Sciweavers

1568 search results - page 83 / 314
» Boosting Object Detection Using Feature Selection
Sort
View
CVPR
2005
IEEE
15 years 8 months ago
The Distinctiveness, Detectability, and Robustness of Local Image Features
We introduce a new method that characterizes typical local image features (e.g., SIFT [9], phase feature [3]) in terms of their distinctiveness, detectability, and robustness to i...
Gustavo Carneiro, Allan D. Jepson
CVPR
2008
IEEE
16 years 4 months ago
Scale invariance without scale selection
In this work we construct scale invariant descriptors (SIDs) without requiring the estimation of image scale; we thereby avoid scale selection which is often unreliable. Our start...
Iasonas Kokkinos, Alan L. Yuille
ICASSP
2011
IEEE
14 years 6 months ago
Objective evaluation of the Dynamic Model Selection method for spectral voice conversion
Spectral voice conversion is usually performed using a single model selected in order to represent a tradeoff between goodness of fit and complexity. Recently, we proposed a new ...
Pierre Lanchantin, Xavier Rodet
SMC
2010
IEEE
132views Control Systems» more  SMC 2010»
15 years 21 days ago
Selection of SIFT feature points for scene description in robot vision
This paper presents a method for selection of SIFT(Scale-Invariant Feature Transform) feature points using OC-SVM (One Class-Support Vector Machines). We proposed the method for au...
Yuya Utsumi, Masahiro Tsukada, Hirokazu Madokoro, ...
CVPR
2007
IEEE
16 years 4 months ago
Toward A Discriminative Codebook: Codeword Selection across Multi-resolution
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...
Lei Wang