Sciweavers

Share
warning: Creating default object from empty value in /var/www/modules/taxonomy/taxonomy.module on line 1416.
ICDAR
2011
IEEE
9 years 10 months ago
Tuning between Exponential Functions and Zones for Membership Functions Selection in Voronoi-Based Zoning for Handwritten Charac
— In Handwritten Character Recognition, zoning is rigtly considered as one of the most effective feature extraction techniques. In the past, many zoning methods have been propose...
Sebastiano Impedovo, Giuseppe Pirlo
IJON
2011
186views more  IJON 2011»
10 years 1 months ago
Discriminative structure selection method of Gaussian Mixture Models with its application to handwritten digit recognition
, Yunde Jia Model structure selection is currently an open problem in modeling data via Gaussian Mixture Models (GMM). This paper proposes a discriminative method to select GMM st...
Xuefeng Chen, Xiabi Liu, Yunde Jia
NIPS
2001
10 years 11 months ago
Thin Junction Trees
We present an algorithm that induces a class of models with thin junction trees--models that are characterized by an upper bound on the size of the maximal cliques of their triang...
Francis R. Bach, Michael I. Jordan
FUZZY
2001
Springer
184views Fuzzy Logic» more  FUZZY 2001»
11 years 2 months ago
Handwritten Digit Recognition: A Neural Network Demo
Abstract. A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen’s self-organizing feature map...
Berend-Jan van der Zwaag
ICDAR
2003
IEEE
11 years 3 months ago
A class-modular GLVQ ensemble with outlier learning for handwritten digit recognition
A class-modular generalized learning vector quantization (GLVQ) ensemble method with outlier learning for handwritten digit recognition is proposed. A GLVQ classifier is one of d...
Katsuhiko Takahashi, Daisuke Nishiwaki
DAGM
2009
Springer
11 years 5 months ago
Deformation-Aware Log-Linear Models
Abstract. In this paper, we present a novel deformation-aware discriminative model for handwritten digit recognition. Unlike previous approaches our model directly considers image ...
Tobias Gass, Thomas Deselaers, Hermann Ney
ICPR
2002
IEEE
11 years 11 months ago
The Economics of Classification: Error vs. Complexity
Although usually classifier error is the main concern in publications, in real applications classifier evaluation complexity may play a large role as well. In this paper, a simple...
Dick de Ridder, Elzbieta Pekalska, Robert P. W. Du...
ICPR
2008
IEEE
11 years 11 months ago
A new HMM training and testing scheme
One of disadvantages of Hidden Markov Models (HMMs) is its low resistance to unexpected noises among observation sequences. Unexpected noises in a sequence usually "break&quo...
Albert Hung-Ren Ko, Alceu de Souza Britto Jr., Rob...
ICCV
2001
IEEE
12 years 10 days ago
Separating Appearance from Deformation
By representing images and image prototypes by linear subspaces spanned by "tangent vectors" (derivatives of an image with respect to translation, rotation, etc.), impre...
Nebojsa Jojic, Patrice Simard, Brendan J. Frey, Da...
books