EREL: Extremal Regions of Extremum Levels

Mehdi Faraji, Jamshid Shanbehzadeh, Kamal Nasrollahi, Thomas B. Moeslund

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

12 Citationer (Scopus)
506 Downloads (Pure)


Maximally Stable Extremal Regions (MSER) is a novel region detector. It has been employed in many applications in order to extract affine covariant regions. Although MSER results in regions with almost high repeatability, it is heavily dependent on the union-find approach which is a fairly complicated algorithm, and should be completed sequentially. Furthermore, it detects regions with low repeatability under the blur transformations. The reason for the latter shortcoming is the absence of boundaries information in stability criterion. To tackle these problems we propose to employ prior information about boundaries of regions, which results in a novel region detector algorithm that not only outperforms MSER, but avoids the MSER's rather complicated steps of union-finding. To achieve that, we introduce Maxima of Gradient Magnitudes (MGMs) and use them to find handful of Extremum Levels (ELs). The chosen ELs are then scanned to detect their Extremal Regions (ER). The proposed algorithm which is called Extremal Regions of Extremum Levels (EREL) has been tested on the public benchmark dataset of Mikolajczyk. Our experimental evaluations illustrate that, in many cases EREL achieves higher repeatability scores than MSER even for very low overlap errors.
TitelIEEE International Conference on Image Processing (ICIP), 2015
ForlagIEEE Signal Processing Society
ISBN (Trykt)978-1-4799-8339-1
StatusUdgivet - 2015
BegivenhedIEEE International Conference on Image Processing - Québec City, Canada
Varighed: 27 sep. 201530 sep. 2015


KonferenceIEEE International Conference on Image Processing
By Québec City


Dyk ned i forskningsemnerne om 'EREL: Extremal Regions of Extremum Levels'. Sammen danner de et unikt fingeraftryk.