Sciweavers

1282 search results - page 25 / 257
» Feature selection with neural networks
Sort
View
SSPR
2004
Springer
14 years 3 months ago
Recognition of Handwritten Numerals Using a Combined Classifier with Hybrid Features
Off-line handwritten numeral recognition is a very difficult task. It is hard to achieve high recognition results using a single set of features and a single classifier, since hand...
Kyoung Min Kim, Joong Jo Park, Young Gi Song, In-C...
ICNC
2005
Springer
14 years 3 months ago
Texture Segmentation Using Neural Networks and Multi-scale Wavelet Features
This paper presents a novel texture segmentation method using Bayesian estimation and neural networks. Multi-scale wavelet coefficients and the context information extracted from n...
Tae-Hyung Kim, Il Kyu Eom, Yoo Shin Kim
CORR
2002
Springer
106views Education» more  CORR 2002»
13 years 9 months ago
On model selection and the disability of neural networks to decompose tasks
A neural network with fixed topology can be regarded as a parametrization of functions, which decides on the correlations between functional variations when parameters are adapted...
Marc Toussaint
AVSS
2007
IEEE
14 years 4 months ago
Face localization by neural networks trained with Zernike moments and Eigenfaces feature vectors. A comparison
Face localization using neural network is presented in this communication. Neural network was trained with two different kinds of feature parameters vectors; Zernike moments and E...
Mohammed Saaidia, Anis Chaari, Sylvie Lelandais, V...
INTERSPEECH
2010
13 years 4 months ago
Hierarchical bottle neck features for LVCSR
This paper investigates the combination of different neural network topologies for probabilistic feature extraction. On one hand, a five-layer neural network used in bottle neck f...
Christian Plahl, Ralf Schlüter, Hermann Ney