Sciweavers

566 search results - page 61 / 114
» OCR with No Shape Training
Sort
View
85
Voted
ICDAR
2009
IEEE
14 years 10 months ago
Handwritten Word Image Retrieval with Synthesized Typed Queries
We propose a new method for handwritten word-spotting which does not require prior training or gathering examples for querying. More precisely, a model is trained "on the fly...
José A. Rodríguez-Serrano, Florent P...
ECCV
1998
Springer
16 years 2 months ago
Active Appearance Models
?We describe a new method of matching statistical models of appearance to images. A set of model parameters control modes of shape and gray-level variation learned from a training ...
Timothy F. Cootes, Gareth J. Edwards, Christopher ...
97
Voted
CVPR
2010
IEEE
15 years 9 months ago
Layered Object Detection for Multi-Class Segmentation
We formulate a layered model for object detection and multi-class segmentation. Our system uses the output of a bank of object detectors in order to define shape priors for suppo...
Yi Yang, Sam Hallman, Deva Ramanan, Charless Fowlk...
108
Voted
ICIP
2000
IEEE
15 years 5 months ago
Modelling Profiles with a Mixture of Gaussians
Point Distribution Models are useful tools for modelling the variability of particular classes of shapes. A common approach is to apply a Principle Component Analysis to the data,...
James Orwell, Darrel Greenhill, Jonathan D. Rymel,...
103
Voted
JIFS
2006
85views more  JIFS 2006»
15 years 24 days ago
Experiments with artificial haptic perception in a robotic hand
The LUCS Haptic Hand I together with a set of haptic models is the first in a series of projects aimed at studying haptic perception for building several robotic hands together wi...
Magnus Johnsson, Christian Balkenius