A perceptual shape descriptor

Date

2002-08-15

Author

Arica, N
Yarman Vural, Fatoş Tunay

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

109
views

0
downloads

In this study, we present the two dimensional object silhouette by a one dimensional descriptor, which,preserves the perceptual structure of its shape. The proposed descriptor is based on the moments of the angles between the bearings of a point on the boundary, in a set of neighborhood systems. At each point on the boundary, the angle between a pair of bearings is calculated to extract the topological information of the boundary in a given locality. The proposed method does not use any-heuristic rule or empirical threshold value in the shape representation. The similarity between the patterns is measured by elastic matching of the descriptors. The proposed shape descriptor is tested on dataset of MPEG 7 Core Experiments Shape-1. The experiments show better results than the previous studies reported in the literature.

Subject Keywords

MPEG 7 standard, Humans, Data mining, Testing, Noise shaping, Visual system, Shape measurement, Image databases, Image resolution, Skeleton

URI

https://hdl.handle.net/11511/62424

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

A compact shape descriptor based on the beam angle statistics Arica, N; Yarman Vural, Fatoş Tunay (2003-01-01) In this study, we propose a compact shape descriptor, which represents the 2-D shape information by 1-D functions. For this purpose a two-step method is proposed. In the first step, the 2-D shape information is mapped into 1-D moment functions without using a predefined resolution. The mapping is based on the beams, which are originated from a boundary point, connecting that point with the rest of the points on the boundary. At each point, the angle between a pair of beams is taken as a random variable to d...
A Non-Structural Representation Scheme for Articulated Shapes Genctav, Asli; Tarı, Zehra Sibel (2018-10-01) Articulated shapes are successfully represented by structural representations which are organized in the form of graphs of shape components. We present an alternative representation scheme which is equally powerful but does not require explicit modeling or discovery of structural relations. The key element in our scheme is a novel multi scale pixel-based distinctness measure which implicitly quantifies how rare a particular pixel is in terms of its geometry with respect to all pixels of the shape. The spati...
A physical model for dimensional reduction and its effects on the observable parameters of the universe Karaca, Koray; Bayın, Selçuk; Department of Physics (2005) In this thesis, assuming that higher spatial dimensions existed only during the inflationary prematter phases of the universe, we construct a (1+D)-dimensional (D>3), nonsingular, homogeneous and isotropic Friedmann model for dimensional reduction. In this model, dimensional reduction occurs in the form of a phase transition that follows from a purely thermodynamical consideration that the universe heats up during the inflationary prematter phases. When the temperature reaches its Planck value Tpl,D, which ...
An Algorithmic Metaphysics of Self-Patterns Benı, Majıd Davoody (Frontiers Media SA, 2020-12-01) The paper draws on an algorithmic criterion to demonstrate that the self (as initially described in Shaun Gallagher's a pattern theory of self) is a composite, scattered, and patterned object. It also addresses the question of extendedness of the self-pattern. Based on the criteria drawn from algorithmic complexity, I argue that although the self-pattern possesses a genuinely extended aspect (and in this sense, the self-pattern is minimally extended) the self-pattern and its environment do not constitute a ...
3D Shape Correspondence Under Topological Noise Genctav, Ash; Sahillioğlu, Yusuf; Tarı, Zehra Sibel (2016-05-19) In this work, we present a new approach for the problem of 3D shape correspondence under topological noise. Topological noise can be easily encountered in 3D models acquired by various ways such as motion capture technology. In our proposed approach, the pair of 3D shapes is brought to comparable topology before doing matching. We remove the connections leading to topological changes by moving the shape surface inward along the surface normal with a velocity relative to the curvature at each point. We emplo...

Citation Formats

N. Arica and F. T. Yarman Vural, “A perceptual shape descriptor,” 2002, p. 375, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/62424.