SlideShare una empresa de Scribd logo
1 de 21
Descargar para leer sin conexión
Information Retrieved
           - Image based search


     s1160123 Tomoyuki Soeta
  Supervised by Prof. Qiangfu Zhao
      System Intelligence Lab



                                     1
Outline
   Introduction
   Information Retrieval
   VQ (Vector Quantization)
   Divide into the 8x8 block
   Making of Code book
   K-means algorithm
   Extract each image’s feature vector
   Result
       Image and feature vector
       Distance of feature vector
   Conclusion
   Future work                           2
Introduction
   I want to aim at the improvement of information retrieval
    system to search it even if the input data are documents
    or images.
   I have charge of a research on information retrieval
    based on a image.
   To search images using a search engine, we may use the
    index attached to the image, the file name, etc. as the
    key-words. We may also use "the contents of an image
    themselves."
   I study a new image search technique based on the code
    book information.




                                                          3
Information Retrieved
                                     Image
     Text
                            Divide into the block
                                (1 block 8x8)
 Morphological
   Analysis
                                                    Code book

Word Filtering
                             Code of each block


 Feature Vector
                                 Feature Vector



                 NNTree or SVM
                                                                4
VQ (Vector Quantization)
                     Compression coding of images
                     Image compression technology

image               In my study, I use VQ to
    Vector           translate an image into a bag-
        Quantization of-blocks (BOB)
    (VQ)




                      same way as document search
                                                      5
 feature vector
Divide into the 8x8 block (1)

   I used 10 facial images with the size 256x256.
   images are converted to gray scale images.
   Divided into the block (one-block 8x8 size).
   Each image obtains the block of 32×32
    pieces severally.
                         32 blocks
                   32
                    b
                    l                  1 block 8x8
                    o
                    c
                    k
                    s
                                                     6
Divide into the 8x8 block (2)
             Block’s pixel value is read.
             Pixel read value is stored in the array of
              1x64.
             One image can be divided into 1024 blocks,
              and an array of 1024 rows can be obtained.
                                                                                     1x64
                 2   3   4   6   8   3   7   2   2   3   4   6   8   3   7   2   8    2   8   2
                 8   2   8   2   8   2



1 block 8x8

                                                                             ・
                                                                             ・
                                                                             ・
                                                                             ・
                             8x8                                         1024 rows                7
10 images




Image 0   Image 1   Image 2   Image 3   Image 4




Image 5   Image 6   Image 7   Image 8   Image 9

                                                  8
Making of Code book

 The  array of 10240 that can be done
  by reading 10 images is made
 The code book is made by using the
  k-means method.
   Making Code book (size 256)




                                         9
K-means algorithm
Step 1) k initial "means" are randomly selected from
the data set .
Step 2) k clusters are created by associating every
observation with the nearest mean.
Step 3) The centroid of each of the k clusters
becomes the new means.
Step 4) Steps 2 and 3 are repeated until
convergence has been reached.




Step 1        Step 2         Step 3         Step 4     10
Extract each image’s feature vector (1)
           The feature vector are extracted by using code book.
           There is arrangement 1024 per one image.
           Arranging an individual distance of the array each one
            and code book is measured
           The number of the nearest code is returned.
           Which code how many times came out is preserved as
            an array.
                                                             5
        1x64
                                                             4
2 3 4 7 8 9 2 ##########   Code 7
                                                             3
                           Code 38
                           Code 72                           2

                           Code 200                          1
                           Code 7
                                      Code 200
                                      Code 72
                                       Code 38
                                             7               0
        ・                                                        1                        256
        ・                                                            7   38   72   200
        ・
    1024 rows                                    Code book                               11
Result – image and feature vector(1)
    Image 0              Image 1




                                   12
Result – image and feature vector(2)
    Image 2              Image 3




                                   13
Result – image and feature vector(3)
    Image 4              Image 5




                                   14
Result – image and feature vector(4)
    Image 6              Image 7




                                   15
Result – image and feature vector(5)
    Image 8              Image 9




                                   16
Result - Distance of feature vector(1)
         Euclidean distance between feature vectors
          is measured, and the accuracy of the code
          book is seen.
   P and Q are assumed to be two feature vectors.
   Data : x = (x1, x2, ..., xn) and y = (y1, y2, ..., yn)
   n : size of the feature vector
   The distance of P and Q is below.




                                                             17
Result - Distance of feature vector(2)
      256 feature0    feature1       feature2    feature3    feature4    feature5    feature6    feature7    feature8    feature9
feature0             0 0.279945 0.280761 0.226158 0.291376 0.322875 0.300502                        0.2307     0.23509 0.228708
feature1   0.279945              0     0.19849 0.271927 0.318353 0.352126 0.324807 0.272823 0.269333                       0.30847
feature2   0.280761     0.19849                 0 0.308124 0.352732 0.378846 0.359333 0.310492 0.316141 0.324054
feature3   0.226158 0.271927 0.308124                       0 0.221109 0.276269 0.240734           0.09959 0.086469 0.136439
feature4   0.291376 0.318353 0.352732 0.221109                          0 0.222279     0.17478 0.202749 0.210865 0.248531
feature5   0.322875 0.352126 0.378846 0.276269 0.222279                             0 0.084866 0.282603 0.270858 0.306136
feature6   0.300502 0.324807 0.359333 0.240734                 0.17478 0.084866                 0 0.245255 0.232873 0.276931
feature7     0.2307 0.272823 0.310492              0.09959 0.202749 0.282603 0.245255                       0 0.105974 0.155957
feature8    0.23509 0.269333 0.316141 0.086469 0.210865 0.270858 0.232873 0.105974                                      0 0.152093
feature9   0.228708     0.30847 0.324054 0.136439 0.248531 0.306136 0.276931 0.155957 0.152093                                      0

    :minimum distance
                                                 The image5 and image6 is the same
                                                  persons, image5 doesn't wear glasses,
                                                  and image6 wears glasses.
                                                 Between feature5 and feature6 is
                                                  minimum distance.
Image 5              Image 6                                                                                                18
Conclusion
   In my research, I study a new image search
    technique based on the code book
    information. The code book is obtained using
    the VQ method.
   It is thought that an accurate feature vector
    was able to be extracted about the accuracy
    of the feature vector because the distance
    between Feature5 and 6 was short.



           Information retrieval based on
       "the contents of a image themselves."        19
Future work
   The background is nullified.

   The feature vector is extracted in the block
    of a different size like the block of not the
    block of 8x8 size but 16x16 size etc.

   Multimedia retrieval that uses SVM.




                                                20
Thank you for your attention!



                                21

Más contenido relacionado

La actualidad más candente

Protein Secondary Structure Prediction using Deep Learning methods
Protein Secondary Structure Prediction using Deep Learning methodsProtein Secondary Structure Prediction using Deep Learning methods
Protein Secondary Structure Prediction using Deep Learning methodsChrysoula Kosma
 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesIJCSES Journal
 
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONS
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONSA (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONS
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONSIJNSA Journal
 
Kccsi 2012 a real-time robust object tracking-v2
Kccsi 2012   a real-time robust object tracking-v2Kccsi 2012   a real-time robust object tracking-v2
Kccsi 2012 a real-time robust object tracking-v2Prarinya Siritanawan
 
Shearlet Frames and Optimally Sparse Approximations
Shearlet Frames and Optimally Sparse ApproximationsShearlet Frames and Optimally Sparse Approximations
Shearlet Frames and Optimally Sparse ApproximationsJakob Lemvig
 
Lecture 7: DHT and P2P Games
Lecture 7: DHT and P2P GamesLecture 7: DHT and P2P Games
Lecture 7: DHT and P2P GamesWei Tsang Ooi
 
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICES
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICESA BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICES
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICEScsandit
 
Esoteric LINQ and Structural Madness
Esoteric LINQ and Structural MadnessEsoteric LINQ and Structural Madness
Esoteric LINQ and Structural MadnessChris Eargle
 
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...Yusuf Bhujwalla
 
Multimodal Residual Networks for Visual QA
Multimodal Residual Networks for Visual QAMultimodal Residual Networks for Visual QA
Multimodal Residual Networks for Visual QAJin-Hwa Kim
 
Fast dct algorithm using winograd’s method
Fast dct algorithm using winograd’s methodFast dct algorithm using winograd’s method
Fast dct algorithm using winograd’s methodIAEME Publication
 
WABI2012-SuccinctMultibitTree
WABI2012-SuccinctMultibitTreeWABI2012-SuccinctMultibitTree
WABI2012-SuccinctMultibitTreeYasuo Tabei
 
Mlab2012 tabei 20120806
Mlab2012 tabei 20120806Mlab2012 tabei 20120806
Mlab2012 tabei 20120806Yasuo Tabei
 

La actualidad más candente (16)

Protein Secondary Structure Prediction using Deep Learning methods
Protein Secondary Structure Prediction using Deep Learning methodsProtein Secondary Structure Prediction using Deep Learning methods
Protein Secondary Structure Prediction using Deep Learning methods
 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
 
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONS
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONSA (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONS
A (2, N) VISUAL CRYPTOGRAPHIC TECHNIQUE FOR BANKING APPLICATIONS
 
Kccsi 2012 a real-time robust object tracking-v2
Kccsi 2012   a real-time robust object tracking-v2Kccsi 2012   a real-time robust object tracking-v2
Kccsi 2012 a real-time robust object tracking-v2
 
JavaYDL7
JavaYDL7JavaYDL7
JavaYDL7
 
Shearlet Frames and Optimally Sparse Approximations
Shearlet Frames and Optimally Sparse ApproximationsShearlet Frames and Optimally Sparse Approximations
Shearlet Frames and Optimally Sparse Approximations
 
Lecture 7: DHT and P2P Games
Lecture 7: DHT and P2P GamesLecture 7: DHT and P2P Games
Lecture 7: DHT and P2P Games
 
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICES
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICESA BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICES
A BLIND ROBUST WATERMARKING SCHEME BASED ON SVD AND CIRCULANT MATRICES
 
Esoteric LINQ and Structural Madness
Esoteric LINQ and Structural MadnessEsoteric LINQ and Structural Madness
Esoteric LINQ and Structural Madness
 
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...
An RKHS Approach to Systematic Kernel Selection in Nonlinear System Identific...
 
Multimodal Residual Networks for Visual QA
Multimodal Residual Networks for Visual QAMultimodal Residual Networks for Visual QA
Multimodal Residual Networks for Visual QA
 
Fast dct algorithm using winograd’s method
Fast dct algorithm using winograd’s methodFast dct algorithm using winograd’s method
Fast dct algorithm using winograd’s method
 
Ijcatr04041020
Ijcatr04041020Ijcatr04041020
Ijcatr04041020
 
Bt32444450
Bt32444450Bt32444450
Bt32444450
 
WABI2012-SuccinctMultibitTree
WABI2012-SuccinctMultibitTreeWABI2012-SuccinctMultibitTree
WABI2012-SuccinctMultibitTree
 
Mlab2012 tabei 20120806
Mlab2012 tabei 20120806Mlab2012 tabei 20120806
Mlab2012 tabei 20120806
 

Destacado

Valtech jamespot-social business
Valtech jamespot-social businessValtech jamespot-social business
Valtech jamespot-social businessAlain GARNIER
 
20110111040208282
2011011104020828220110111040208282
20110111040208282capavez_88
 
Play pets and co introduction
Play pets and co introductionPlay pets and co introduction
Play pets and co introductionazieger
 
The literature review
The literature reviewThe literature review
The literature reviews1160123
 
Jamespot web2 connect2010 - l'avenir des reseaux sociaux en entreprise
Jamespot  web2 connect2010 - l'avenir des reseaux sociaux en entrepriseJamespot  web2 connect2010 - l'avenir des reseaux sociaux en entreprise
Jamespot web2 connect2010 - l'avenir des reseaux sociaux en entrepriseAlain GARNIER
 
Trobada mediació
Trobada mediacióTrobada mediació
Trobada mediaciónemracaral
 
Newsletter Q4 Issue II
Newsletter Q4 Issue IINewsletter Q4 Issue II
Newsletter Q4 Issue IImandalsailik
 

Destacado (16)

Week10
Week10Week10
Week10
 
Valtech jamespot-social business
Valtech jamespot-social businessValtech jamespot-social business
Valtech jamespot-social business
 
20110111040208282
2011011104020828220110111040208282
20110111040208282
 
Play pets and co introduction
Play pets and co introductionPlay pets and co introduction
Play pets and co introduction
 
Week14
Week14Week14
Week14
 
Elisabeth Interview
Elisabeth InterviewElisabeth Interview
Elisabeth Interview
 
The literature review
The literature reviewThe literature review
The literature review
 
Til Elisabeth 29.Januar
Til Elisabeth 29.JanuarTil Elisabeth 29.Januar
Til Elisabeth 29.Januar
 
Trust
TrustTrust
Trust
 
Jamespot web2 connect2010 - l'avenir des reseaux sociaux en entreprise
Jamespot  web2 connect2010 - l'avenir des reseaux sociaux en entrepriseJamespot  web2 connect2010 - l'avenir des reseaux sociaux en entreprise
Jamespot web2 connect2010 - l'avenir des reseaux sociaux en entreprise
 
Week11
Week11Week11
Week11
 
Week13
Week13Week13
Week13
 
Portfolio Samples
Portfolio SamplesPortfolio Samples
Portfolio Samples
 
Trobada mediació
Trobada mediacióTrobada mediació
Trobada mediació
 
Week12
Week12Week12
Week12
 
Newsletter Q4 Issue II
Newsletter Q4 Issue IINewsletter Q4 Issue II
Newsletter Q4 Issue II
 

Similar a Thesis writing - week9

Decimal To Hexadecimal Conversion Tips
Decimal To Hexadecimal Conversion TipsDecimal To Hexadecimal Conversion Tips
Decimal To Hexadecimal Conversion TipsKathleenSSmith
 
Learning to Spot and Refactor Inconsistent Method Names
Learning to Spot and Refactor Inconsistent Method NamesLearning to Spot and Refactor Inconsistent Method Names
Learning to Spot and Refactor Inconsistent Method NamesDongsun Kim
 
L1 Sudoku
L1 SudokuL1 Sudoku
L1 Sudokubnmoran
 
11.secure compressed image transmission using self organizing feature maps
11.secure compressed image transmission using self organizing feature maps11.secure compressed image transmission using self organizing feature maps
11.secure compressed image transmission using self organizing feature mapsAlexander Decker
 
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...Sangwoo Mo
 
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...Gurbinder Gill
 
Digital Image Processing: Programming Fundamentals
Digital Image Processing: Programming FundamentalsDigital Image Processing: Programming Fundamentals
Digital Image Processing: Programming FundamentalsDivya K Rathore
 
Presentation vision transformersppt.pptx
Presentation vision transformersppt.pptxPresentation vision transformersppt.pptx
Presentation vision transformersppt.pptxhtn540
 
Image classification using neural network
Image classification using neural networkImage classification using neural network
Image classification using neural networkBhavyateja Potineni
 
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....OthmaneABOUELAECHA
 
Blur Filter - Hanpo
Blur Filter - HanpoBlur Filter - Hanpo
Blur Filter - HanpoHanpo Cheng
 
Vector Tile for Sea Wind
Vector Tile for Sea WindVector Tile for Sea Wind
Vector Tile for Sea WindSANGHEE SHIN
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonAditya Bhattacharya
 
Image retrieval using vlad with
Image retrieval using vlad withImage retrieval using vlad with
Image retrieval using vlad withcsandit
 
Image Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple FeaturesImage Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple Featurescsandit
 
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...A Novel Method for Image Watermarking Using Luminance Based Block Selection a...
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...IJERA Editor
 
Visual cryptography1
Visual cryptography1Visual cryptography1
Visual cryptography1patisa
 
Signature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiSignature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiDr. Vinayak Bharadi
 

Similar a Thesis writing - week9 (20)

Decimal To Hexadecimal Conversion Tips
Decimal To Hexadecimal Conversion TipsDecimal To Hexadecimal Conversion Tips
Decimal To Hexadecimal Conversion Tips
 
Learning to Spot and Refactor Inconsistent Method Names
Learning to Spot and Refactor Inconsistent Method NamesLearning to Spot and Refactor Inconsistent Method Names
Learning to Spot and Refactor Inconsistent Method Names
 
L1 Sudoku
L1 SudokuL1 Sudoku
L1 Sudoku
 
11.secure compressed image transmission using self organizing feature maps
11.secure compressed image transmission using self organizing feature maps11.secure compressed image transmission using self organizing feature maps
11.secure compressed image transmission using self organizing feature maps
 
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...
A Unified Framework for Computer Vision Tasks: (Conditional) Generative Model...
 
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...
Efficient Variable Size Template Matching Using Fast Normalized Cross Correla...
 
Digital Image Processing: Programming Fundamentals
Digital Image Processing: Programming FundamentalsDigital Image Processing: Programming Fundamentals
Digital Image Processing: Programming Fundamentals
 
Presentation vision transformersppt.pptx
Presentation vision transformersppt.pptxPresentation vision transformersppt.pptx
Presentation vision transformersppt.pptx
 
Image classification using neural network
Image classification using neural networkImage classification using neural network
Image classification using neural network
 
Embedded mesh colors
Embedded mesh colorsEmbedded mesh colors
Embedded mesh colors
 
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....
StoryVisualization using StoryGAN implemented by pytorch on Pororro Dataset​....
 
Blur Filter - Hanpo
Blur Filter - HanpoBlur Filter - Hanpo
Blur Filter - Hanpo
 
Vector Tile for Sea Wind
Vector Tile for Sea WindVector Tile for Sea Wind
Vector Tile for Sea Wind
 
Computer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathonComputer vision-nit-silchar-hackathon
Computer vision-nit-silchar-hackathon
 
Image retrieval using vlad with
Image retrieval using vlad withImage retrieval using vlad with
Image retrieval using vlad with
 
Image Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple FeaturesImage Retrieval Using VLAD with Multiple Features
Image Retrieval Using VLAD with Multiple Features
 
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...A Novel Method for Image Watermarking Using Luminance Based Block Selection a...
A Novel Method for Image Watermarking Using Luminance Based Block Selection a...
 
Visual cryptography1
Visual cryptography1Visual cryptography1
Visual cryptography1
 
Visual cryptography1
Visual cryptography1Visual cryptography1
Visual cryptography1
 
Signature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertatiSignature recognition using clustering techniques dissertati
Signature recognition using clustering techniques dissertati
 

Último

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
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
 
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
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek SchlawackFwdays
 
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
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 3652toLead Limited
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
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
 
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
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embeddingZilliz
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfRankYa
 
"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
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 

Último (20)

What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
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
 
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
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
"Subclassing and Composition – A Pythonic Tour of Trade-Offs", Hynek Schlawack
 
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
 
Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365Ensuring Technical Readiness For Copilot in Microsoft 365
Ensuring Technical Readiness For Copilot in Microsoft 365
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
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
 
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
 
Training state-of-the-art general text embedding
Training state-of-the-art general text embeddingTraining state-of-the-art general text embedding
Training state-of-the-art general text embedding
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Search Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 2024.pdfSearch Engine Optimization SEO PDF for 2024.pdf
Search Engine Optimization SEO PDF for 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...
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 

Thesis writing - week9

  • 1. Information Retrieved - Image based search s1160123 Tomoyuki Soeta Supervised by Prof. Qiangfu Zhao System Intelligence Lab 1
  • 2. Outline  Introduction  Information Retrieval  VQ (Vector Quantization)  Divide into the 8x8 block  Making of Code book  K-means algorithm  Extract each image’s feature vector  Result  Image and feature vector  Distance of feature vector  Conclusion  Future work 2
  • 3. Introduction  I want to aim at the improvement of information retrieval system to search it even if the input data are documents or images.  I have charge of a research on information retrieval based on a image.  To search images using a search engine, we may use the index attached to the image, the file name, etc. as the key-words. We may also use "the contents of an image themselves."  I study a new image search technique based on the code book information. 3
  • 4. Information Retrieved Image Text Divide into the block (1 block 8x8) Morphological Analysis Code book Word Filtering Code of each block Feature Vector Feature Vector NNTree or SVM 4
  • 5. VQ (Vector Quantization)  Compression coding of images  Image compression technology image  In my study, I use VQ to Vector translate an image into a bag- Quantization of-blocks (BOB) (VQ) same way as document search 5 feature vector
  • 6. Divide into the 8x8 block (1)  I used 10 facial images with the size 256x256.  images are converted to gray scale images.  Divided into the block (one-block 8x8 size).  Each image obtains the block of 32×32 pieces severally. 32 blocks 32 b l 1 block 8x8 o c k s 6
  • 7. Divide into the 8x8 block (2)  Block’s pixel value is read.  Pixel read value is stored in the array of 1x64.  One image can be divided into 1024 blocks, and an array of 1024 rows can be obtained. 1x64 2 3 4 6 8 3 7 2 2 3 4 6 8 3 7 2 8 2 8 2 8 2 8 2 8 2 1 block 8x8 ・ ・ ・ ・ 8x8 1024 rows 7
  • 8. 10 images Image 0 Image 1 Image 2 Image 3 Image 4 Image 5 Image 6 Image 7 Image 8 Image 9 8
  • 9. Making of Code book  The array of 10240 that can be done by reading 10 images is made  The code book is made by using the k-means method.  Making Code book (size 256) 9
  • 10. K-means algorithm Step 1) k initial "means" are randomly selected from the data set . Step 2) k clusters are created by associating every observation with the nearest mean. Step 3) The centroid of each of the k clusters becomes the new means. Step 4) Steps 2 and 3 are repeated until convergence has been reached. Step 1 Step 2 Step 3 Step 4 10
  • 11. Extract each image’s feature vector (1)  The feature vector are extracted by using code book.  There is arrangement 1024 per one image.  Arranging an individual distance of the array each one and code book is measured  The number of the nearest code is returned.  Which code how many times came out is preserved as an array. 5 1x64 4 2 3 4 7 8 9 2 ########## Code 7 3 Code 38 Code 72 2 Code 200 1 Code 7 Code 200 Code 72 Code 38 7 0 ・ 1 256 ・ 7 38 72 200 ・ 1024 rows Code book 11
  • 12. Result – image and feature vector(1) Image 0 Image 1 12
  • 13. Result – image and feature vector(2) Image 2 Image 3 13
  • 14. Result – image and feature vector(3) Image 4 Image 5 14
  • 15. Result – image and feature vector(4) Image 6 Image 7 15
  • 16. Result – image and feature vector(5) Image 8 Image 9 16
  • 17. Result - Distance of feature vector(1)  Euclidean distance between feature vectors is measured, and the accuracy of the code book is seen.  P and Q are assumed to be two feature vectors.  Data : x = (x1, x2, ..., xn) and y = (y1, y2, ..., yn)  n : size of the feature vector  The distance of P and Q is below. 17
  • 18. Result - Distance of feature vector(2) 256 feature0 feature1 feature2 feature3 feature4 feature5 feature6 feature7 feature8 feature9 feature0 0 0.279945 0.280761 0.226158 0.291376 0.322875 0.300502 0.2307 0.23509 0.228708 feature1 0.279945 0 0.19849 0.271927 0.318353 0.352126 0.324807 0.272823 0.269333 0.30847 feature2 0.280761 0.19849 0 0.308124 0.352732 0.378846 0.359333 0.310492 0.316141 0.324054 feature3 0.226158 0.271927 0.308124 0 0.221109 0.276269 0.240734 0.09959 0.086469 0.136439 feature4 0.291376 0.318353 0.352732 0.221109 0 0.222279 0.17478 0.202749 0.210865 0.248531 feature5 0.322875 0.352126 0.378846 0.276269 0.222279 0 0.084866 0.282603 0.270858 0.306136 feature6 0.300502 0.324807 0.359333 0.240734 0.17478 0.084866 0 0.245255 0.232873 0.276931 feature7 0.2307 0.272823 0.310492 0.09959 0.202749 0.282603 0.245255 0 0.105974 0.155957 feature8 0.23509 0.269333 0.316141 0.086469 0.210865 0.270858 0.232873 0.105974 0 0.152093 feature9 0.228708 0.30847 0.324054 0.136439 0.248531 0.306136 0.276931 0.155957 0.152093 0  :minimum distance  The image5 and image6 is the same persons, image5 doesn't wear glasses, and image6 wears glasses.  Between feature5 and feature6 is minimum distance. Image 5 Image 6 18
  • 19. Conclusion  In my research, I study a new image search technique based on the code book information. The code book is obtained using the VQ method.  It is thought that an accurate feature vector was able to be extracted about the accuracy of the feature vector because the distance between Feature5 and 6 was short. Information retrieval based on "the contents of a image themselves." 19
  • 20. Future work  The background is nullified.  The feature vector is extracted in the block of a different size like the block of not the block of 8x8 size but 16x16 size etc.  Multimedia retrieval that uses SVM. 20
  • 21. Thank you for your attention! 21