Scale and translation invariant pattern classification.

Date

1984

Author

Atak, B. Uğur

Metadata

Show full item record

Item Usage Stats

48
views

0
downloads

URI

https://hdl.handle.net/11511/7129

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Scale Normalization for Isometric Shape Matching Sahillioğlu, Yusuf; Yemez, Y. (2012-09-01) We address the scale problem inherent to isometric shape correspondence in a combinatorial matching framework. We consider a particular setting of the general correspondence problem where one of the two shapes to be matched is an isometric (or nearly isometric) part of the other up to an arbitrary scale. We resolve the scale ambiguity by finding a coarse matching between shape extremities based on a novel scale-invariant isometric distortion measure. The proposed algorithm also supports (partial) dense matc...
Scale-model and Simulation-based Assessments for Design Alternatives of Daylight Redirecting Systems in a Side-lighting Educational Room Kazanasmaz, Tuğçe; Hancı Geçit, Burçin; Sevinç, Zeynep; Altınkaya, Gülce; Aksakarya, Gizem; Ergin, Meltem; Öztürk, Yasemin; Grobe, Lars O. (Middle East Technical University, Faculty of Architecture, 2017-11-20) Daylight has been proven to have positive effects on well-being, comfort and performance of occupants in buildings; it specifically increases learning performance in educational buildings. Side-lighting from one direction leads to unbalanced and insufficient illuminance, especially in large and deep spaces. A design studio at the Izmir Institute of Technology (IZTECH) in Urla, Turkey, has been chosen as an example of a space in such a context. Its geometrical attributes has taken to be the baseline. First, ...
SCALE-SPACE APPROACH FOR THE COMPARISON OF HK AND SC CURVATURE DESCRIPTIONS AS APPLIED TO OBJECT RECOGNITION Akagunduz, Erdem; Eskizara, Oemer; Ulusoy, İlkay (2009-11-10) Using mean curvature (H) and Gaussian curvature (K) values or shape index (S) and curvedness (C) values, HK and SC curvature spaces are constructed in order to classify surface patches into types such as pits, peaks, saddles etc. Since both HK and SC curvature spaces classify surface patches in to similar types, their classification capabilities are comparable. Previously, HK and SC curvature spaces were compared in terms of their classification ability only at the given data resolution [2]. When calculatin...
Scale-free correlations in collective motion with position-based interactions Ferrante, Eliseo; Turgut, Ali Emre; Wenseleers, Tom; Huepe, Cristián (2014-08-02)
Scaling and self-similarity in two-dimensional hydrodynamics Ercan, Ali; Kavvas, M. Levent (2015-07-01) The conditions under which depth-averaged two-dimensional (2D) hydrodynamic equations system as an initial-boundary value problem (IBVP) becomes self-similar are investigated by utilizing one-parameter Lie group of point scaling transformations. Self-similarity conditions due to the 2D k-epsilon turbulence model are also investigated. The self-similarity conditions for the depth-averaged 2D hydrodynamics are found for the flow variables including the time, the longitudinal length, the transverse length, the...

Citation Formats

B. U. Atak, “Scale and translation invariant pattern classification.,” Middle East Technical University, 1984.