farah prsentatation gvip 14 juin 2008
TRANSCRIPT
![Page 1: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/1.jpg)
Satellite Image Retrieval Based On Ontology Merging
Imed Riadh Farah(1,2), Wassim Messaoudi(1,2),Karim saheb ettabâa (1,2)and Basel Solaiman(2)
(1) RIADI Laboratory, ENSI, Manouba University, Tunis, Tunisia(2) ITI Laboratory, Telecom Bretagne, France
![Page 2: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/2.jpg)
Outline
• Context and problematic• State of the art : Satellite image retrieval• Our contribution
– Ontological modeling– Ontological model merging– Satellite image Retrieval
• Conclusion
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
2
![Page 3: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/3.jpg)
Context and problematic
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
4
RETRIVE ?
Satellite image baseSatellite image base
![Page 4: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/4.jpg)
State of the art : satellite image retrieval
• Text-based metadata image retrieval
• Content-based image retrieval
Semantic image retrieval
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
5
![Page 5: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/5.jpg)
State of the art : satellite image retrieval
• Relevant feed back approach– Bring user in the retrieval process :
• The system provides initial retrieval results• the user judges the above results by selecting the
accepted results• Then, a machine learning algorithm is applied to learn
the user feedback
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
6
![Page 6: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/6.jpg)
State of the art : satellite image retrieval
• Machine Learning
Associate low-level features with query concepts.• Neural network for concept learning [Town et al 01]• Bayesian network for image classification [Vailaya et al 01]• SVM for image annotation
• Semantic Template– Support high-level image retrieval [Rui et al 99, Smith et al 98]
– Creating a map between high-level concept and low-level visual features.
• Example : Semantic Visual Template [Chang et al 98]
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
7
![Page 7: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/7.jpg)
State of the art : satellite image retrieval
• Ontology-based approach– Define high-level concepts– Representing of image content [Ruan et al 06, Zheng et al 03]
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
8
![Page 8: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/8.jpg)
Our Contribution
• Objectives
– Describe the semantic image content– Manage uncertain information– Retrieve satellite images
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
9
![Page 9: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/9.jpg)
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
10
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Ontological Model 1
Ontological Model 2
Ontological Model 3
Merged ontological model
MOD
ULE
1 : O
NTOL
OGIC
AL M
ODEL
MOD
ELIN
G AN
D M
ERGI
NG
![Page 10: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/10.jpg)
Region Extraction
• Satellite Image Segmentation– Partitioning an image into no overlapping regions that are homogeneous with
regards to some characteristics such as spectral and texture.
• Normalized cut• Edgeflow• Variational image decomposition• Split and merging• K-means• Fuzzy C-means• Etc.
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
11
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 11: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/11.jpg)
Region Extraction
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
12
Satellite image 1
Satellite image N
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 12: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/12.jpg)
Ontological Modeling
• Ontology – Specification of a conceptualization [Gruber 1993].
Knowledge representationExtendibility and reusabilityA higher degree of abstraction
• An ontology O is a 4-tuple (C,R,I,A), where – C : set of concepts– R : set of relations– I : set of instances – A : is a set of axioms
• Ontology language – XOL, OIL, DAML+OIL, RDF, OWL, OKBC, Ontolingua, etc
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
13
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 13: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/13.jpg)
Sensor Ontological Model
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
14
Sensor
Active Passive
OpticRadar
OWL model:
<owl:Class rdf:ID="Sensor"/><owl:Class rdf:ID="Active"> <rdfs:subClassOf rdf:resource="#Sensor"/> </owl:Class><owl:Class rdf:ID="Passive"> <rdfs:subClassOf rdf:resource="#Sensor"/> </owl:Class><owl:Class rdf:ID="Optic"> <rdfs:subClassOf rdf:resource="#Passive"/> </owl:Class><owl:Class rdf:ID="Radar"> <rdfs:subClassOf rdf:resource="#Active"/> </owl:Class>
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 14: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/14.jpg)
Scene Ontological Model
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
15
Urban zone
Scene
Terrestrial zone Humid zone
Mountain
Communication ways
Energy lineBridge Road Railway
ParcelConstruction Forest River
Lac
Sea
Cultivate parcel Uncultivated parcel
Canal
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 15: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/15.jpg)
Spatial Relation ontological Model
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
16
Relation spatiale
At the right
At the left
Distance relation
On
Direction relation
Postion relation
Topologic relation
underbetween
FarNear
Disjunction relation
Inclusion relation
Adjacency relation
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 16: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/16.jpg)
Ontological Model Merging
• Ontology Merging
• Approaches : – ONION, PROMPT, FCA-MERGE, Etc.
Don’t manage information uncertainty
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
17
Incompletes ontological model
Merged model
MERGING
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 17: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/17.jpg)
OWL probabilistic model
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
18
For each instance in O1 and O2 If (Instance exists in O1 and not in O2) Or (Instance exists in O2 and not in O1) Then
Add Instance to M Else //(Instance not exists in tow models)
If (Instance has the same probability value in the two models O1 and O2) Then Add Instance to M Else //(Instance has different probability value) Apply the probabilistic method Add the accepted Instance.
End IfEnd
Union + Intersection + Uncertainty management
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 18: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/18.jpg)
OWL probabilistic model
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
19
Modèle O1 <Road> <Nom>R</Nom> <Probability>0.2</Probability> </Road> <River> <Nom>R</Nom> <Probability>0.8</Probability> </River><Cultivated zone> <Nom >Zone agricole</Nom> <Superficie> 500 Ha </Superficie> </Cultivated zone> <Urbain zone> <Nom >ZU1</Nom> <Area> 10 Ha </Area> </Urbain zone>
Modèle O2<Road> <Name>R</Name> <Probability>0.4</Probability></Road><River> <Name>R</Name> <Probabilité >0.6</Probabilité></River><Lake> <Name>Lac_de_Bizerte</Name> <area> 300 m3 </area></Lake><Urbain zone> <Nom >ZU1</Nom> <Area> 10 Ha </Area> </Urbain Zone>
Modèle M<Road> <Name>R</Name> <Probability>0.3</Probability></Road><River> <Name>R</Name> <Probability >0.7</Probability></River><cultivated zone> <Nom >Zone agricole</Nom><Area> 500 Ha </Area> </cultivated zone><Lake> <Nom Lac_de_Bizerte</Nom> <Area> 300 m3 </Area></Lake><Urbain Zone> <Nom >ZU1</Nom> <Area> 10 Ha </Area> </Urbain Zone>
+
Region Extraction
Ontological Modeling
Ontological Model Merging
Satellite images
Sensor O.M.
Scene O.M.
Spatial Relation O.M.
Semantic strategic Image Retrieval
![Page 19: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/19.jpg)
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
20
Merged ontological model
Similarity MeasureBase of
Ontological Models
Similar Satellite images
MOD
ULE
2 : S
TRAT
EGIC
IMAG
E RE
TRIE
VAL
Similar Ontological Models
![Page 20: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/20.jpg)
Similarity Measure
• Terminological measure – Syntactic : String Matching [Maedche et al 02]
– Linguistic : Word-Net (S-Match)• Structural measure :semantic cotopy [Maedche et al 02] :
SC(Ci,H) ={CjA|H(Ci,Cj) v H(Cj,Ci)} : super and sub concepts of C
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
21
|))2H{L}),(((22))1H{L}),(((1
1|
|))2H{L}),(((22))1H{L}),(((1
1|O2)O1,(L,TO'
FSCFFSCF
FSCFFSCF
![Page 21: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/21.jpg)
Example
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
22
Scene 1
Terrestrial zone Humid zone
MountainParcel
River
Cultivate parcelM
CP1
R
CP2
Scene 2
Terrestrial zone Humid zone
MountainParcel
Cultivate parcelM
CP1
Lac
L
![Page 22: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/22.jpg)
Conclusion
• We presented an ontology based approach for retrieving satellite image retrieval.
• Our approach attempts to : – improve the quality of image retrieval– Describe the semantic content of the satellite
image– Manage uncertainty– Provide an automatic solution for efficient satellite
image retrieval.
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
23
![Page 23: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/23.jpg)
References
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
24
[Rui et al 98] Y. Rui, T.S. Huang, M. Ortega, S. Mehrotra, Relevance feedback: a power tool for interactive content-based image retrieval, IEEETrans. Circuits Video Technol. 8 (5) (1998) 644–655.
[Rui et al 2000] Y. Rui, T.S. Huang, Optimizing learning in image retrieval, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, June 2000, pp. 1236–1243.
[Rui et al 99] Y. Rui, T.S. Huang, S.-F. Chang, Image retrieval: current techniques, promising directions, and open issues, J. Visual Commun. Image Representation 10 (4) (1999) 39–62.
[Smith et al 98] J.R. Smith, C.-S. Li, Decoding image semantics using composite region templates, IEEEWorkshop on Content-Based Access of Image and Video Libraries (CBAIVL-98), June 1998, pp. 9–13.
[Chang et al 98] S.F. Chang, W. Chen, H. Sundaram, Semantic visual templates: linking visual features to semantics, International Conference on Image Processing (ICIP), Workshop on Content Based Video Search and Retrieval, vol. 3, October 1998, pp. 531–534.
[Vailaya et al 01] A. Vailaya, M.A.T. Figueiredo, A.K. Jain, H.J. Zhang, Image classification for content-based indexing, IEEE Trans. Image Process.10 (1) (2001) 117–130.
[Town et al 01] C.P. Town, D. Sinclair, Content-based image retrieval using semantic visual categories, Society for Manufacturing Engineers, Technical Report MV01-211, 2001.
[Cai et al 04] D. Cai, X. He, Z. Li, W.-Y. Ma, J.-R. Wen, Hierachical clustering of WWWimage search results using visual, textual and link information, Proceedings of the ACM International Conference on Multimedia, 2004.
[Ruan et al 06] N. Ruan, N. Huang, W. Hong, “Semantic-Based Image Retrieval in Remote Sensing Archive: An Ontology Approach”, Geoscience and Remote Sensing Symposium, 2006. IGARSS 2006, pages 2903-2906.
[Hyvönen et al 02] E. Hyvönen, A. Styrman, and S. Saarela. “Ontology-based Image Retrieval”, HIIT Publications Number 2002-03, pages 15-27.
[Kong et al 05] H. Kong, M. Hwang, P. Kim, "The Study on the Semantic Image Retrieval based on the Personalized Ontology", IEEE, 2005.
[Zheng et al 03] W. Zheng, Y. Ouyang, J. Ford, Fillia S. Makedon “Ontology-based Image Retrieval”, WSEAS MMACTEE-WAMUS-NOLASC 2003, Vouliagmeni, Athens, Greece, December 29-31, 2003
[Rahm et al 01] E. Rahm, P. Bernstein. “A survey of approaches to automatic schema matching”, VLDB Journal, 10(4):334–350, 2001.
[Maedche et al 02] A. Maedche, S. Staab, "Measuring Similarity between Ontologies", in the Proceedings of the European Conference on Knowledge Acquisition and Management EKAW-2002, Madrid, Spain, October 1-4, pp. 251-263, 2002
![Page 24: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/24.jpg)
Satellite Image Retrieval Based On Ontology Merging
Thank you for your attention
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
25
![Page 25: Farah Prsentatation Gvip 14 Juin 2008](https://reader035.vdocuments.us/reader035/viewer/2022081521/542c9a568d7f72e62f8b61a3/html5/thumbnails/25.jpg)
03/05/23Satellite Image Retrieval Based On Ontology Merging
Imed Riadh farah,Wassim Messaoudi, Karim saheb ettabâa and Basel Solaiman
26
Education Research
Development