ROBUST APPEARANCE MATCHING WITH FILTERED COMPONENT ANALYSIS

Fernando De la Torre, Alvaro Collet, Jeffrey F. Cohn, Takeo Kanade

2007

Abstract

Appearance Models (AM) are commonly used to model appearance and shape variation of objects in images. In particular, they have proven useful to detection, tracking, and synthesis of people’s faces from video. While AM have numerous advantages relative to alternative approaches, they have at least two important drawbacks. First, they are especially prone to local minima in fitting; this problem becomes increasingly problematic as the number of parameters to estimate grows. Second, often few if any of the local minima correspond to the correct location of the model error. To address these problems, we propose Filtered Component Analysis (FCA), an extension of traditional Principal Component Analysis (PCA). FCA learns an optimal set of filters with which to build a multi-band representation of the object. FCA representations were found to be more robust than either grayscale or Gabor filters to problems of local minima. The effectiveness and robustness of the proposed algorithm is demonstrated in both synthetic and real data.

Download


Paper Citation


in Harvard Style

De la Torre F., Collet A., F. Cohn J. and Kanade T. (2007). ROBUST APPEARANCE MATCHING WITH FILTERED COMPONENT ANALYSIS . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, ISBN 978-972-8865-73-3, pages 207-212. DOI: 10.5220/0002049202070212


in Bibtex Style

@conference{visapp07,
author={Fernando De la Torre and Alvaro Collet and Jeffrey F. Cohn and Takeo Kanade},
title={ROBUST APPEARANCE MATCHING WITH FILTERED COMPONENT ANALYSIS},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,},
year={2007},
pages={207-212},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002049202070212},
isbn={978-972-8865-73-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP,
TI - ROBUST APPEARANCE MATCHING WITH FILTERED COMPONENT ANALYSIS
SN - 978-972-8865-73-3
AU - De la Torre F.
AU - Collet A.
AU - F. Cohn J.
AU - Kanade T.
PY - 2007
SP - 207
EP - 212
DO - 10.5220/0002049202070212