Beyond MSER: Maximally Stable Regions using Tree of Shapes - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Beyond MSER: Maximally Stable Regions using Tree of Shapes


This article explores the application of a tree-based feature extraction algorithm for the widely-used MSER features, and proposes a Tree of Shapes based detector of Maximally Stable Regions. Changing an underlying component tree in the algorithm allows considering alternative properties and pixel orderings for extracting the Maximally Stable Regions. Differences introduced to the region structure with changing the underlying tree are discussed, as well as the spatial organization of the detected regions imposed by using a self-dual image representation for detection. Performance evaluation is carried out on a standard matching benchmark in terms of repeat ability and matching score under different image transformations, as well as in a large scale image retrieval setup, measuring Mean Average Precision. The proposed de-scriptor is compared to the standard MSER implementation as well as a tree-based MSER implementation, achieving competitive results in the matching setup and outperforming the baseline MSER in the retrieval experiments.
Fichier principal
Vignette du fichier
bmvc2015.pdf (4.3 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01194372 , version 1 (13-11-2019)


  • HAL Id : hal-01194372 , version 1


Petra Bosilj, Ewa Kijak, Sébastien Lefèvre. Beyond MSER: Maximally Stable Regions using Tree of Shapes. British Machine Vision Conference, Sep 2015, Swansea, United Kingdom. ⟨hal-01194372⟩
232 View
141 Download


Gmail Facebook X LinkedIn More