Sciweavers

558 search results - page 17 / 112
» Highly Discriminative Invariant FEatures for Image Matching
Sort
View
CVPR
2009
IEEE
1390views Computer Vision» more  CVPR 2009»
16 years 9 months ago
Stacks of Convolutional Restricted Boltzmann Machines for Shift-Invariant Feature Learning
In this paper we present a method for learning classspecific features for recognition. Recently a greedy layerwise procedure was proposed to initialize weights of deep belief ne...
Mohammad Norouzi (Simon Fraser University), Mani R...
130
Voted
ICDAR
2005
IEEE
15 years 7 months ago
Online Character Recognition Based on Elastic Matching and Quadratic Discrimination
We try to link elastic matching with a statistical discrimination framework to overcome the overfitting problem which often degrades the performance of elastic matchingbased onli...
Hiroto Mitoma, Seiichi Uchida, Hiroaki Sakoe
DSSCV
2005
Springer
15 years 7 months ago
Using Top-Points as Interest Points for Image Matching
We consider the use of so-called top-points for object retrieval. These points are based on scale-space and catastrophe theory, and are invariant under gray value scaling and offse...
Bram Platel, Evguenia Balmachnova, Luc Florack, Fr...
ICPR
2004
IEEE
16 years 3 months ago
Global Localization and Relative Pose Estimation Based on Scale-Invariant Features
The capability of maintaining the pose of the mobile robot is central for basic navigation and map building tasks. In this paper we describe a vision-based hybrid localization sch...
Jana Kosecka, Xiaolong Yang
ICPR
2006
IEEE
16 years 3 months ago
Computation of Rotation Local Invariant Features using the Integral Image for Real Time Object Detection
We present a framework for object detection that is invariant to object translation, scale, rotation, and to some degree, occlusion, achieving high detection rates, at 14 fps in c...
Michael Villamizar, Alberto Sanfeliu, Juan Andrade...