Affine morphological Shape Stable Boundary Regions (SSBR) for image representation

Kapsalas, P; Kollias, S

dc.contributor.author	Kapsalas, P	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T02:52:52Z
dc.date.available	2014-03-01T02:52:52Z
dc.date.issued	2011	en
dc.identifier.issn	15224880	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/36120
dc.subject	affine invariant	en
dc.subject	Morphological scale-space	en
dc.subject	Stable Regions	en
dc.subject.other	Affine invariant	en
dc.subject.other	Affine transformations	en
dc.subject.other	Anisotropic Diffusion	en
dc.subject.other	Benchmark datasets	en
dc.subject.other	Boundary regions	en
dc.subject.other	Boundary shapes	en
dc.subject.other	Different scale	en
dc.subject.other	Feature matching	en
dc.subject.other	Gaussian scale space	en
dc.subject.other	Image representations	en
dc.subject.other	Interest regions	en
dc.subject.other	Morphological images	en
dc.subject.other	Morphological scale-space	en
dc.subject.other	Multi scale analysis	en
dc.subject.other	Multiscales	en
dc.subject.other	Object class recognition	en
dc.subject.other	Region boundaries	en
dc.subject.other	Scale-space	en
dc.subject.other	Stable boundary	en
dc.subject.other	Stable region	en
dc.subject.other	State of the art	en
dc.subject.other	Structure-based	en
dc.subject.other	Transition boundaries	en
dc.subject.other	Velocity maps	en
dc.subject.other	Feature extraction	en
dc.subject.other	Object recognition	en
dc.subject.other	Detectors	en
dc.title	Affine morphological Shape Stable Boundary Regions (SSBR) for image representation	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/ICIP.2011.6116435	en
heal.identifier.secondary	http://dx.doi.org/10.1109/ICIP.2011.6116435	en
heal.identifier.secondary	6116435	en
heal.publicationDate	2011	en
heal.abstract	This paper presents a new structure-based interest region detector called Shape-Stable Region Boundaries (SSRB) which we use for object class recognition. The SSRB interest operator detects stable boundary regions within the multi-scale morphological image representation [1]. To detect robust boundary regions, we perform multi-scale analysis via anisotropic diffusion operators to preserve boundaries and guarantee invariance to affine transformations. We extract the transition boundaries of the diffusivity velocity map and track their evolution at each level of the scale-space. The stability of the boundary shape is subsequently estimated through a minimization process over different scales. Unlike most state of the art detectors which use the Gaussian scale space for multi-scale image representation, our approach is intrinsically affine invariant [1]. Experiments on different benchmark datasets show that SSRB is comparable or superior to state-of the art detectors for both feature matching and object recognition. © 2011 IEEE.	en
heal.journalName	Proceedings - International Conference on Image Processing, ICIP	en
dc.identifier.doi	10.1109/ICIP.2011.6116435	en
dc.identifier.spage	3381	en
dc.identifier.epage	3384	en