An axis-based representation for recognition

Download

index.pdf

Date

2005-01-01

Author

Aslan, C
Tarı, Zehra Sibel

Metadata

Show full item record

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

Item Usage Stats

105
views

38
downloads

We present a new axis-hased shape representation scheme along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes and their metric properties in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By increasing the amount of smoothing on the evolving curve, only those symmetry axes that correspond to the most prominent parts of a shape are extracted The representation does not suffer from the common instability problems of the traditional connected skeletons. It captures the perceptual qualities of shapes well. Therefore finding the similarities and the differences among shapes becomes easier. The matching process gives highly successful results on a diverse database of 2D shapes.

Subject Keywords

Shape, Skeleton, Smoothing methods, Electric shock, Computer vision, Rough surfaces, Surface roughness, Databases, Lighting, Guidelines

URI

https://hdl.handle.net/11511/57699

DOI

https://doi.org/10.1109/iccv.2005.32

Conference Name

10th IEEE International Conference on Computer Vision (ICCV 2005)

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Disconnected Skeleton: Shape at Its Absolute Scale Aslan, Cagri; Erdem, Aykut; Erdem, Erkut; Tarı, Zehra Sibel (Institute of Electrical and Electronics Engineers (IEEE), 2008-12-01) We present a new skeletal representation along with a matching framework to address the deformable shape recognition problem. The disconnectedness arises as a result of excessive regularization that we use to describe a shape at an attainably coarse scale. Our motivation is to rely on the stable properties of the shape instead of inaccurately measured secondary details. The new representation does not suffer from the common instability problems of traditional connected skeletons and the matching process giv...
An octree-based solution-adaptive Cartesian grid generator and Euler solver for the simulation of three-dimensional inviscid compressible flows Kara, Emre; KUTLAR, AHMET İHSAN; Aksel, Mehmet Haluk (2016-01-01) Cartesian grid generation methods are especially designed algorithms to generate automatic grids for complex geometries and to simulate flows around such geometries regardless of the body shape. Cartesian grids are generated by constructing an octree-based data structure for the purpose of connecting the Cartesian cells to each other. Entire algorithm is implemented in object-oriented FORTRAN programming language. Some special Cartesian algorithms, namely, Ray-Casting method and cut-cell adaptation are used...
Modified Redundant Representation for Designing Arithmetic Circuits with Small Complexity AKLEYLEK, SEDAT; Özbudak, Ferruh (Institute of Electrical and Electronics Engineers (IEEE), 2012-03-01) We give a modified redundant representation for designing arithmetic circuits with small complexity. Using our modified redundant representation, we improve many of the complexity values significantly. Our method works for any finite field. We also give some applications in cryptography.
Disconnected skeletons for shape recognition Aslan, Çağrı; Adalı, Orhan; Department of Computer Engineering (2005) This study presents a new shape representation scheme based on disconnected symmetry axes along with a matching framework to address the problem of generic shape recognition. The main idea is to define the relative spatial arrangement of local symmetry axes in a shape centered coordinate frame. The resulting descriptions are invariant to scale, rotation, small changes in viewpoint and articulations. Symmetry points are extracted from a surface whose level curves roughly mimic the motion by curvature. By inc...
An FPGA implementation of real-time electro-optic & IR image fusion Çölova, İbrahim Melih; Akar, Gözde; Department of Electrical and Electronics Engineering (2010) In this thesis, a modified 2D Discrete Cosine Transform based electro-optic and IR image fusion algorithm is proposed and implemented on an FPGA platform. The platform is a custom FPGA board which uses ALTERA Stratix III family FPGA. The algorithm is also compared with state of the art image fusion algorithms by means of an image fusion software application GUI developed in Matlab®. The proposed algorithm principally takes corresponding 4x4 pixel blocks of two images to be fused and transforms them by means...

Citation Formats

C. Aslan and Z. S. Tarı, “An axis-based representation for recognition,” presented at the 10th IEEE International Conference on Computer Vision (ICCV 2005), Beijing, PEOPLES R CHINA, 2005, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/57699.