Contour Grouping and Abstraction Using Simple Part Models
Abstract
We address the problem of contour-based perceptual grouping using a user-defined vocabulary of simple part models. We train a family of classifiers on the vocabulary, and apply them to a region oversegmentation of the input image to detect closed contours that are consistent with some shape in the vocabulary. Given such a set of consistent cycles, they are both abstracted and categorized through a novel application of an active shape model also trained on the vocabulary. From an image of a real object, our framework recovers the projections of the abstract surfaces that comprise an idealized model of the object. We evaluate our framework on a newly constructed dataset annotated with a set of ground truth abstract surfaces.
Cite
Text
Sala and Dickinson. "Contour Grouping and Abstraction Using Simple Part Models." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_44Markdown
[Sala and Dickinson. "Contour Grouping and Abstraction Using Simple Part Models." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/sala2010eccv-contour/) doi:10.1007/978-3-642-15555-0_44BibTeX
@inproceedings{sala2010eccv-contour,
title = {{Contour Grouping and Abstraction Using Simple Part Models}},
author = {Sala, Pablo and Dickinson, Sven J.},
booktitle = {European Conference on Computer Vision},
year = {2010},
pages = {603-616},
doi = {10.1007/978-3-642-15555-0_44},
url = {https://mlanthology.org/eccv/2010/sala2010eccv-contour/}
}