Title :
Are MSER Features Really Interesting?
Author :
Kimmel, Ron ; Cuiping Zhang ; Bronstein, Alexander ; Bronstein, Michael M.
Author_Institution :
Dept. of Comput. Sci., Technion - Israel Inst. of Technol., Haifa, Israel
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 :
computer vision; feature extraction; MSER features; affine-invariant feature description; affine-invariant feature detection; computer vision applications; curvature scale space; invariance properties; maximally stable extremal regions; Detectors; Feature extraction; Image edge detection; Level set; Shape; Stability criteria; MSER; affine invariance; correspondence.; feature detector; stable region;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2011.133