Direkt zum Inhalt springen

# Technical University of Munich

Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components (bibtex)
Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components (bibtex)
by M Wimmer, C Mayer, F Stulp and B Radig
Abstract:
Geometric models allow to determine semantic information about real-world objects. Model fitting algorithms need to find the best match between a parameterized model and a gi ven image. This task inherently requires an objective function to estimate the error between a model parameterization and an image. The accuracy of this function directly inf luences the accuracy of the entire process of model fitting. Unfortunately, building these functions is a non-trivial task. Dedicated to the application of face model fitting, this paper proposes to consider a multi-band image representation that indicates the facial components, from which a large set of image features is computed. Since it is not possible to manually formulate an objective function that considers this large amount of features, we apply a Machine Lear ning framework to construct them. This automatic approach is capable of considering the large amount of features provided and yield highly accurate objective functions for fa ce model fitting. Since the Machine Learning framework rejects non-relevant image features, we obtain high performance runtime characteristics as well.
Reference:
Face Model Fitting based on Machine Learning from Multi-band Images of Facial Components (M Wimmer, C Mayer, F Stulp and B Radig), In Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment, held in conjunction with CVPR, 2008.
Bibtex Entry:
@inproceedings{wimmer_face_2008,
author = {M Wimmer and C Mayer and F Stulp and B Radig},
title = {Face Model Fitting based on Machine Learning from Multi-band Images
of Facial Components},
booktitle = {Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment,
held in conjunction with {CVPR}},
year = {2008},
month = {jun},
abstract = {Geometric models allow to determine semantic information about real-world
objects. Model fitting algorithms need to find the best match between
a parameterized model and a gi ven image. This task inherently requires
an objective function to estimate the error between a model parameterization
and an image. The accuracy of this function directly inf luences
the accuracy of the entire process of model fitting. Unfortunately,
building these functions is a non-trivial task. Dedicated to the
application of face model fitting, this paper proposes to consider
a multi-band image representation that indicates the facial components,
from which a large set of image features is computed. Since it is
not possible to manually formulate an objective function that considers
this large amount of features, we apply a Machine Lear ning framework
to construct them. This automatic approach is capable of considering
the large amount of features provided and yield highly accurate objective
functions for fa ce model fitting. Since the Machine Learning framework
rejects non-relevant image features, we obtain high performance runtime
characteristics as well.},
keywords = {facial expressions},
}