Sciweavers

566 search results - page 61 / 114
» OCR with No Shape Training
Sort
View
ICDAR
2009
IEEE
14 years 7 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
15 years 11 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 ...
CVPR
2010
IEEE
15 years 6 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...
ICIP
2000
IEEE
15 years 2 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,...
JIFS
2006
85views more  JIFS 2006»
14 years 9 months 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