Sciweavers

803 search results - page 33 / 161
» Size Adaptive Selection of Most Informative Features
Sort
View
SADM
2010
196views more  SADM 2010»
14 years 6 months ago
Bayesian adaptive nearest neighbor
: The k nearest neighbor classification (k-NN) is a very simple and popular method for classification. However, it suffers from a major drawback, it assumes constant local class po...
Ruixin Guo, Sounak Chakraborty
ICIP
2008
IEEE
15 years 6 months ago
General region merging approaches based on information theory statistical measures
This work presents a new statistical approach to region merging where regions are modeled as arbitrary discrete distributions, directly estimated from the pixel values. Under this...
Felipe Calderero, Ferran Marqués
PR
2007
96views more  PR 2007»
14 years 11 months ago
Style-preserving English handwriting synthesis
This paper presents a novel and effective approach to synthesize English handwriting in the user’s writing style. We select the most important features that depict the handwriti...
Zhouchen Lin, Liang Wan
CICLING
2007
Springer
15 years 6 months ago
On the Impact of Lexical and Linguistic Features in Genre- and Domain-Based Categorization
Abstract. Classification in genres and domains is a major field of research for Information Retrieval (scientific and technical watch, datamining, etc.) and the selection of app...
Guillaume Cleuziou, Céline Poudat
MCS
2007
Springer
15 years 6 months ago
Selecting Diversifying Heuristics for Cluster Ensembles
Abstract. Cluster ensembles are deemed to be better than single clustering algorithms for discovering complex or noisy structures in data. Various heuristics for constructing such ...
Stefan Todorov Hadjitodorov, Ludmila I. Kuncheva