Skip to Main content Skip to Navigation
Conference papers

Beyond MSER: Maximally Stable Regions using Tree of Shapes

Petra Bosilj 1, 2 Ewa Kijak 2 Sébastien Lefèvre 1
1 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : 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.
Complete list of metadatas

Cited literature [42 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01194372
Contributor : Sébastien Lefèvre <>
Submitted on : Wednesday, November 13, 2019 - 5:46:58 PM
Last modification on : Thursday, April 2, 2020 - 1:54:23 AM

File

bmvc2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01194372, version 1

Citation

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⟩

Share

Metrics

Record views

1132

Files downloads

117