by M Wimmer, S Pietzsch, F Stulp and B Radig
Abstract:
Model-based image interpretation extracts high-level information from images using a priori knowledge about the object of interest. The computational challenge is to determine the model parameters that best match a given image by searching for the global optimum of the involved objective function. Unfortunately, this function is usually designed manually, based on implicit and domain-dependent knowledge, which prevents the fitting task from yielding accurate results. In this paper, we demonstrate how to improve model fitting by learning objective functions from annotated training images. Our approach automates many critical decisions and the remaining manual steps hardly require domain-dependent knowledge. This yields more robust objective functions that are able to achieve the accurate model fit. Our evaluation uses a publicly available image database and compares the obtained results to a recent state-of-the-art approach.
Reference:
Learning Robust Objective Functions with Application to Face Model Fitting (M Wimmer, S Pietzsch, F Stulp and B Radig), In Proceedings of the 29th DAGM Symposium, volume 1, 2007.
Bibtex Entry:
@inproceedings{wimmer_learning_2007,
author = {M Wimmer and S Pietzsch and F Stulp and B Radig},
title = {Learning Robust Objective Functions with Application to Face Model
Fitting},
booktitle = {Proceedings of the 29th {DAGM} Symposium},
year = {2007},
volume = {1},
pages = {486--496},
address = {Heidelberg, Germany},
month = {sep},
abstract = {Model-based image interpretation extracts high-level information from
images using a priori knowledge about the object of interest. The
computational challenge is to determine the model parameters that
best match a given image by searching for the global optimum of the
involved objective function. Unfortunately, this function is usually
designed manually, based on implicit and domain-dependent knowledge,
which prevents the fitting task from yielding accurate results. In
this paper, we demonstrate how to improve model fitting by learning
objective functions from annotated training images. Our approach
automates many critical decisions and the remaining manual steps
hardly require domain-dependent knowledge. This yields more robust
objective functions that are able to achieve the accurate model fit.
Our evaluation uses a publicly available image database and compares
the obtained results to a recent state-of-the-art approach.},
keywords = {facial expressions},
}