Proceedings International Workshop on Multi-Media Database Management Systems (Cat. No.98TB100249)
DOI: 10.1109/mmdbms.1998.709516
|View full text |Cite
|
Sign up to set email alerts
|

NeuroMerge: an approach for merging heterogeneous features in content-based image retrieval systems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
7
0
1

Publication Types

Select...
3
2
1

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(8 citation statements)
references
References 12 publications
0
7
0
1
Order By: Relevance
“…As a result, content-based similarity matching is often performed using single individual features. Since different features may place different degrees of importance or focus on different aspects of the original video data, the result of similarity matching may be different when different features are used in the single feature matching process although the underlying video data set is the same in every case [23,24]. A more robust strategy is to combine the features in a reasonable way.…”
Section: Introductionmentioning
confidence: 99%
See 3 more Smart Citations
“…As a result, content-based similarity matching is often performed using single individual features. Since different features may place different degrees of importance or focus on different aspects of the original video data, the result of similarity matching may be different when different features are used in the single feature matching process although the underlying video data set is the same in every case [23,24]. A more robust strategy is to combine the features in a reasonable way.…”
Section: Introductionmentioning
confidence: 99%
“…The combination function for combining the feature vectors is another critical issue. Studies have already shown that the various features may not necessarily be linearly related [3,23,24]. Thus, a non-linear feature combination function should be incorporated in the similarity matching procedure.…”
Section: Introductionmentioning
confidence: 99%
See 2 more Smart Citations
“…Já [Shah et ah, 2004] faz uma avaliação a respeito da influência do dinamismo dos dados nas buscas por similaridades em imagens. A lógica nebulosa é utilizada nas funções de distância aplicadas por [Zhang & Zhang, 2003], enquanto que [Vasconcelos, 2004a] [Sheikholeslami et al, 1998, Lee, 2003, ou até mesmo a utilização de um conjunto desses classificadores [Skrypnik et ah, 1999]. [Rui et al, 1997].…”
Section: Cálculo De Propriedades Locaisunclassified