Sciweavers

184 search results - page 11 / 37
» Scale invariance without scale selection
Sort
View
ICMCS
2008
IEEE
174views Multimedia» more  ICMCS 2008»
14 years 4 months ago
Cascaded classification with optimal candidate selection for effective place recognition
A two-stage cascaded classification approach with an optimal candidate selection scheme is proposed to recognize places using images taken by camera phones. An optimal acceptance ...
Yiqun Li, Joo-Hwee Lim, Hanlin Goh
IBPRIA
2005
Springer
14 years 3 months ago
Gabor Parameter Selection for Local Feature Detection
Abstract. Some recent works have addressed the object recognition problem by representing objects as the composition of independent image parts, where each part is modeled with “...
Plinio Moreno, Alexandre Bernardino, José S...
ECAI
2008
Springer
13 years 11 months ago
Learning to Select Object Recognition Methods for Autonomous Mobile Robots
Selecting which algorithms should be used by a mobile robot computer vision system is a decision that is usually made a priori by the system developer, based on past experience and...
Reinaldo A. C. Bianchi, Arnau Ramisa, Ramon L&oacu...
JMLR
2010
206views more  JMLR 2010»
13 years 4 months ago
Learning Translation Invariant Kernels for Classification
Appropriate selection of the kernel function, which implicitly defines the feature space of an algorithm, has a crucial role in the success of kernel methods. In this paper, we co...
Sayed Kamaledin Ghiasi Shirazi, Reza Safabakhsh, M...
ICCV
2009
IEEE
15 years 2 months ago
Active Appearance Models with Rotation Invariant Kernels
2D Active Appearance Models (AAM) and 3D Morphable Models (3DMM) are widely used techniques. AAM provide a fast fitting process, but may represent unwanted 3D transformations un...
Onur C. Hamsici, Aleix M. Martinez