Gradient Networks: Explicit Shape Matching Without Extracting Edges - Robotics Institute Carnegie Mellon University

Gradient Networks: Explicit Shape Matching Without Extracting Edges

Conference Paper, Proceedings of 27th AAAI Conference on Artificial Intelligence (AAAI '13), pp. 417 - 423, July, 2013

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.

BibTeX

@conference{Hsiao-2013-7752,
author = {Edward Hsiao and Martial Hebert},
title = {Gradient Networks: Explicit Shape Matching Without Extracting Edges},
booktitle = {Proceedings of 27th AAAI Conference on Artificial Intelligence (AAAI '13)},
year = {2013},
month = {July},
pages = {417 - 423},
keywords = {gradient networks, shape matching, object detection, edges, gradients},
}