Scale-invariant medial features based on gradient vector flow fields
Authors:
- 1 December 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2008 19th International Conference on Pattern Recognition
- No. 10514651,p. 1-4
Abstract
We propose a novel set of medial feature interest points based on gradient vector flow (GVF) fields [18]. We exploit the long ranging GVF fields for symmetry estimation by calculating the flux flow on it. We propose interest points that are located on maxima of that flux flow and offer a straight forward way to estimate salient local scales. The features owe their robustness in clutter to the nature of the GVF which accomplishes two goals simultaneously - smoothing of orientation information and its preservation at salient edge boundaries. A learning framework based on them, in contrast to classical edge-based feature detectors, would unlikely be distracted by background clutter and spurious edges, as these new mid-level features are shape-centered. We evaluate our scale-invariant feature coding scheme against standard SIFT keypoints by demonstrating generalization over scale in a patch-based pedestrian detection task.Keywords
This publication has 15 references indexed in Scilit:
- Image representations beyond histograms of gradients: The role of Gestalt descriptors2007
- Image Matching via Saliency Region Correspondences2007
- Object recognition and segmentation by a fragment-based hierarchyTrends in Cognitive Sciences, 2007
- Generic Object Recognition via Shock Patch Fragments2007
- Learning Hierarchical Shape Models from Examples2005
- Object class recognition by unsupervised scale-invariant learning2003
- Multiscale Medial Loci and Their PropertiesInternational Journal of Computer Vision, 2003
- The Role of Propagation and Medial Geometry in Human Vision2002
- Object recognition from local scale-invariant features1999
- The Hamilton-Jacobi skeleton1999