Image Information Mining System Evaluation Using Information-Theoretic Measures

Daschiel, H.; Datcu, Mihai

doi:10.1155/asp.2005.2153

Cited by 6 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed approach extends the statistical independence assumption from the features, which has been proved valid in [26] and [27], to the posterior probabilities. The proposed approach is derived from the belief that the statistical independence can be inherited if the extracted features from the original data are independent.…”

Section: B Assumption Of Posterior Probability Independencementioning

confidence: 96%

Accelerated Probabilistic Learning Concept for Mining Heterogeneous Earth Observation Images

Alonso

Datcu

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

We present an accelerated probabilistic learning concept and its prototype implementation for mining heterogeneous Earth observation images, e.g., multispectral images, synthetic aperture radar (SAR) images, image time series, or geographical information systems (GIS) maps. The system prototype combines, at pixel level, the unsupervised clustering results of different features, extracted from heterogeneous satellite images and geographical information resources, with user-defined semantic annotations in order to calculate the posterior probabilities that allow the final probabilistic searches. The system is able to learn different semantic labels based on a newly developed Bayesian networks algorithm and allows different probabilistic retrieval methods of all semantically related images with only a few user interactions. The new algorithm reduces the computational cost, overperforming existing conventional systems, under certain conditions, by several orders of magnitude. The achieved speed-up allows the introduction of new feature models improving the learning capabilities of knowledge-driven image information mining systems and opening them to Big Data environments. Index Terms-Active learning (AL), bag-of-words (BoW), Bayesian networks, Big Data, data fusion, geographical information systems (GIS), image mining.1939-1404

show abstract

Section: B Assumption Of Posterior Probability Independencementioning

confidence: 96%

Accelerated Probabilistic Learning Concept for Mining Heterogeneous Earth Observation Images

Alonso

Datcu

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The knowledge driven IIM (Image Information Mining) system has a clear hierarchical information representation, the image content being modeled in a Bayesian formulation [3], Figure 1. Logical structure of the knowledge-based image information mining system; the system is designed for interactive learning and probabilistic retrieval of remote sensing image content.…”

Section: Knowledge Centered Data Mining Systemmentioning

confidence: 99%

User image mining for natural hazards

Popescu

Vaduva

Faur

et al. 2010

2010 IEEE International Conference on Automation, Quality and Testing, Robotics (AQTR)

View full text Add to dashboard Cite

Natural hazards such as floods, avalanches, volcanic eruptions or earthquakes inflict losses to human settlements and manmade infrastructure and have negative impact on the local economy and environment. The growing number of satellite missions and space services facilitates the access to information for researches and decision makers. Space imagery offers the necessary support for risk prevention and mitigation, but requires human visual inspection which can be subjective, time consuming and ineffective. This paper aims to prove the efficiency of an intelligent knowledge driven EO information mining system in supporting natural hazards' management, by combining large database systems with visual capabilities. Two scenarios are envisaged both considering damage assessment for natural hazards like earthquakes and tsunami.

show abstract

“…The retrieval of images from large remote sensing image databases relies on the ability to extract appropriate information from the data, and on the robustness of this extraction [3]. Most queries do not concern, for example, imaging modality, but rather information that is invariant to imaging modality, for instance the land cover type of a region.…”

Section: Introductionmentioning

confidence: 99%

Indexing Satellite Images with Features Computed from Man-Made Structures on the Earth's Surface

Bhattacharya

Roux

Maître

et al. 2007

2007 International Workshop on Content-Based Multimedia Indexing

View full text Add to dashboard Cite

'Indexing satellite images with features computed from man-made structures on the Earth's surface. ', in 2007 International Workshop on Content-Based Multimedia Indexing ; proceedings. Piscataway, NJ: IEEE, pp. 244-250.Further information on publisher's website: Use policyThe full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. INDEXING SATELLITE IMAGES WITH FEATURES COMPUTED FROM MAN-MADE STRUCTURES ON THE EARTH'S SURFACE ABSTRACTIndexing and retrieval from remote sensing image databases relies on the extraction of appropriate information from the data about the entity of interest (e.g. land cover type) and on the robustness of this extraction to nuisance variables. Other entities in an image may be strongly correlated with the entity of interest and their properties can therefore be used to characterize this entity. The road network contained in an image is one example. The properties of road networks vary considerably from one geographical environment to another, and they can therefore be used to classify and retrieve such environments. In this paper, we define several such environments, and classify them with the aid of geometrical and topological features computed from the road networks occurring in them. The relative failure of network extraction methods in certain types of urban area obliges us to segment such areas and to add a second set of geometrical and topological features computed from the segmentations. To validate the approach, feature selection and SVM linear kernel classification are performed on the feature set arising from a diverse image database.

show abstract

Image Information Mining System Evaluation Using Information-Theoretic Measures

Cited by 6 publications

References 10 publications

Accelerated Probabilistic Learning Concept for Mining Heterogeneous Earth Observation Images

Accelerated Probabilistic Learning Concept for Mining Heterogeneous Earth Observation Images

User image mining for natural hazards

Indexing Satellite Images with Features Computed from Man-Made Structures on the Earth's Surface

Contact Info

Product

Resources

About