Sciweavers

63 search results - page 10 / 13
» A New Shape Transformation Approach to Handwritten Character...
Sort
View
CIMAGING
2009
265views Hardware» more  CIMAGING 2009»
13 years 8 months ago
Multi-object segmentation using coupled nonparametric shape and relative pose priors
We present a new method for multi-object segmentation in a maximum a posteriori estimation framework. Our method is motivated by the observation that neighboring or coupling objec...
Mustafa Gökhan Uzunbas, Octavian Soldea, M&uu...
CVPR
2001
IEEE
14 years 9 months ago
Learning Models for Object Recognition
We consider learning models for object recognition from examples. Our method is motivated by systems that use the Hausdorff distance as a shape comparison measure. Typically an ob...
Pedro F. Felzenszwalb
IJPRAI
2002
97views more  IJPRAI 2002»
13 years 7 months ago
Shape Description and Invariant Recognition Employing Connectionist Approach
This paper presents a new approach for shape description and invariant recognition by geometric-normalization implemented by neural networks. The neural system consists of a shape...
Jezekiel Ben-Arie, Zhiqian Wang
ICPR
2000
IEEE
14 years 8 months ago
Invariant Image Object Recognition Using Mixture Densities
In this paper we present a mixture density based approach to invariant image object recognition. We start our experiments using Gaussian mixture densities within a Bayesian classi...
Daniel Keysers, Hermann Ney, Jörg Dahmen, Mar...
GECCO
2007
Springer
186views Optimization» more  GECCO 2007»
14 years 1 months ago
Knowledge reuse in genetic programming applied to visual learning
We propose a method of knowledge reuse for an ensemble of genetic programming-based learners solving a visual learning task. First, we introduce a visual learning method that uses...
Wojciech Jaskowski, Krzysztof Krawiec, Bartosz Wie...