Model-Based Matching of Line Drawings by Linear Combinations of Prototypes
Abstract
We describe a technique for finding pixelwise correspondences between two images by using models of objects of the same class to guide the search. The object models are "learned" from example images (also called prototypes) of an object class. The models consist of a linear combination of prototypes. The flow fields giving pixelwise correspondences between a base prototype and each of the other prototypes must be given. A novel image of an object of the same class is matched to a model by minimizing an error between the novel image and the current guess for the closest model image. Currently, the algorithm applies to line drawings of objects. An extension to real grey level images is discussed.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Jones and Poggio. "Model-Based Matching of Line Drawings by Linear Combinations of Prototypes." IEEE/CVF International Conference on Computer Vision, 1995. doi:10.1109/ICCV.1995.466894Markdown
[Jones and Poggio. "Model-Based Matching of Line Drawings by Linear Combinations of Prototypes." IEEE/CVF International Conference on Computer Vision, 1995.](https://mlanthology.org/iccv/1995/jones1995iccv-model/) doi:10.1109/ICCV.1995.466894BibTeX
@inproceedings{jones1995iccv-model,
title = {{Model-Based Matching of Line Drawings by Linear Combinations of Prototypes}},
author = {Jones, Michael J. and Poggio, Tomaso A.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1995},
pages = {531-536},
doi = {10.1109/ICCV.1995.466894},
url = {https://mlanthology.org/iccv/1995/jones1995iccv-model/}
}