2012
DOI: 10.1007/s13173-012-0087-1
|View full text |Cite
|
Sign up to set email alerts
|

Evaluation of parameters for combining multiple textual sources of evidence for Web image retrieval using genetic programming

Abstract: Web image retrieval is a research area that is receiving a lot of attention in the last few years due to the growing availability of images on the Web. Since contentbased image retrieval is still considered very difficult and expensive in the Web context, most current large-scale Web image search engines use textual descriptions to represent the content of the Web images. In this paper we present a study about the usage of genetic programming (GP) to address the problem of image retrieval on the World Wide Web… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
2
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
4
1

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 11 publications
0
2
0
Order By: Relevance
“…Saraiva et al, 76 on the other hand, used GP to combine multiple textual sources of evidence, such as image file name, the content of HTML, page title, alt tag, keywords, description, and text passages around the image, to rank web‐based image retrievals.…”
Section: Category‐wise Image Processing Applications Of Gpmentioning
confidence: 99%
“…Saraiva et al, 76 on the other hand, used GP to combine multiple textual sources of evidence, such as image file name, the content of HTML, page title, alt tag, keywords, description, and text passages around the image, to rank web‐based image retrievals.…”
Section: Category‐wise Image Processing Applications Of Gpmentioning
confidence: 99%
“…In general, approaches for classification are applied in very close configurations like few classes or isolated binary cases. Regarding function learning for general purposes, GP has also been used to learn formulas to combine time series similarity functions [32,33], or formulas that extract relevant information from similarity measures obtained throughout the user relevance feedback iterations [34], or textual sources [35].…”
Section: Related Workmentioning
confidence: 99%
“…Com relação aos parâmetros GP, além da taxa de reprodução, existem alguns atributos a levar em consideração: taxa de mutação, taxa de crossover, número de indivíduos na população inicial, número de gerações e profundidade da árvore. Utilizaram-se as metodologias propostas em [4,24,62] para avaliar o impacto dos parâmetros GP nos experimentos de reconhecimento de objetos considerados.…”
Section: Configuração Gpunclassified
“…Por outro lado, para avaliar os parâmetros número de indivíduos na população inicial (X), número de gerações (Y ) e profundidade da árvore (Z) utilizou-se um modelo fullfactorial de dois níveis [10] que serve para conhecer a importância de cada parâmetro nos resultados. Este modelo foi testado e utilizado em [4,24,62]. Neste tipo de modelo, cada parâmetro é avaliado com dois valores, um valor baixo (−) e um valor alto (+).…”
Section: Configuração Gpunclassified