: Detect and roughly localize all instances of a generic object class, such as a face, in a greyscale scene, measuring performance in terms of computation and false alarms. Our approach is sequential testing which is coarse-to-fine in both in the exploration of poses and the representation of objects. All the tests are binary and indicate the presence or absence of loose spatial arrangements of oriented edge fragments. Starting from training examples, we recursively find larger and larger arrangements which are “decomposable,” which implies the probability of an arrangement appearing on an object decays slowly with its size. Detection means finding a sufficient number of arrangements of each size along a decreasing sequence of pose cells. At the beginning, the tests are simple and universal, accommodating many poses simultaneously, but the false alarm rate is relatively high. Eventually, the tests are more discriminating, but also more complex and dedicated to specific poses. As a result, the spatial distribution of processing is highly skewed and detection is rapid, but at the expense of (isolated) false alarms which, presumably, could be eliminated with localized, more intensive, processing.

visual selection face detection pose decomposition coarse-to-fine search sequential testing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Kluwer Academic Publishers 2001

Authors and Affiliations

  • Francois Fleuret
    • 1
  • Donald Geman
    • 2
  1. 1.Avant-Projet IMEDIAINRIA-Rocquencourt, Domaine de VoluceauLe ChesnayFrance
  2. 2.Department of Mathematics and StatisticsUniversity of MassachusettsAmherstUSA

Personalised recommendations