Localizing parts of faces using a consensus of exemplars

Citations Over TimeTop 1% of 2011 papers

Abstract

We present a novel approach to localizing parts in images of human faces. The approach combines the output of local detectors with a non-parametric set of global models for the part locations based on over one thousand hand-labeled exemplar images. By assuming that the global models generate the part locations as hidden variables, we derive a Bayesian objective function. This function is optimized using a consensus of models for these hidden variables. The resulting localizer handles a much wider range of expression, pose, lighting and occlusion than prior ones. We show excellent performance on a new dataset gathered from the internet and show that our localizer achieves state-of-the-art performance on the less challenging BioID dataset.

Related Papers

• A Statistical Parametric and Probe Yield Analysis Methodology(1996)
• → A statistical parametric and probe yield analysis methodology [IC manufacture](2002)11 cited
• Shape constraints from parametric and non-parametric models(1993)
• Discussion on the Continuity of Parametric LP with Vector Parameter(1993)
• → Using Non-Parametric Tests(2019)