Title of article
on the beneficial effect of noise in vertex localization
Author/Authors
raftopoulos, k.a. conservatoire national des arts et métiers cnam (cnam) - centre d etudes et de recherche en informatique et communications (cédric), france , raftopoulos, k.a. national technical university of athens - video and multimedia systems lab (ivml), greece , kollias, s.d. university of lincoln, uk , sourlas, d.d. elais unilever hellas sa, greece , ferecatu, m. conservatoire national des arts et métiers cnam (cnam) - centre d etudes et de recherche en informatique et communications (cédric), france
From page
111
To page
139
Abstract
a theoretical and experimental analysis related to the effect of noise in the task of vertex identification in unknown shapes is presented. shapes are seen as real functions of their closed boundary. an alternative global perspective of curvature is examined providing insight into the process of noise-enabled vertex localization. the analysis reveals that noise facilitates in the localization of certain vertices. the concept of noising is thus considered and a relevant global method for localizing global vertices is investigated in relation to local methods under the presence of increasing noise. theoretical analysis reveals that induced noise can indeed help localizing certain vertices if combined with global descriptors. experiments with noise and a comparison to localized methods validate the theoretical results.
Keywords
global curvature , global vertices , incremental noising , noising , object recognition , shape modeling , shape representation , vertex localization
Journal title
INTERNATIONAL JOURNAL OF COMPUTER VISION
Journal title
INTERNATIONAL JOURNAL OF COMPUTER VISION
Record number
2590002
Link To Document