SlideShare a Scribd company logo
1 of 56
Ontology Based Object Learning and Recognition PhD Defence 14/12/2005 Supervised by Monique Thonnat Nicolas MAILLOT Orion team INRIA Sophia Antipolis
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Outline
Introduction ,[object Object],[object Object],[object Object],[object Object],[object Object]
Introduction: Semantic Image Interpretation Oslo Accords (1993) ,[object Object],handshake agreement   Need of  a priori  knowledge  in  international politics
Introduction: object categorization  ,[object Object],[object Object],Aircraft
Introduction: Goal ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Introduction: Proposed Approach ,[object Object],High-Level Interpretation Mapping Image Processing Domain knowledge  Knowledge about the mapping between domain knowledge  and image processing knowledge
Introduction: Proposed Approach ,[object Object],Reduction of the knowledge acquisition problem and of the semantic gap Performing categorization as experts do
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Outline
State of the Art : Object Recognition ,[object Object],[object Object],[object Object],[object Object],Geometric model alignment  ,[object Object]
State of the Art : Object Recognition ,[object Object],Implicit objects models Use of multiple views  ,[object Object],[object Object],[object Object],[object Object]
State of the Art : Object Recognition ,[object Object],[object Object],[object Object],[object Object]
State of the Art : Object Recognition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Knowledge Acquisition Domain Expert Knowledge Acquisition Knowledge Base Knowledge acquisition  guided  by a  visual concept ontology  (i.e  geometry, texture, color ) to describe the objects of the domain. Visual Concept  Ontology
Knowledge Acquisition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Knowledge Acquisition ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Knowledge Acquisition Texture Repartition Pattern Repetitive Random Regular Oriented Granulated Coarse Complex Visual concept ontology  content:  some   texture concepts Based on cognitive experiments  [Bhushan et al 97]
Knowledge Acquisition Subpart Tree ,[object Object],[object Object],[object Object],[object Object],Cytoplasm ,[object Object],[object Object],[object Object],[object Object],Domain knowledge   described using  visual   concept ontology Poaceae Pollen Pore
[object Object],[object Object],[object Object],[object Object],[object Object],Knowledge Acquisition
Knowledge Acquisition Each visual concept is associated with numerical features: Histograms Color Coherence Vectors  [Pass96] Blue, Bright, Dark Color Gabor Features  [Manjunath 96] Co-Occurrence Matrices Granulated, Smooth Texture SIFT Features  [Lowe 99] Polygonal, Straight  Shape Numerical Features Examples Visual Concept
Knowledge Acquisition  ,[object Object],[object Object],Acquisition Context  Point of View Sensor Rear View Front View Profile View Microscope Camera CCD Camera IR Camera
Domain  class hierarchy Subparts hierarchy Ontology driven description Image samples management Knowledge Acquisition
Poaceae Composition Link Specialization Link Pollen Grain Pori Non Apertured Pollen Cupressaceae Pori of Poaceae Pori of Parietaria Knowledge Base (18 domain classes + 17 visual concepts) Cytoplasm Of Cupressaceae Pollen with Pori Pollen with  Pori and Colpi Apertured Pollen Parietaria Olea Colpi Colpi of Olea Knowledge Acquisition Context: Sensor: Microscope Magnification: 60 Dye: Fuchsin
High-Level Interpretation Mapping Image Processing Domain knowledge  Completely Acquired Mapping Knowledge Partially Acquired Knowledge Acquisition ,[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Talk Overview
Visual Concept Learning ,[object Object],[object Object],[object Object],[object Object],Granulated  Texture Detector Granulated Texture Confidence=0.8
Visual Concept Learning ,[object Object],[object Object],[object Object],[object Object],[object Object]
Selection  of an image sample of Poaceae object Interactive selection  of region of interest with a drawing tool ,[object Object],[object Object],[object Object],[object Object],[object Object],Visual Concept Learning
Visual Concept Learning ,[object Object]
Automatic Segmentation Feature Extraction  Clustering (k-means) Cluster Visualization and Annotation  Visual Concept Learning ,[object Object],Image training set  Annotated Clusters Visual concept Ontology
Automatic Segmentation Size Computation k-means Small Cluster Visualization and Annotation ,[object Object],Visual concept Ontology Visual Concept Learning Image Training Set … … … … … Large
[object Object],Get Positive and Negative Samples Of C Visual Concept Detector SVM Training Feature Extraction And Selection Annotated Regions Visual Concept Learning SVM based on Radial Basis Function Kernels
Granulated  Texture Detector ,[object Object],[object Object],Get Positive and Negative Samples of Concept Granulated Texture Annotated Regions Visual Concept Learning LDA SVM Gabor Filter
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Talk Overview
Object Categorization ,[object Object],[object Object],[object Object],[object Object],Object Categorization Input  Image Class + Visual Description
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Object Categorization
[object Object],Circular Shape Detector Granulated Texture Detector Pink Hue Detector 0.63 Σ Object Categorization 0.5 0.6 0.8 (0.5+0.6+0.8)/3 0.63>0.5 : hypothesis verified ? Feature Extraction Automatic Segmentation ,[object Object],[object Object],[object Object],[object Object],Current  Hypothesis :
Object Categorization Automatic Segmentation Feature Extraction Input Image Poaceae 0.63 Circular 0.5 Pink 0.8 Granulated 0.6 Object Categorization Visual Concept Detectors Mapping Knowledge Base
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Talk Overview
Results ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Results ,[object Object],Image Database Object Categorization Indexed  Images Use of categorization results as  index  for images Indexing time:  1 sec for a 600x400 image on a Intel Pentium IV 3.06Ghz
Results ,[object Object],Indexed Images Semantic Query: Object Class /  Object Description ,[object Object],Retrieved  Images Retrieval
Results ,[object Object],[object Object],[object Object],No approach combines  weak supervision  with a  rich high-level knowledge layer
Results Composition Link Specialization Link Outdoor Scene Transport Vehicles Background Sky Aircraft Tarmac Grass Sea Car Motorbike Knowledge acquisition
Results Knowledge acquisition Uniform Bottom Green Grass Uniform Bottom Grey Black Tarmac Smooth Top Dark Light Blue Grey Sky Center Polygonal Motorbike Center Polygonal Car Center Polygonal Aircraft Pattern Position Geometry Brightness Hue
Results ,[object Object],[object Object],[object Object],Background images Images containing objects of interest
Results: Caltech Database on 3 object classes ,[object Object],Precision=n/A Recall=n/N n: number of  relevant   retrieved  images  A: number of  retrieved  images   N: number of  relevant   images
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Talk Overview
Conclusion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],Conclusion
Conclusion ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Future Works ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
[object Object]
Publications ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Proposed Approach Data Management   Knowledge Base of  Visual Concepts  and Data Data Management Engine Interpretation   Knowledge Base of Application Domain and  Visual Concepts  Interpretation Engine Program Supervision Library of vision programs Knowledge Base of Program Utilization Program Supervision Engine Current Image Interpretation Object Hypotheses Image Processing Request Numerical data Image description Visual Concept Ontology Cognitive vision   platform   [Hudelot 05]

More Related Content

Viewers also liked

Extracting and Reducing the Semantic Information Content of Web Documents to ...
Extracting and Reducing the Semantic Information Content of Web Documents to ...Extracting and Reducing the Semantic Information Content of Web Documents to ...
Extracting and Reducing the Semantic Information Content of Web Documents to ...ijsrd.com
 
Financial management ppt @ mba
Financial management ppt @ mbaFinancial management ppt @ mba
Financial management ppt @ mbaBabasab Patil
 
OBJECTIVES OF FINANCIAL MANAGEMENT
OBJECTIVES OF FINANCIAL MANAGEMENTOBJECTIVES OF FINANCIAL MANAGEMENT
OBJECTIVES OF FINANCIAL MANAGEMENTAnurag Chakraborty
 
ppt on financial management
 ppt on financial management ppt on financial management
ppt on financial managementAanchal
 
Financial Management Lesson Notes
Financial Management Lesson NotesFinancial Management Lesson Notes
Financial Management Lesson NotesEkrem Tufan
 
Financial Management
Financial ManagementFinancial Management
Financial Managementshart sood
 
Financial management complete note
Financial management complete noteFinancial management complete note
Financial management complete notekabul university
 
Financial management ppt
Financial management pptFinancial management ppt
Financial management pptRanal Nair
 
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...Shirshanka Das
 

Viewers also liked (11)

Extracting and Reducing the Semantic Information Content of Web Documents to ...
Extracting and Reducing the Semantic Information Content of Web Documents to ...Extracting and Reducing the Semantic Information Content of Web Documents to ...
Extracting and Reducing the Semantic Information Content of Web Documents to ...
 
Financial management ppt @ mba
Financial management ppt @ mbaFinancial management ppt @ mba
Financial management ppt @ mba
 
OBJECTIVES OF FINANCIAL MANAGEMENT
OBJECTIVES OF FINANCIAL MANAGEMENTOBJECTIVES OF FINANCIAL MANAGEMENT
OBJECTIVES OF FINANCIAL MANAGEMENT
 
ppt on financial management
 ppt on financial management ppt on financial management
ppt on financial management
 
Financial Management Lesson Notes
Financial Management Lesson NotesFinancial Management Lesson Notes
Financial Management Lesson Notes
 
Astrology
AstrologyAstrology
Astrology
 
Financial Management
Financial ManagementFinancial Management
Financial Management
 
Financial management complete note
Financial management complete noteFinancial management complete note
Financial management complete note
 
Financial management ppt
Financial management pptFinancial management ppt
Financial management ppt
 
Financial management
Financial managementFinancial management
Financial management
 
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...
Taming the ever-evolving Compliance Beast : Lessons learnt at LinkedIn [Strat...
 

Similar to Ontology Based Object Learning and Recognition

2D/Multi-view Segmentation and Tracking
2D/Multi-view Segmentation and Tracking2D/Multi-view Segmentation and Tracking
2D/Multi-view Segmentation and TrackingTouradj Ebrahimi
 
Object tracking a survey
Object tracking a surveyObject tracking a survey
Object tracking a surveyHaseeb Hassan
 
Flag segmentation, feature extraction & identification using support vector m...
Flag segmentation, feature extraction & identification using support vector m...Flag segmentation, feature extraction & identification using support vector m...
Flag segmentation, feature extraction & identification using support vector m...R M Shahidul Islam Shahed
 
Digital_Image_Classification.pptx
Digital_Image_Classification.pptxDigital_Image_Classification.pptx
Digital_Image_Classification.pptxBivaYadav3
 
Digital image classification22oct
Digital image classification22octDigital image classification22oct
Digital image classification22octAleemuddin Abbasi
 
Tracking of objects with known color signature - ELITECH 20
Tracking of objects with known color signature - ELITECH 20Tracking of objects with known color signature - ELITECH 20
Tracking of objects with known color signature - ELITECH 20Lukas Tencer
 
Mit6870 orsu lecture2
Mit6870 orsu lecture2Mit6870 orsu lecture2
Mit6870 orsu lecture2zukun
 
Using FCA for Visual Browsing
Using FCA for Visual BrowsingUsing FCA for Visual Browsing
Using FCA for Visual Browsingvillerd
 
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...sipij
 
Capter10 cluster basic
Capter10 cluster basicCapter10 cluster basic
Capter10 cluster basicHouw Liong The
 
Capter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberCapter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberHouw Liong The
 
Ala Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talkAla Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talkwolf
 
OBJECT DETECTION AND RECOGNITION: A SURVEY
OBJECT DETECTION AND RECOGNITION: A SURVEYOBJECT DETECTION AND RECOGNITION: A SURVEY
OBJECT DETECTION AND RECOGNITION: A SURVEYJournal For Research
 
DM UNIT_4 PPT for btech final year students
DM UNIT_4 PPT for btech final year studentsDM UNIT_4 PPT for btech final year students
DM UNIT_4 PPT for btech final year studentssriharipatilin
 
A Survey on Approaches for Object Tracking
A Survey on Approaches for Object TrackingA Survey on Approaches for Object Tracking
A Survey on Approaches for Object Trackingjournal ijrtem
 
Digital Image Classification.pptx
Digital Image Classification.pptxDigital Image Classification.pptx
Digital Image Classification.pptxHline Win
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedbutest
 

Similar to Ontology Based Object Learning and Recognition (20)

Multimedia searching
Multimedia searchingMultimedia searching
Multimedia searching
 
2D/Multi-view Segmentation and Tracking
2D/Multi-view Segmentation and Tracking2D/Multi-view Segmentation and Tracking
2D/Multi-view Segmentation and Tracking
 
Object tracking a survey
Object tracking a surveyObject tracking a survey
Object tracking a survey
 
Flag segmentation, feature extraction & identification using support vector m...
Flag segmentation, feature extraction & identification using support vector m...Flag segmentation, feature extraction & identification using support vector m...
Flag segmentation, feature extraction & identification using support vector m...
 
Digital_Image_Classification.pptx
Digital_Image_Classification.pptxDigital_Image_Classification.pptx
Digital_Image_Classification.pptx
 
Digital image classification22oct
Digital image classification22octDigital image classification22oct
Digital image classification22oct
 
Tracking of objects with known color signature - ELITECH 20
Tracking of objects with known color signature - ELITECH 20Tracking of objects with known color signature - ELITECH 20
Tracking of objects with known color signature - ELITECH 20
 
Mit6870 orsu lecture2
Mit6870 orsu lecture2Mit6870 orsu lecture2
Mit6870 orsu lecture2
 
Using FCA for Visual Browsing
Using FCA for Visual BrowsingUsing FCA for Visual Browsing
Using FCA for Visual Browsing
 
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...
Semi-Supervised Method of Multiple Object Segmentation with a Region Labeling...
 
Capter10 cluster basic
Capter10 cluster basicCapter10 cluster basic
Capter10 cluster basic
 
Capter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & KamberCapter10 cluster basic : Han & Kamber
Capter10 cluster basic : Han & Kamber
 
Object tracking
Object trackingObject tracking
Object tracking
 
Ala Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talkAla Stolpnik's Standard Model talk
Ala Stolpnik's Standard Model talk
 
OBJECT DETECTION AND RECOGNITION: A SURVEY
OBJECT DETECTION AND RECOGNITION: A SURVEYOBJECT DETECTION AND RECOGNITION: A SURVEY
OBJECT DETECTION AND RECOGNITION: A SURVEY
 
PPT s01-machine vision-s2
PPT s01-machine vision-s2PPT s01-machine vision-s2
PPT s01-machine vision-s2
 
DM UNIT_4 PPT for btech final year students
DM UNIT_4 PPT for btech final year studentsDM UNIT_4 PPT for btech final year students
DM UNIT_4 PPT for btech final year students
 
A Survey on Approaches for Object Tracking
A Survey on Approaches for Object TrackingA Survey on Approaches for Object Tracking
A Survey on Approaches for Object Tracking
 
Digital Image Classification.pptx
Digital Image Classification.pptxDigital Image Classification.pptx
Digital Image Classification.pptx
 
Ch 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-basedCh 9-1.Machine Learning: Symbol-based
Ch 9-1.Machine Learning: Symbol-based
 

Recently uploaded

Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CVKhem
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024The Digital Insurer
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherRemote DBA Services
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdflior mazor
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoffsammart93
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProduct Anonymous
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfhans926745
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?Igalia
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century educationjfdjdjcjdnsjd
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 

Recently uploaded (20)

Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
Real Time Object Detection Using Open CV
Real Time Object Detection Using Open CVReal Time Object Detection Using Open CV
Real Time Object Detection Using Open CV
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024Partners Life - Insurer Innovation Award 2024
Partners Life - Insurer Innovation Award 2024
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Strategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a FresherStrategies for Landing an Oracle DBA Job as a Fresher
Strategies for Landing an Oracle DBA Job as a Fresher
 
GenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdfGenAI Risks & Security Meetup 01052024.pdf
GenAI Risks & Security Meetup 01052024.pdf
 
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot TakeoffStrategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
Strategize a Smooth Tenant-to-tenant Migration and Copilot Takeoff
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
Tech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdfTech Trends Report 2024 Future Today Institute.pdf
Tech Trends Report 2024 Future Today Institute.pdf
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?A Year of the Servo Reboot: Where Are We Now?
A Year of the Servo Reboot: Where Are We Now?
 
presentation ICT roal in 21st century education
presentation ICT roal in 21st century educationpresentation ICT roal in 21st century education
presentation ICT roal in 21st century education
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 

Ontology Based Object Learning and Recognition

  • 1. Ontology Based Object Learning and Recognition PhD Defence 14/12/2005 Supervised by Monique Thonnat Nicolas MAILLOT Orion team INRIA Sophia Antipolis
  • 2.
  • 3.
  • 4.
  • 5.
  • 6.
  • 7.
  • 8.
  • 9.
  • 10.
  • 11.
  • 12.
  • 13.
  • 14.
  • 15. Knowledge Acquisition Domain Expert Knowledge Acquisition Knowledge Base Knowledge acquisition guided by a visual concept ontology (i.e geometry, texture, color ) to describe the objects of the domain. Visual Concept Ontology
  • 16.
  • 17.
  • 18. Knowledge Acquisition Texture Repartition Pattern Repetitive Random Regular Oriented Granulated Coarse Complex Visual concept ontology content: some texture concepts Based on cognitive experiments [Bhushan et al 97]
  • 19.
  • 20.
  • 21. Knowledge Acquisition Each visual concept is associated with numerical features: Histograms Color Coherence Vectors [Pass96] Blue, Bright, Dark Color Gabor Features [Manjunath 96] Co-Occurrence Matrices Granulated, Smooth Texture SIFT Features [Lowe 99] Polygonal, Straight Shape Numerical Features Examples Visual Concept
  • 22.
  • 23. Domain class hierarchy Subparts hierarchy Ontology driven description Image samples management Knowledge Acquisition
  • 24. Poaceae Composition Link Specialization Link Pollen Grain Pori Non Apertured Pollen Cupressaceae Pori of Poaceae Pori of Parietaria Knowledge Base (18 domain classes + 17 visual concepts) Cytoplasm Of Cupressaceae Pollen with Pori Pollen with Pori and Colpi Apertured Pollen Parietaria Olea Colpi Colpi of Olea Knowledge Acquisition Context: Sensor: Microscope Magnification: 60 Dye: Fuchsin
  • 25.
  • 26.
  • 27.
  • 28.
  • 29.
  • 30.
  • 31.
  • 32.
  • 33.
  • 34.
  • 35.
  • 36.
  • 37.
  • 38.
  • 39. Object Categorization Automatic Segmentation Feature Extraction Input Image Poaceae 0.63 Circular 0.5 Pink 0.8 Granulated 0.6 Object Categorization Visual Concept Detectors Mapping Knowledge Base
  • 40.
  • 41.
  • 42.
  • 43.
  • 44.
  • 45. Results Composition Link Specialization Link Outdoor Scene Transport Vehicles Background Sky Aircraft Tarmac Grass Sea Car Motorbike Knowledge acquisition
  • 46. Results Knowledge acquisition Uniform Bottom Green Grass Uniform Bottom Grey Black Tarmac Smooth Top Dark Light Blue Grey Sky Center Polygonal Motorbike Center Polygonal Car Center Polygonal Aircraft Pattern Position Geometry Brightness Hue
  • 47.
  • 48.
  • 49.
  • 50.
  • 51.
  • 52.
  • 53.
  • 54.
  • 55.
  • 56. Proposed Approach Data Management Knowledge Base of Visual Concepts and Data Data Management Engine Interpretation Knowledge Base of Application Domain and Visual Concepts Interpretation Engine Program Supervision Library of vision programs Knowledge Base of Program Utilization Program Supervision Engine Current Image Interpretation Object Hypotheses Image Processing Request Numerical data Image description Visual Concept Ontology Cognitive vision platform [Hudelot 05]