SlideShare a Scribd company logo
1 of 21
Blind Source Camera Identification
Introduction
In today’s digital age, the creation and manipulation of digital images is
made simple by digital processing tools that are easily and widely
available. As a consequence, we can no longer take the authenticity of
images, analog or digital, for granted. This is especially true when it comes
to legal photographic evidence
Introduction
Although digital watermarks have been proposed as a tool to provide
authenticity to images, it is a fact that the overwhelming majority of
images that are captured today do not contain a digital watermark.
And this situation is likely to continue for the foreseeable future.
Problem Statement
There are images from unknown source with no or untraceable
watermark, but it is known to originate from either one of limited given
standard cameras , say x, y, z. It is needed to classify the images into
the groups based on originality. So the problem simplifies to whether a
particular image came was originated from camera x, camera y or
camera z.
Related Works
 A number of features of images have been identified that can
prove to be a crucial part in classification .
 Classification of the images have been a matter of study for past
few years and it has been done with maximum achieved average
accuracy of 93.42 % for set of two cameras, namely Nikon and
Sony.
 Classification of images among 5 different cameras has been
conducted with an average accuracy of 88.02 %.
 It is found out that a full generality of classification i.e. classification
among a set of unknown number of devices , is difficult on a higher
level.
Goals and Objectives
 Identifying features that can be used in classification.
 Develop a classifier function that classifies images into two groups
based on originality.
Methodology
 34 features have been identified till now that are and can be used
in classification.
 The features are mentioned in the following slides :-
AVERAGE PIXEL VALUE
This measure is based on the gray world assumption, which states
that the average values in RGB channels of an image should
average to gray, assuming that the images has enough color
variations. Thus the features are the mean value of the 3 RGB
channels (3 features).
RGB PAIRS CORRELATION
This measure attempts to capture the fact that depending
on the camera structure, the correlation between different color
bands could vary. There are 3 correlation pairs, namely RG, RB (3
features).
NEIGHBOR DISTRIBUTION CENTER OF MASS
This measure is calculated for each color band separately
by first calculating the number of pixel neighbors for each pixel
value, where a pixels neighbor are defined as all pixels which
have a difference of value of 1 or -1, from the pixel value in
question.
RGB pairs energy ratio
It is important because it is used in the process of white point correction which
is an integral part of a camera pipeline. The calculated features (3 features) are:
E1 = |G|2 /|B|2
E2 = |G|2 /|R|2
E3 = |B|2 /|R|2
WAVELET DOMAIN STATISTICS
Decomposed each color band of the image using separable quadratic
mirror filters and then calculated the mean for each of the 3 resulting sub-bands
(9 features).
IMAGE QUALITY METRICS (IQM)
We can categorize the set of IQM used into 3 classes :-
• The pixel difference based measures (i.e. mean square error, mean absolute
error, modified infinity norm)
• The correlation based measures (i.e. normalized cross correlation, Czekonowski
correlation)
• The spectral distance based measures (i.e. spectral phase and magnitude errors)
This is a set of 13 features.
Classifier
• We are going to use Support Vector Machine(SVM) Classifier.
• It is primarily a classier method that performs classification tasks by
constructing hyper planes in a multidimensional space.
• To construct an optimal hyper plane, SVM employs an iterative
training algorithm, which is used to minimize an error function.
Linear Classifier
• It classifies data set by linear
hyper plane.
The image below is the output from the simulation of linear classification using octave.
Gaussian Kernel Classifier
• It is non linear SVM kernel
• Also known as Radial
basis function (RBF) kernel
The image beside is the
output from the simulation
of Gaussian classification
using octave.
SVM Classifier can classify data in at most two groups at a time.
So how we can classify data into more than 2 groups ?
We can do that by training 3 classifiers , for each group vs all other groups
Group1 vs All
Group2 Vs All
Group3 Vs All
Conclusion
The technique studied in the research project will
aide in improvement in performance and accuracy
of blind source camera identification.
Reference
[1] Mehdi Kharrazi , Husrev T. Sencar and Nasir Memon ,
”Blind Source Camera Identification”.
[2] C.-C. Chang and C.-J. Lin, LIBSVM: a library for support vector
machines, 2001, software available at
http://www.csie.ntu.edu.tw/˜cjlin/libsvm.
[3] Andrew Ng, ”Machine Learning CS-229 Standford”
http://cs229.standford.edu

More Related Content

What's hot

IMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSINGIMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSINGgarima0690
 
Band ratioing presentation
Band ratioing presentationBand ratioing presentation
Band ratioing presentationsk asadul haque
 
Region based image segmentation
Region based image segmentationRegion based image segmentation
Region based image segmentationSafayet Hossain
 
Region based segmentation
Region based segmentationRegion based segmentation
Region based segmentationramya marichamy
 
Simultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesSimultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesCristina Pérez Benito
 
Image classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIImage classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIP.K. Mani
 
Filtering underwater image
Filtering underwater imageFiltering underwater image
Filtering underwater imagerishithabandi1
 
VIRTUAL RESTORATION OF DAMAGED IMAGES
VIRTUAL RESTORATION OF DAMAGED IMAGESVIRTUAL RESTORATION OF DAMAGED IMAGES
VIRTUAL RESTORATION OF DAMAGED IMAGESVardan Kurkchiyan
 
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...Dibya Jyoti Bora
 
Images Analysis  in matlab
Images Analysis  in matlabImages Analysis  in matlab
Images Analysis  in matlabmustafa_92
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image FundamentalsKalyan Acharjya
 
Image segmentation for high resolution images
Image segmentation for high resolution imagesImage segmentation for high resolution images
Image segmentation for high resolution imagesjeet patalia
 
Image analysis basics and principles
Image analysis basics and principlesImage analysis basics and principles
Image analysis basics and principlesMohsin Siddique
 
Digital image processing
Digital image processingDigital image processing
Digital image processingVandana Verma
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretationP.K. Mani
 
A Trained CNN Based Resolution Enhancement of Digital Images
A Trained CNN Based Resolution Enhancement of Digital ImagesA Trained CNN Based Resolution Enhancement of Digital Images
A Trained CNN Based Resolution Enhancement of Digital ImagesIJMTST Journal
 

What's hot (20)

IMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSINGIMAGE FUSION IN IMAGE PROCESSING
IMAGE FUSION IN IMAGE PROCESSING
 
Band ratioing presentation
Band ratioing presentationBand ratioing presentation
Band ratioing presentation
 
Region based image segmentation
Region based image segmentationRegion based image segmentation
Region based image segmentation
 
Region based segmentation
Region based segmentationRegion based segmentation
Region based segmentation
 
Depth estimation using deep learning
Depth estimation using deep learningDepth estimation using deep learning
Depth estimation using deep learning
 
Simultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color ImagesSimultaneous Smoothing and Sharpening of Color Images
Simultaneous Smoothing and Sharpening of Color Images
 
Image classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANIImage classification, remote sensing, P K MANI
Image classification, remote sensing, P K MANI
 
Filtering underwater image
Filtering underwater imageFiltering underwater image
Filtering underwater image
 
VIRTUAL RESTORATION OF DAMAGED IMAGES
VIRTUAL RESTORATION OF DAMAGED IMAGESVIRTUAL RESTORATION OF DAMAGED IMAGES
VIRTUAL RESTORATION OF DAMAGED IMAGES
 
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...
Multispectral Satellite Color Image Segmentation Using Fuzzy Based Innovative...
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
regions
regionsregions
regions
 
Images Analysis  in matlab
Images Analysis  in matlabImages Analysis  in matlab
Images Analysis  in matlab
 
3D reconstruction
3D reconstruction3D reconstruction
3D reconstruction
 
Digital Image Fundamentals
Digital Image FundamentalsDigital Image Fundamentals
Digital Image Fundamentals
 
Image segmentation for high resolution images
Image segmentation for high resolution imagesImage segmentation for high resolution images
Image segmentation for high resolution images
 
Image analysis basics and principles
Image analysis basics and principlesImage analysis basics and principles
Image analysis basics and principles
 
Digital image processing
Digital image processingDigital image processing
Digital image processing
 
Digital image processing and interpretation
Digital image processing and interpretationDigital image processing and interpretation
Digital image processing and interpretation
 
A Trained CNN Based Resolution Enhancement of Digital Images
A Trained CNN Based Resolution Enhancement of Digital ImagesA Trained CNN Based Resolution Enhancement of Digital Images
A Trained CNN Based Resolution Enhancement of Digital Images
 

Viewers also liked

Top 8 contract manager resume samples
Top 8 contract manager resume samplesTop 8 contract manager resume samples
Top 8 contract manager resume samplesLucyAlexis678
 
historia regional
historia regionalhistoria regional
historia regionaljanet251099
 
Kelompok 8 sistem limfa
Kelompok 8 sistem limfaKelompok 8 sistem limfa
Kelompok 8 sistem limfaNyoman Rahayu
 
Top 8 contracts administrator resume samples
Top 8 contracts administrator resume samplesTop 8 contracts administrator resume samples
Top 8 contracts administrator resume samplesLucyAlexis678
 
Top 8 contract administrator resume samples
Top 8 contract administrator resume samplesTop 8 contract administrator resume samples
Top 8 contract administrator resume samplesLucyAlexis678
 
INNPERIUM - Mercado e Produto
INNPERIUM - Mercado e ProdutoINNPERIUM - Mercado e Produto
INNPERIUM - Mercado e ProdutoWagner Henrique
 
INNPERIUM - A Oportunidade
INNPERIUM - A OportunidadeINNPERIUM - A Oportunidade
INNPERIUM - A OportunidadeWagner Henrique
 
Google Form-д асуулт оруулах
Google Form-д асуулт оруулахGoogle Form-д асуулт оруулах
Google Form-д асуулт оруулахBatzaya Dashdondog
 
Casos De Aplicación Reglamentos Del Aprendiz
Casos De Aplicación Reglamentos Del AprendizCasos De Aplicación Reglamentos Del Aprendiz
Casos De Aplicación Reglamentos Del AprendizGuerrerojhonatan
 
Seattle AT&T Hackathon
Seattle AT&T HackathonSeattle AT&T Hackathon
Seattle AT&T HackathonDoug Sillars
 
sf chronicle Page 1
sf chronicle Page 1sf chronicle Page 1
sf chronicle Page 1Sherry Higgs
 
la fisica en relacion a otras ciencias
la fisica en relacion a otras cienciasla fisica en relacion a otras ciencias
la fisica en relacion a otras cienciasAngieJaramillo27
 
tema 2 de tecnología aplicada a la educación
tema 2 de tecnología aplicada a la educacióntema 2 de tecnología aplicada a la educación
tema 2 de tecnología aplicada a la educaciónaracelis2
 
My First CorporateInternship at Graphicacy
My First CorporateInternship at Graphicacy My First CorporateInternship at Graphicacy
My First CorporateInternship at Graphicacy Martin Massiah
 
Factores que influyen en la toma de decision MAD
Factores que influyen en la toma de decision  MADFactores que influyen en la toma de decision  MAD
Factores que influyen en la toma de decision MADPatricia Lozada Lopez
 
Top 8 contract specialist resume samples
Top 8 contract specialist resume samplesTop 8 contract specialist resume samples
Top 8 contract specialist resume samplesLucyAlexis678
 
Relación de la física con otras ciencias pablo iña
Relación de la física con otras ciencias pablo iñaRelación de la física con otras ciencias pablo iña
Relación de la física con otras ciencias pablo iñaPablito2016
 
Top 8 country manager resume samples
Top 8 country manager resume samplesTop 8 country manager resume samples
Top 8 country manager resume samplesFabianBarthez012
 
Línea tecnológica del programa dolca
Línea tecnológica del programa dolcaLínea tecnológica del programa dolca
Línea tecnológica del programa dolcaGuerrerojhonatan
 

Viewers also liked (20)

Top 8 contract manager resume samples
Top 8 contract manager resume samplesTop 8 contract manager resume samples
Top 8 contract manager resume samples
 
historia regional
historia regionalhistoria regional
historia regional
 
Kelompok 8 sistem limfa
Kelompok 8 sistem limfaKelompok 8 sistem limfa
Kelompok 8 sistem limfa
 
Top 8 contracts administrator resume samples
Top 8 contracts administrator resume samplesTop 8 contracts administrator resume samples
Top 8 contracts administrator resume samples
 
Top 8 contract administrator resume samples
Top 8 contract administrator resume samplesTop 8 contract administrator resume samples
Top 8 contract administrator resume samples
 
INNPERIUM - Mercado e Produto
INNPERIUM - Mercado e ProdutoINNPERIUM - Mercado e Produto
INNPERIUM - Mercado e Produto
 
INNPERIUM - A Oportunidade
INNPERIUM - A OportunidadeINNPERIUM - A Oportunidade
INNPERIUM - A Oportunidade
 
Google Form-д асуулт оруулах
Google Form-д асуулт оруулахGoogle Form-д асуулт оруулах
Google Form-д асуулт оруулах
 
Casos De Aplicación Reglamentos Del Aprendiz
Casos De Aplicación Reglamentos Del AprendizCasos De Aplicación Reglamentos Del Aprendiz
Casos De Aplicación Reglamentos Del Aprendiz
 
Seattle AT&T Hackathon
Seattle AT&T HackathonSeattle AT&T Hackathon
Seattle AT&T Hackathon
 
sf chronicle Page 1
sf chronicle Page 1sf chronicle Page 1
sf chronicle Page 1
 
la fisica en relacion a otras ciencias
la fisica en relacion a otras cienciasla fisica en relacion a otras ciencias
la fisica en relacion a otras ciencias
 
tema 2 de tecnología aplicada a la educación
tema 2 de tecnología aplicada a la educacióntema 2 de tecnología aplicada a la educación
tema 2 de tecnología aplicada a la educación
 
My First CorporateInternship at Graphicacy
My First CorporateInternship at Graphicacy My First CorporateInternship at Graphicacy
My First CorporateInternship at Graphicacy
 
TRANSISTORES
TRANSISTORESTRANSISTORES
TRANSISTORES
 
Factores que influyen en la toma de decision MAD
Factores que influyen en la toma de decision  MADFactores que influyen en la toma de decision  MAD
Factores que influyen en la toma de decision MAD
 
Top 8 contract specialist resume samples
Top 8 contract specialist resume samplesTop 8 contract specialist resume samples
Top 8 contract specialist resume samples
 
Relación de la física con otras ciencias pablo iña
Relación de la física con otras ciencias pablo iñaRelación de la física con otras ciencias pablo iña
Relación de la física con otras ciencias pablo iña
 
Top 8 country manager resume samples
Top 8 country manager resume samplesTop 8 country manager resume samples
Top 8 country manager resume samples
 
Línea tecnológica del programa dolca
Línea tecnológica del programa dolcaLínea tecnológica del programa dolca
Línea tecnológica del programa dolca
 

Similar to Blind Source Camera Identification

Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...
Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...
Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...IRJET Journal
 
IRJET- 3D Vision System using Calibrated Stereo Camera
IRJET- 3D Vision System using Calibrated Stereo CameraIRJET- 3D Vision System using Calibrated Stereo Camera
IRJET- 3D Vision System using Calibrated Stereo CameraIRJET Journal
 
Information search using text and image query
Information search using text and image queryInformation search using text and image query
Information search using text and image queryeSAT Publishing House
 
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by MadhuAN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by MadhuMadhu Rock
 
Information search using text and image query
Information search using text and image queryInformation search using text and image query
Information search using text and image queryeSAT Journals
 
Paper id 21201419
Paper id 21201419Paper id 21201419
Paper id 21201419IJRAT
 
Performance of Efficient Closed-Form Solution to Comprehensive Frontier Exposure
Performance of Efficient Closed-Form Solution to Comprehensive Frontier ExposurePerformance of Efficient Closed-Form Solution to Comprehensive Frontier Exposure
Performance of Efficient Closed-Form Solution to Comprehensive Frontier Exposureiosrjce
 
Image processing
Image processingImage processing
Image processingkamal330
 
IRJET- Crowd Density Estimation using Image Processing
IRJET- Crowd Density Estimation using Image ProcessingIRJET- Crowd Density Estimation using Image Processing
IRJET- Crowd Density Estimation using Image ProcessingIRJET Journal
 
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
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern PresentationDaniel Cahall
 
A Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVMA Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVMIJEEE
 
Image processing sw & hw
Image processing sw & hwImage processing sw & hw
Image processing sw & hwamalalhait
 
An Introduction to digital image processing
An Introduction to digital image processingAn Introduction to digital image processing
An Introduction to digital image processingnastaranEmamjomeh1
 
Blur Detection Methods for Digital Images-A Survey
Blur Detection Methods for Digital Images-A SurveyBlur Detection Methods for Digital Images-A Survey
Blur Detection Methods for Digital Images-A SurveyEditor IJCATR
 
IRJET- Low Light Image Enhancement using Convolutional Neural Network
IRJET-  	  Low Light Image Enhancement using Convolutional Neural NetworkIRJET-  	  Low Light Image Enhancement using Convolutional Neural Network
IRJET- Low Light Image Enhancement using Convolutional Neural NetworkIRJET Journal
 

Similar to Blind Source Camera Identification (20)

Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...
Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...
Automatic License Plate Detection in Foggy Condition using Enhanced OTSU Tech...
 
IRJET- 3D Vision System using Calibrated Stereo Camera
IRJET- 3D Vision System using Calibrated Stereo CameraIRJET- 3D Vision System using Calibrated Stereo Camera
IRJET- 3D Vision System using Calibrated Stereo Camera
 
Information search using text and image query
Information search using text and image queryInformation search using text and image query
Information search using text and image query
 
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by MadhuAN INTEGRATED APPROACH TO CONTENT BASED IMAGERETRIEVAL by Madhu
AN INTEGRATED APPROACH TO CONTENT BASED IMAGE RETRIEVAL by Madhu
 
Information search using text and image query
Information search using text and image queryInformation search using text and image query
Information search using text and image query
 
Paper id 21201419
Paper id 21201419Paper id 21201419
Paper id 21201419
 
Performance of Efficient Closed-Form Solution to Comprehensive Frontier Exposure
Performance of Efficient Closed-Form Solution to Comprehensive Frontier ExposurePerformance of Efficient Closed-Form Solution to Comprehensive Frontier Exposure
Performance of Efficient Closed-Form Solution to Comprehensive Frontier Exposure
 
I010634450
I010634450I010634450
I010634450
 
Image processing
Image processingImage processing
Image processing
 
IRJET- Crowd Density Estimation using Image Processing
IRJET- Crowd Density Estimation using Image ProcessingIRJET- Crowd Density Estimation using Image Processing
IRJET- Crowd Density Estimation using Image Processing
 
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...
 
Presentation shortstory
Presentation shortstoryPresentation shortstory
Presentation shortstory
 
Himadeep
HimadeepHimadeep
Himadeep
 
Cahall Final Intern Presentation
Cahall Final Intern PresentationCahall Final Intern Presentation
Cahall Final Intern Presentation
 
A Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVMA Review of Feature Extraction Techniques for CBIR based on SVM
A Review of Feature Extraction Techniques for CBIR based on SVM
 
Image processing sw & hw
Image processing sw & hwImage processing sw & hw
Image processing sw & hw
 
Image segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
Image segmentation using wvlt trnsfrmtn and fuzzy logic. pptImage segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
Image segmentation using wvlt trnsfrmtn and fuzzy logic. ppt
 
An Introduction to digital image processing
An Introduction to digital image processingAn Introduction to digital image processing
An Introduction to digital image processing
 
Blur Detection Methods for Digital Images-A Survey
Blur Detection Methods for Digital Images-A SurveyBlur Detection Methods for Digital Images-A Survey
Blur Detection Methods for Digital Images-A Survey
 
IRJET- Low Light Image Enhancement using Convolutional Neural Network
IRJET-  	  Low Light Image Enhancement using Convolutional Neural NetworkIRJET-  	  Low Light Image Enhancement using Convolutional Neural Network
IRJET- Low Light Image Enhancement using Convolutional Neural Network
 

Recently uploaded

Heart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxHeart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxPoojaBan
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...Soham Mondal
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AIabhishek36461
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...ranjana rawat
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024Mark Billinghurst
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx959SahilShah
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionDr.Costas Sachpazis
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )Tsuyoshi Horigome
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidNikhilNagaraju
 
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝soniya singh
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSCAESB
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxwendy cai
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
power system scada applications and uses
power system scada applications and usespower system scada applications and uses
power system scada applications and usesDevarapalliHaritha
 
microprocessor 8085 and its interfacing
microprocessor 8085  and its interfacingmicroprocessor 8085  and its interfacing
microprocessor 8085 and its interfacingjaychoudhary37
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort servicejennyeacort
 

Recently uploaded (20)

Heart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptxHeart Disease Prediction using machine learning.pptx
Heart Disease Prediction using machine learning.pptx
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
 
Past, Present and Future of Generative AI
Past, Present and Future of Generative AIPast, Present and Future of Generative AI
Past, Present and Future of Generative AI
 
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
(ANVI) Koregaon Park Call Girls Just Call 7001035870 [ Cash on Delivery ] Pun...
 
IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024IVE Industry Focused Event - Defence Sector 2024
IVE Industry Focused Event - Defence Sector 2024
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx
 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
 
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
VICTOR MAESTRE RAMIREZ - Planetary Defender on NASA's Double Asteroid Redirec...
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfid
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
Model Call Girl in Narela Delhi reach out to us at 🔝8264348440🔝
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentation
 
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
What are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptxWhat are the advantages and disadvantages of membrane structures.pptx
What are the advantages and disadvantages of membrane structures.pptx
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
power system scada applications and uses
power system scada applications and usespower system scada applications and uses
power system scada applications and uses
 
microprocessor 8085 and its interfacing
microprocessor 8085  and its interfacingmicroprocessor 8085  and its interfacing
microprocessor 8085 and its interfacing
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
 

Blind Source Camera Identification

  • 1. Blind Source Camera Identification
  • 2. Introduction In today’s digital age, the creation and manipulation of digital images is made simple by digital processing tools that are easily and widely available. As a consequence, we can no longer take the authenticity of images, analog or digital, for granted. This is especially true when it comes to legal photographic evidence
  • 3. Introduction Although digital watermarks have been proposed as a tool to provide authenticity to images, it is a fact that the overwhelming majority of images that are captured today do not contain a digital watermark. And this situation is likely to continue for the foreseeable future.
  • 4. Problem Statement There are images from unknown source with no or untraceable watermark, but it is known to originate from either one of limited given standard cameras , say x, y, z. It is needed to classify the images into the groups based on originality. So the problem simplifies to whether a particular image came was originated from camera x, camera y or camera z.
  • 5. Related Works  A number of features of images have been identified that can prove to be a crucial part in classification .  Classification of the images have been a matter of study for past few years and it has been done with maximum achieved average accuracy of 93.42 % for set of two cameras, namely Nikon and Sony.  Classification of images among 5 different cameras has been conducted with an average accuracy of 88.02 %.  It is found out that a full generality of classification i.e. classification among a set of unknown number of devices , is difficult on a higher level.
  • 6. Goals and Objectives  Identifying features that can be used in classification.  Develop a classifier function that classifies images into two groups based on originality.
  • 7. Methodology  34 features have been identified till now that are and can be used in classification.  The features are mentioned in the following slides :-
  • 8. AVERAGE PIXEL VALUE This measure is based on the gray world assumption, which states that the average values in RGB channels of an image should average to gray, assuming that the images has enough color variations. Thus the features are the mean value of the 3 RGB channels (3 features). RGB PAIRS CORRELATION This measure attempts to capture the fact that depending on the camera structure, the correlation between different color bands could vary. There are 3 correlation pairs, namely RG, RB (3 features).
  • 9. NEIGHBOR DISTRIBUTION CENTER OF MASS This measure is calculated for each color band separately by first calculating the number of pixel neighbors for each pixel value, where a pixels neighbor are defined as all pixels which have a difference of value of 1 or -1, from the pixel value in question. RGB pairs energy ratio It is important because it is used in the process of white point correction which is an integral part of a camera pipeline. The calculated features (3 features) are: E1 = |G|2 /|B|2 E2 = |G|2 /|R|2 E3 = |B|2 /|R|2
  • 10. WAVELET DOMAIN STATISTICS Decomposed each color band of the image using separable quadratic mirror filters and then calculated the mean for each of the 3 resulting sub-bands (9 features). IMAGE QUALITY METRICS (IQM) We can categorize the set of IQM used into 3 classes :- • The pixel difference based measures (i.e. mean square error, mean absolute error, modified infinity norm) • The correlation based measures (i.e. normalized cross correlation, Czekonowski correlation) • The spectral distance based measures (i.e. spectral phase and magnitude errors) This is a set of 13 features.
  • 11. Classifier • We are going to use Support Vector Machine(SVM) Classifier. • It is primarily a classier method that performs classification tasks by constructing hyper planes in a multidimensional space. • To construct an optimal hyper plane, SVM employs an iterative training algorithm, which is used to minimize an error function.
  • 12. Linear Classifier • It classifies data set by linear hyper plane.
  • 13. The image below is the output from the simulation of linear classification using octave.
  • 14. Gaussian Kernel Classifier • It is non linear SVM kernel • Also known as Radial basis function (RBF) kernel
  • 15. The image beside is the output from the simulation of Gaussian classification using octave.
  • 16. SVM Classifier can classify data in at most two groups at a time. So how we can classify data into more than 2 groups ?
  • 17. We can do that by training 3 classifiers , for each group vs all other groups Group1 vs All
  • 20. Conclusion The technique studied in the research project will aide in improvement in performance and accuracy of blind source camera identification.
  • 21. Reference [1] Mehdi Kharrazi , Husrev T. Sencar and Nasir Memon , ”Blind Source Camera Identification”. [2] C.-C. Chang and C.-J. Lin, LIBSVM: a library for support vector machines, 2001, software available at http://www.csie.ntu.edu.tw/˜cjlin/libsvm. [3] Andrew Ng, ”Machine Learning CS-229 Standford” http://cs229.standford.edu