Learning Mixtures of Smooth, Nonuniform Deformation Models for Probabilistic Image Matching
Abstract
By representing images and image prototypes by linear subspaces spanned by "tangent vectors" (derivatives of an image with respect to translation, rotation, etc.), impressive invariance to known types of uniform distortion can be built into feedforward discriminators. We describe a new probability model that can jointly cluster data and learn mixtures of nonuniform, smooth deformation fields. Our fields are based on low-frequency wavelets, so they use very few parameters to model a wide range of smooth deformations (unlike, e.g., factor analysis, which uses a large number of parameters to model deformations). We give results on handwritten digit recognition and face recognition.
Cite
Text
Jojic et al. "Learning Mixtures of Smooth, Nonuniform Deformation Models for Probabilistic Image Matching." Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, 2001.Markdown
[Jojic et al. "Learning Mixtures of Smooth, Nonuniform Deformation Models for Probabilistic Image Matching." Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics, 2001.](https://mlanthology.org/aistats/2001/jojic2001aistats-learning/)BibTeX
@inproceedings{jojic2001aistats-learning,
title = {{Learning Mixtures of Smooth, Nonuniform Deformation Models for Probabilistic Image Matching}},
author = {Jojic, Nebojsa and Simard, Patrice Y. and Frey, Brendan J. and Heckerman, David},
booktitle = {Proceedings of the Eighth International Workshop on Artificial Intelligence and Statistics},
year = {2001},
pages = {137-142},
volume = {R3},
url = {https://mlanthology.org/aistats/2001/jojic2001aistats-learning/}
}