On the beneficial effect of noise in vertex localization

Kollias, Stefanos (2018) On the beneficial effect of noise in vertex localization. International Journal of Computer Vision, 126 (1). pp. 111-139. ISSN 0920-5691

ijcvpaper.pdf - Whole Document

Item Type:Article
Item Status:Live Archive


A theoretical and experimental analysis related to the effect of noise
in the task of vertex identication in unknown shapes is presented. Shapes are
seen as real functions of their closed boundary. An alternative global per-
spective 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 com-
bined with global descriptors. Experiments with noise and a comparison to
localized methods validate the theoretical results.

Keywords:Noising, Global Vertices, Global Curvature, Shape Representation, Object Recognition, Shape Modeling, Incremental Noising, Vertex Localization
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
Related URLs:
ID Code:30083
Deposited On:02 Mar 2018 16:47

Repository Staff Only: item control page