Sciweavers

3716 search results - page 327 / 744
» On the monotonization of the training set
Sort
View
PRL
2000
148views more  PRL 2000»
15 years 6 months ago
One-dimensional representation of two-dimensional information for HMM based handwriting recognition
: In this study, we introduce a set of one-dimensional features to represent two dimensional shape information for HMM (Hidden Markov Model) based handwritten optical character rec...
Nafiz Arica, Fatos T. Yarman-Vural
IJCV
2002
232views more  IJCV 2002»
15 years 6 months ago
Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional
We present a modification of the Mumford-Shah functional and its cartoon limit which facilitates the incorporation of a statistical prior on the shape of the segmenting contour. By...
Daniel Cremers, Florian Tischhäuser, Joachim ...
ICRA
2010
IEEE
118views Robotics» more  ICRA 2010»
15 years 5 months ago
Tactile object class and internal state recognition for mobile manipulation
— Tactile information is valuable in determining properties of objects that are inaccessible from visual perception. In this work, we present a tactile perception strategy that a...
Sachin Chitta, Matthew Piccoli, Jürgen Sturm
IDEAL
2010
Springer
15 years 5 months ago
Dimension Reduction for Regression with Bottleneck Neural Networks
Dimension reduction for regression (DRR) deals with the problem of finding for high-dimensional data such low-dimensional representations, which preserve the ability to predict a ...
Elina Parviainen
PR
2010
144views more  PR 2010»
15 years 5 months ago
Classifying transformation-variant attributed point patterns
This paper presents a classification approach, where a sample is represented by a set of feature vectors called an attributed point pattern. Some attributes of a point are transf...
K. E. Dungan, L. C. Potter