Gradient Networks: Explicit Shape Matching Without Extracting Edges
Abstract
We present a novel framework for shape-based template matching in images. While previous approaches required brittle contour extraction, considered only local information, or used coarse statistics, we propose to match the shape explicitly on low-level gradients by formulating the problem as traversing paths in a gradient network. We evaluate our algorithm on a challenging dataset of objects in cluttered environments and demonstrate significant improvement over state-of-the-art methods for shape matching and object detection.
Cite
Text
Hsiao and Hebert. "Gradient Networks: Explicit Shape Matching Without Extracting Edges." AAAI Conference on Artificial Intelligence, 2013. doi:10.1609/AAAI.V27I1.8559Markdown
[Hsiao and Hebert. "Gradient Networks: Explicit Shape Matching Without Extracting Edges." AAAI Conference on Artificial Intelligence, 2013.](https://mlanthology.org/aaai/2013/hsiao2013aaai-gradient/) doi:10.1609/AAAI.V27I1.8559BibTeX
@inproceedings{hsiao2013aaai-gradient,
title = {{Gradient Networks: Explicit Shape Matching Without Extracting Edges}},
author = {Hsiao, Edward and Hebert, Martial},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2013},
pages = {417-423},
doi = {10.1609/AAAI.V27I1.8559},
url = {https://mlanthology.org/aaai/2013/hsiao2013aaai-gradient/}
}