Stable Affine Frames on Isophotes

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F07%3A03135474" target="_blank" >RIV/68407700:21230/07:03135474 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Stable Affine Frames on Isophotes

Original language description

We propose a new affine-covariant feature, the Stable Affine Frame (SAF). SAFs lie on the boundary of extremal regions, ie. on isophotes. Instead of requiring the whole isophote to be stable with respect to intensity perturbation as in maximally stable extremal regions (MSERs), stability is required only locally, for the primitives constituting the three-point frames. The primitives are extracted by an affine invariant process that exploits properties of bitangents and algebraic moments. Thus, instead of using closed stable isophotes, ie. MSERs, and detecting affine frames on them, SAFs are sought even on some unstable extremal regions. We show experimentally on standard datasets that SAFs have repeatability comparable to the best affine covariant detectors and consistently produce a significantly higher number of features per image. Moreover, the features cover images more evenly than MSERs, which facilitates robustness to occlusion.

Czech name

Stable Affine Frames on Isophotes

Czech description

We propose a new affine-covariant feature, the Stable Affine Frame (SAF). SAFs lie on the boundary of extremal regions, ie. on isophotes. Instead of requiring the whole isophote to be stable with respect to intensity perturbation as in maximally stable extremal regions (MSERs), stability is required only locally, for the primitives constituting the three-point frames. The primitives are extracted by an affine invariant process that exploits properties of bitangents and algebraic moments. Thus, instead of using closed stable isophotes, ie. MSERs, and detecting affine frames on them, SAFs are sought even on some unstable extremal regions. We show experimentally on standard datasets that SAFs have repeatability comparable to the best affine covariant detectors and consistently produce a significantly higher number of features per image. Moreover, the features cover images more evenly than MSERs, which facilitates robustness to occlusion.

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/GA201%2F06%2F1821" target="_blank" >GA201/06/1821: Algorithms of image recognition</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2007

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

ICCV 2007: Proceedings of Eleventh IEEE International Conference on Computer Vision

ISBN

978-1-4244-1630-1

ISSN

—

e-ISSN

—

Number of pages

8

Pages from-to

—

Publisher name

Omnipress

Place of publication

Madison

Event location

Rio de Janeiro

Event date

Oct 14, 2007

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—