Are MSER Features Really Interesting?

Authors:
Ron Kimmel;Cuiping Zhang;Alex Bronstein;Michael Bronstein
Affiliations:
Technion, Haifa;CMART Systems, Inc., Santa Clara;Tel Aviv University, Tel Aviv;Universita' della Svizzera Italiana, Lugano
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2011

Citing 0
Cited 5

Shape google: Geometric words and expressions for invariant shape retrieval

ACM Transactions on Graphics (TOG)
SMI 2011: Full Paper: Diffusion-geometric maximally stable component detection in deformable shapes

Computers and Graphics
Fattening Free Block Matching

Journal of Mathematical Imaging and Vision
Epithelial area detection in cytokeratin microscopic images using MSER segmentation in an anisotropic pyramid

PRIB'11 Proceedings of the 6th IAPR international conference on Pattern recognition in bioinformatics
Graph-Based detection of objects with regular regions

ICIRA'12 Proceedings of the 5th international conference on Intelligent Robotics and Applications - Volume Part III

Quantified Score

Hi-index	0.14

Visualization

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.