Keypoints from Symmetries by Wave Propagation

Samuele Salti, Alessandro Lanza, Luigi Di Stefano; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2898-2905

Abstract


The paper conjectures and demonstrates that repeatable keypoints based on salient symmetries at different scales can be detected by a novel analysis grounded on the wave equation rather than the heat equation underlying traditional Gaussian scale-space theory. While the image structures found by most state-of-the-art detectors, such as blobs and corners, occur typically on planar highly textured surfaces, salient symmetries are widespread in diverse kinds of images, including those related to untextured objects, which are hardly dealt with by current feature-based recognition pipelines. We provide experimental results on standard datasets and also contribute with a new dataset focused on untextured objects. Based on the positive experimental results, we hope to foster further research on the promising topic of scale invariant analysis through the wave equation.

Related Material


[pdf]
[bibtex]
@InProceedings{Salti_2013_CVPR,
author = {Salti, Samuele and Lanza, Alessandro and Di Stefano, Luigi},
title = {Keypoints from Symmetries by Wave Propagation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}