Are MSER Features Really Interesting?

作者：Kimmel Ron^*; Zhang Cuiping; Bronstein Alexander M; Bronstein Michael M

来源：IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(11): 2316-2320.

DOI：10.1109/TPAMI.2011.133

• MSER
• feature detector
• affine invariance
• stable region
• correspondence

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.

• 出版日期2011-11