Are MSER Features Really Interesting?
- 30 June 2011
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 33 (11) , 2316-2320
Abstract
Detection and description of affine-invariant features is a cornerstone component in numerous computer vision applications. In this note, we analyze the notion of maximally stable extremal regions (MSERs) through the prism of the curvature scale space, and conclude that in its original definition, MSER prefers regular (round) regions. Arguing that interesting features in natural images usually have irregular shapes, we propose alternative definitions of MSER which are free of this bias, yet maintain their invariance properties.Keywords
This publication has 24 references indexed in Scilit:
- A fully affine invariant image comparison method2009
- A Theory of Shape Identification2008
- Shape Descriptors for Maximally Stable Extremal Regions2007
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004
- Video Google: a text retrieval approach to object matching in videos2003
- Edge Detection by Helmholtz PrincipleJournal of Mathematical Imaging and Vision, 2001
- Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulationsJournal of Computational Physics, 1988
- The heat equation shrinks embedded plane curves to round pointsJournal of Differential Geometry, 1987
- The heat equation shrinking convex plane curvesJournal of Differential Geometry, 1986