2013
DOI: 10.1109/tgrs.2013.2262232
|View full text |Cite
|
Sign up to set email alerts
|

Earth-Observation Image Retrieval Based on Content, Semantics, and Metadata

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
31
0

Year Published

2015
2015
2021
2021

Publication Types

Select...
5
4
1

Relationship

1
9

Authors

Journals

citations
Cited by 74 publications
(31 citation statements)
references
References 27 publications
0
31
0
Order By: Relevance
“…Here, the SVM uses a large pool of unlabelled data (test data) and only a small set of labelled data (training data) to predict an image semantic class. Starting from a limited number of labeled data, active learning selects the most informative samples to speed up the convergence of accuracy and to reduce the manual effort of labeling (Espinoza-Molina and Datcu, 2013). Active learning has two core components: the sample selection strategy and the model learning, which are repeated until convergence.…”
Section: Semantic Definition and Indexing Of The Image Contentmentioning
confidence: 99%
“…Here, the SVM uses a large pool of unlabelled data (test data) and only a small set of labelled data (training data) to predict an image semantic class. Starting from a limited number of labeled data, active learning selects the most informative samples to speed up the convergence of accuracy and to reduce the manual effort of labeling (Espinoza-Molina and Datcu, 2013). Active learning has two core components: the sample selection strategy and the model learning, which are repeated until convergence.…”
Section: Semantic Definition and Indexing Of The Image Contentmentioning
confidence: 99%
“…In case the descriptors are computed locally on patches, which produces multiple descriptors per image, they are first aggregated to produce a singular descriptor entry for each image [11,12]. Finally, the image descriptors are further used in dedicated indexing schemes [9,[13][14][15]] to achieve the end goal of successful retrieval.…”
Section: Introductionmentioning
confidence: 99%
“…It provides good visualization; however, no real-image processing is achieved. Advanced queries using metadata, semantics, and image content were presented in [15], showing how the integration of multiple sources helps the end-user in finding scenes of interest. Moreover, in recent years, the development of ontologies as explicit formal specifications of the terms in the domain and relations among them [16] has been applied to the EO framework [17].…”
Section: Introductionmentioning
confidence: 99%