SlideShare a Scribd company logo
1 of 18
IMAGE RETRIEVAL:
  	

CONTENT 
VERSUS 
  	

CONTEXT	

Thijs Westerveld	

	

Teoria e Tecnologia della Comunicazione	

Sistemi Informativi Multimediali AA’11-’12
	

Angelo Oldani 	

744818
INTRODUCTION	



         Through these slides will be presented the paper “Image
         retrieval: content versus context” of Thijs Westerveld.
         
         	

         This paper presents a “new” approach to image retrieval
         that takes the best from two worlds.	

         	

         It combine image features – content
                   collateral text – context
INDEX	




TRADITIONAL IMAGE RETRIEVAL	


LATENT SEMANTIC INDEXING	


FEATURE EXTRACTION PROCESS	


EXPERIMENTS	

DISCUSSION
CONTEXT
BASE
IMAGE
RETRIEVAL	


               May be based on two modes:	

               •  Annotations that are manually added.	

               •  Collateral text available with an image.	

               	

               The similarity between images is then based on the
               similarity between the associated texts.
CONTEXT
BASE
IMAGE
RETRIEVAL	

PROBLEMS	


               •  Synonymy	

                  Use different words to describe the same subject in
                  different documents.	

                  	

               •  Ambiguity	

                  Same words describe different subjects.
CONTENT
BASE
IMAGE
RETRIEVAL	


               Return images that are visually most similar.	

               Similarity is based on a set of low-level image
               features like a:	

               •  colour	

               •  shape	

               •  texture	

               •  …..
CONTENT
BASE
IMAGE
RETRIEVAL	

PROBLEMS	


               Semantic gap
LATENT
SEMANTIC
INDEXING
(LSI)	


              LSI is a method that uses co-occurrence statistics of
              terms to find the semantics behind a document’s terms. 	

              Documents using similar terms are probably related. 	

                      	

	





                     RESERVATION	


                    DOUBLE ROOM	

                               SHOWER	


                         BREAKFAST
LATENT
SEMANTIC
INDEXING
(LSI)	

              No one has combined text and image into the same
              semantic space using LSI.	

              List of terms from both modalities in one term document
              matrix and then apply the SVD resulting in a semantic space
              that contains both visual and textual items.
LATENT
SEMANTIC
INDEXING
(LSI)	

CALCULATING
IMAGE TERMS	





                 To use LSI on image content is necessary to
                 define a set of discrete image features that
                 has the same distribuiton as the set of textual
                 terms.	


                                  Set terms that is sparse as the set
                                  of the textual terms.	

                 CALCULATING
                 IMAGE TERMS	


                                  Set of therms that is the same size
                                  of the textual terms.
FEATURE
EXTRACTION	




          Should extract the indexing terms from documents.	

                     TEXTUAL                 IMAGE
                      TERMS	

                FEATURES	



                 Image captions	

           Colours	

                                             Textures
SPARSE
SET OF
IMAGE TERMS	

               COLOUR FEATURES	


           Has been used HSV colour space divided into 18 Hues, 3
           Saturations and 3 Values and were extracted two sets of
           features:	

           •  Histogram for the whole image.	

           •  Binary value of the most frequent color for each
              block.	


               TEXTURE FEATURES	


           Has been used gabor filters at 3 different wavelengths and
           four orientation and was extracted the average energy for
           each combination of wavelengths and orientation. Avg
           energy values are quantified into 128 bands and disregarding
           the values	

that fall within the lower 16 bands.
SPARSE
SET OF
IMAGE TERMS	

                    TERM FREQUENCIES	





                         Tot. #terms	

   Avg. #terms/doc	

   ratio	

          Text	

              4283	

           27	

         158:1	

         Image	

             37752	

           625	

         63:1	

      Combination	

          42035	

           598	

         70:1
SMALL 
SET OF
IMAGE TERMS	

               COLOUR FEATURES	


           Has been used HSV colour space divided into 18 Hues, 3
           Saturations and 3 Values and were extracted two sets of
           features:	

           •  Histogram for each block.	

           •  Histogram for whole image. 	




               TEXTURE FEATURES	


           Has been used gabor filters at 3 different wavelengths and
           four orientation and was extracted the average energy for
           each combination of wavelengths and orientation. Avg
           energy values are quantified into 10 bands and
           disregarding the values	

that fall within the lower 2 bands.
SMALL
SET OF
IMAGE TERMS	

                    TERM FREQUENCIES	





                         Tot. #terms	

   Avg. #terms/doc	

   ratio	

          Text	

              4283	

           27	

         158:1	

         Image	

              4442	

          1131	

         4:1	

      Combination	

           8725	

          1158	

         8:1
EXPERIMENT	

                         3379 images from Reformatorisch Dagblad
                         online archive together with their
                         captions.	


           Set of 20 documents as query	

           
           3 indexes (LSI indexing):	

           •  Visual terms	

           •  Textual term	

           •  Visual  Textual terms	

           	

           Top 100 returned documents
EXPERIMENT	

RESULTS	





             	

             •  The small set of image features seems to perform
                somewhat better than the sparse set 	

             	

             •  The combined approach for this set of features
                outperforms both the image and the text approach for
                queries with many relevant documents in the data set.
DISCUSSION
	



            Latent Semantic Indexing can help bridge the semantic
            gap	



                         LIMITS	


            •  Research based on very small set of images 	

            •  Text is not available with every image

More Related Content

What's hot

Text Extraction from Image using Python
Text Extraction from Image using PythonText Extraction from Image using Python
Text Extraction from Image using Pythonijtsrd
 
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...IJERA Editor
 
Implementation of content based image retrieval using the cfsd algorithm
Implementation of content based image retrieval using the cfsd algorithmImplementation of content based image retrieval using the cfsd algorithm
Implementation of content based image retrieval using the cfsd algorithmeSAT Publishing House
 

What's hot (6)

Text Extraction from Image using Python
Text Extraction from Image using PythonText Extraction from Image using Python
Text Extraction from Image using Python
 
Multimedia searching
Multimedia searchingMultimedia searching
Multimedia searching
 
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...
Review of Use of Nonlocal Spectral – Spatial Structured Sparse Representation...
 
Ct31628631
Ct31628631Ct31628631
Ct31628631
 
OOPSLA04.ppt
OOPSLA04.pptOOPSLA04.ppt
OOPSLA04.ppt
 
Implementation of content based image retrieval using the cfsd algorithm
Implementation of content based image retrieval using the cfsd algorithmImplementation of content based image retrieval using the cfsd algorithm
Implementation of content based image retrieval using the cfsd algorithm
 

Viewers also liked

Selling electronic devices!?
Selling electronic devices!?Selling electronic devices!?
Selling electronic devices!?fraillunatic2504
 
xcel energy EEI_Pres_November_2007SEC
xcel energy  EEI_Pres_November_2007SECxcel energy  EEI_Pres_November_2007SEC
xcel energy EEI_Pres_November_2007SECfinance26
 
pnsr_the_power_of_people_report
pnsr_the_power_of_people_reportpnsr_the_power_of_people_report
pnsr_the_power_of_people_reportSharon Czarnek
 
педагогіка123
педагогіка123педагогіка123
педагогіка123Igor Shevtsov
 
A study on existing and required facilities or amenities for
A study on existing and required facilities or amenities forA study on existing and required facilities or amenities for
A study on existing and required facilities or amenities forAlexander Decker
 
Stacy Davis ETEC Timeline
Stacy Davis ETEC TimelineStacy Davis ETEC Timeline
Stacy Davis ETEC TimelineStacy Davis
 
Back to school scholarships
Back to school scholarshipsBack to school scholarships
Back to school scholarshipsjerry guhyem
 
Programma "Horizon 2020"
Programma "Horizon 2020"Programma "Horizon 2020"
Programma "Horizon 2020"EnricoPanini
 
Tutorials: The Range
Tutorials: The RangeTutorials: The Range
Tutorials: The RangeMedia4math
 
Amnistia30urte
Amnistia30urteAmnistia30urte
Amnistia30urteetengabe
 
мовознавець
мовознавецьмовознавець
мовознавецьgalina90210
 

Viewers also liked (18)

Semantics
Semantics Semantics
Semantics
 
Selling electronic devices!?
Selling electronic devices!?Selling electronic devices!?
Selling electronic devices!?
 
xcel energy EEI_Pres_November_2007SEC
xcel energy  EEI_Pres_November_2007SECxcel energy  EEI_Pres_November_2007SEC
xcel energy EEI_Pres_November_2007SEC
 
pnsr_the_power_of_people_report
pnsr_the_power_of_people_reportpnsr_the_power_of_people_report
pnsr_the_power_of_people_report
 
педагогіка123
педагогіка123педагогіка123
педагогіка123
 
A study on existing and required facilities or amenities for
A study on existing and required facilities or amenities forA study on existing and required facilities or amenities for
A study on existing and required facilities or amenities for
 
Stacy Davis ETEC Timeline
Stacy Davis ETEC TimelineStacy Davis ETEC Timeline
Stacy Davis ETEC Timeline
 
La ley de_ohm[1]
La ley de_ohm[1]La ley de_ohm[1]
La ley de_ohm[1]
 
Road Safety Products
Road Safety ProductsRoad Safety Products
Road Safety Products
 
Future of india
Future of indiaFuture of india
Future of india
 
Back to school scholarships
Back to school scholarshipsBack to school scholarships
Back to school scholarships
 
Programma "Horizon 2020"
Programma "Horizon 2020"Programma "Horizon 2020"
Programma "Horizon 2020"
 
Tutorials: The Range
Tutorials: The RangeTutorials: The Range
Tutorials: The Range
 
Resume Only
Resume OnlyResume Only
Resume Only
 
CV Aditya - Oct 2016
CV Aditya - Oct 2016CV Aditya - Oct 2016
CV Aditya - Oct 2016
 
Amnistia30urte
Amnistia30urteAmnistia30urte
Amnistia30urte
 
мовознавець
мовознавецьмовознавець
мовознавець
 
Ijrdt11 140005
Ijrdt11 140005Ijrdt11 140005
Ijrdt11 140005
 

Similar to Content vs Context

A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...
A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...
A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...Matthias Trapp
 
Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Sujit Pal
 
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...Spot the Dog: An overview of semantic retrieval of unannotated images in the ...
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...Jonathon Hare
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Scienceinventy
 
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...Zahra Mansoori
 
Reference Scope Identification of Citances Using Convolutional Neural Network
Reference Scope Identification of Citances Using Convolutional Neural NetworkReference Scope Identification of Citances Using Convolutional Neural Network
Reference Scope Identification of Citances Using Convolutional Neural NetworkSaurav Jha
 
Parsimonious topic models with salient word discovery
Parsimonious topic models with salient word discoveryParsimonious topic models with salient word discovery
Parsimonious topic models with salient word discoveryieeepondy
 
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...Jonathon Hare
 
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...Jonathon Hare
 
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHES
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHESSECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHES
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHESranjit banshpal
 
Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Jonathon Hare
 
Segmentation - based Historical Handwritten Word Spotting using document-spec...
Segmentation - based Historical Handwritten Word Spotting using document-spec...Segmentation - based Historical Handwritten Word Spotting using document-spec...
Segmentation - based Historical Handwritten Word Spotting using document-spec...Konstantinos Zagoris
 
Probabilistic data structures. Part 4. Similarity
Probabilistic data structures. Part 4. SimilarityProbabilistic data structures. Part 4. Similarity
Probabilistic data structures. Part 4. SimilarityAndrii Gakhov
 
Evolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchEvolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchSujit Pal
 
Show observe and tell giang nguyen
Show observe and tell   giang nguyenShow observe and tell   giang nguyen
Show observe and tell giang nguyenNguyen Giang
 

Similar to Content vs Context (20)

A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...
A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...
A Benchmark for the Use of Topic Models for Text Visualization Tasks - Online...
 
Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...
 
Das09112008
Das09112008Das09112008
Das09112008
 
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...Spot the Dog: An overview of semantic retrieval of unannotated images in the ...
Spot the Dog: An overview of semantic retrieval of unannotated images in the ...
 
Research Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and ScienceResearch Inventy : International Journal of Engineering and Science
Research Inventy : International Journal of Engineering and Science
 
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...
Content-based Image Retrieval Using The knowledge of Color, Texture in Binary...
 
Reference Scope Identification of Citances Using Convolutional Neural Network
Reference Scope Identification of Citances Using Convolutional Neural NetworkReference Scope Identification of Citances Using Convolutional Neural Network
Reference Scope Identification of Citances Using Convolutional Neural Network
 
Ac03401600163.
Ac03401600163.Ac03401600163.
Ac03401600163.
 
Parsimonious topic models with salient word discovery
Parsimonious topic models with salient word discoveryParsimonious topic models with salient word discovery
Parsimonious topic models with salient word discovery
 
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...
Semantic Retrieval and Automatic Annotation: Linear Transformations, Correlat...
 
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...
Multimodal Searching and Semantic Spaces: ...or how to find images of Dalmati...
 
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHES
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHESSECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHES
SECURE IMAGE RETRIEVAL BASED ON HYBRID FEATURES AND HASHES
 
Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...
 
Visual Search
Visual SearchVisual Search
Visual Search
 
Segmentation - based Historical Handwritten Word Spotting using document-spec...
Segmentation - based Historical Handwritten Word Spotting using document-spec...Segmentation - based Historical Handwritten Word Spotting using document-spec...
Segmentation - based Historical Handwritten Word Spotting using document-spec...
 
B0310408
B0310408B0310408
B0310408
 
LSDI 2.pptx
LSDI 2.pptxLSDI 2.pptx
LSDI 2.pptx
 
Probabilistic data structures. Part 4. Similarity
Probabilistic data structures. Part 4. SimilarityProbabilistic data structures. Part 4. Similarity
Probabilistic data structures. Part 4. Similarity
 
Evolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchEvolving a Medical Image Similarity Search
Evolving a Medical Image Similarity Search
 
Show observe and tell giang nguyen
Show observe and tell   giang nguyenShow observe and tell   giang nguyen
Show observe and tell giang nguyen
 

Recently uploaded

Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDGMarianaLemus7
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfjimielynbastida
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024BookNet Canada
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024Lorenzo Miniero
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitecturePixlogix Infotech
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 

Recently uploaded (20)

Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
APIForce Zurich 5 April Automation LPDG
APIForce Zurich 5 April  Automation LPDGAPIForce Zurich 5 April  Automation LPDG
APIForce Zurich 5 April Automation LPDG
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Science&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdfScience&tech:THE INFORMATION AGE STS.pdf
Science&tech:THE INFORMATION AGE STS.pdf
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
New from BookNet Canada for 2024: BNC BiblioShare - Tech Forum 2024
 
SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024SIP trunking in Janus @ Kamailio World 2024
SIP trunking in Janus @ Kamailio World 2024
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Understanding the Laravel MVC Architecture
Understanding the Laravel MVC ArchitectureUnderstanding the Laravel MVC Architecture
Understanding the Laravel MVC Architecture
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 

Content vs Context

  • 1. IMAGE RETRIEVAL: CONTENT VERSUS CONTEXT Thijs Westerveld Teoria e Tecnologia della Comunicazione Sistemi Informativi Multimediali AA’11-’12 Angelo Oldani 744818
  • 2. INTRODUCTION Through these slides will be presented the paper “Image retrieval: content versus context” of Thijs Westerveld. This paper presents a “new” approach to image retrieval that takes the best from two worlds. It combine image features – content collateral text – context
  • 3. INDEX TRADITIONAL IMAGE RETRIEVAL LATENT SEMANTIC INDEXING FEATURE EXTRACTION PROCESS EXPERIMENTS DISCUSSION
  • 4. CONTEXT BASE IMAGE RETRIEVAL May be based on two modes: •  Annotations that are manually added. •  Collateral text available with an image. The similarity between images is then based on the similarity between the associated texts.
  • 5. CONTEXT BASE IMAGE RETRIEVAL PROBLEMS •  Synonymy Use different words to describe the same subject in different documents. •  Ambiguity Same words describe different subjects.
  • 6. CONTENT BASE IMAGE RETRIEVAL Return images that are visually most similar. Similarity is based on a set of low-level image features like a: •  colour •  shape •  texture •  …..
  • 8. LATENT SEMANTIC INDEXING (LSI) LSI is a method that uses co-occurrence statistics of terms to find the semantics behind a document’s terms. Documents using similar terms are probably related. RESERVATION DOUBLE ROOM SHOWER BREAKFAST
  • 9. LATENT SEMANTIC INDEXING (LSI) No one has combined text and image into the same semantic space using LSI. List of terms from both modalities in one term document matrix and then apply the SVD resulting in a semantic space that contains both visual and textual items.
  • 10. LATENT SEMANTIC INDEXING (LSI) CALCULATING IMAGE TERMS To use LSI on image content is necessary to define a set of discrete image features that has the same distribuiton as the set of textual terms. Set terms that is sparse as the set of the textual terms. CALCULATING IMAGE TERMS Set of therms that is the same size of the textual terms.
  • 11. FEATURE EXTRACTION Should extract the indexing terms from documents. TEXTUAL IMAGE TERMS FEATURES Image captions Colours Textures
  • 12. SPARSE SET OF IMAGE TERMS COLOUR FEATURES Has been used HSV colour space divided into 18 Hues, 3 Saturations and 3 Values and were extracted two sets of features: •  Histogram for the whole image. •  Binary value of the most frequent color for each block. TEXTURE FEATURES Has been used gabor filters at 3 different wavelengths and four orientation and was extracted the average energy for each combination of wavelengths and orientation. Avg energy values are quantified into 128 bands and disregarding the values that fall within the lower 16 bands.
  • 13. SPARSE SET OF IMAGE TERMS TERM FREQUENCIES Tot. #terms Avg. #terms/doc ratio Text 4283 27 158:1 Image 37752 625 63:1 Combination 42035 598 70:1
  • 14. SMALL SET OF IMAGE TERMS COLOUR FEATURES Has been used HSV colour space divided into 18 Hues, 3 Saturations and 3 Values and were extracted two sets of features: •  Histogram for each block. •  Histogram for whole image. TEXTURE FEATURES Has been used gabor filters at 3 different wavelengths and four orientation and was extracted the average energy for each combination of wavelengths and orientation. Avg energy values are quantified into 10 bands and disregarding the values that fall within the lower 2 bands.
  • 15. SMALL SET OF IMAGE TERMS TERM FREQUENCIES Tot. #terms Avg. #terms/doc ratio Text 4283 27 158:1 Image 4442 1131 4:1 Combination 8725 1158 8:1
  • 16. EXPERIMENT 3379 images from Reformatorisch Dagblad online archive together with their captions. Set of 20 documents as query 3 indexes (LSI indexing): •  Visual terms •  Textual term •  Visual Textual terms Top 100 returned documents
  • 17. EXPERIMENT RESULTS •  The small set of image features seems to perform somewhat better than the sparse set •  The combined approach for this set of features outperforms both the image and the text approach for queries with many relevant documents in the data set.
  • 18. DISCUSSION Latent Semantic Indexing can help bridge the semantic gap LIMITS •  Research based on very small set of images •  Text is not available with every image