SlideShare a Scribd company logo
TagSense: Leveraging Smartphones
For Automatic Image Tagging
PRESENTED BY: VIJAY MALI
GUIDED BY:
PROF. P. D. GANJEWAR
Overview::-
 Motivation
 Introduction
 Scope Of TagSense
 System Architecture
 Design And Methodology
 Performance Evaluation
 Flowchart
 Limitations of TagSense
 Conclusion
Motivation::-
 Human Tagging: Time Consuming And Boring
 Advantages over facial recognition
 Could save humans from the task of manually tagging photos
 Could be paired with facial recognition to make a robust
solution
 Today’s smartphones have powerful built-in sensors People
always carry their phones.
Introduction::-
 It is a mobile phone–based collaborative system that
senses the people, activity and context in a picture and
merges them to create tags .
 These tags are organized into a “When-Where-Who-What”
format, ultimately creating an automatic description for
picture
Scope Of TagSense::-
 Picture 1: November 21, NasherMuseum, indoor, Romit, Sushma, Naveen,
Souvik, Justin, Xuan, standing, talking.
 Picture 2: December 4, hdsonhall, outdoor, Xuan, standing, snowing.
System Architecture::-
Design And Methodology::-
 When is the picture taken?
Time and date
Time of day (afternoon, evening, night …)
Weather
 Where is the picture taken?
GPS ‐ Reverse lookup
Light sensor (indoor/outdoor)
 What are they doing?
Accelerometer
Acoustic
Vocabulary of activities recognized by phone sensors
(standing, walking, talking …)
Design And Methodology::-
Who Is In The Picture?
Possible Opportunities::-
1. Accelerometer based motion signatures
2. Complementary compass directions
3. Correlating visual and acceleration
1. Accelerometer Based Motion
Signature
 When subject pose for a picture, phones
exhibit a motion signature .
 TagSense find such a signature around the
time of picture click.
2. Complementary Compass
Direction
 The posing signature will be absent in some cases.
 In such cases the direction of their compasses will be
roughly complementary to the camera’s facing
direction.
3. Correlating Visual And
Acceleration
(a) First snap shot (b) Second snap shot
(c)Optical flow of each pixel
3. Correlating Visual And
Acceleration
 Taking several snapshots after shutter click
 Motion vector can be obtained by optical flow from adjacent
snapshots
 Correlate with accelerometer readings to find who
(d) Motion vectors for two
objects
(c)Optical flow of each pixel
Flowchart And Algorithms::-
 Flowchart:
Comparison With iPhoto And
Picasa
Limitations of Tagsense::-
 TagSense vocabulary of tags is quite limited.
 It does not generate effective sentenced captions.
 TagSense methods for tagging people are complex.
 TagSense cannot tag kids as they are not likely to
have phones.
Conclusion::-
 Mobile phones are becoming inseparable from
humans and are replacing traditional cameras.
 TagSense leverages this trend to automatically tag
pictures with people and their activities
 TagSense has somewhat lower precision and
comparable fall-out but significantly higher recall
than iPhoto/Picasa.
References::-
 Chuan Qin, Xuan Bao, Romit Roy Choudhury and
Nelakuditi,” TagSense: leveraging smartphones for
automatic image tagging”, IEEE Transcation on mobile
computing, vol 13, No 1, January 2014.
 (Part1) TagSense A Smartphone‐based Approach to
Automatic Image Tagging – YouTube, Chuan Qin
 (Part2) TagSense A Smartphone‐based Approach to
Automatic Image Tagging – YouTube, Chuan Qin
Thank You…!!
ANY QUESTIONS ?

More Related Content

Viewers also liked

Solar Ordinance Feasibility Study
Solar Ordinance Feasibility StudySolar Ordinance Feasibility Study
Solar Ordinance Feasibility Study
Darya Oreizi
 
Nicolas bocanegra trabajo 1
Nicolas bocanegra trabajo 1Nicolas bocanegra trabajo 1
Nicolas bocanegra trabajo 1
Paola P
 
ชื่อ นาย รชต โชคชัย
ชื่อ นาย รชต โชคชัย ชื่อ นาย รชต โชคชัย
ชื่อ นาย รชต โชคชัย
Aomzin Chokchai
 
Global & usa cancer immunotherapy market analysis to 2020
Global & usa cancer immunotherapy market analysis to 2020Global & usa cancer immunotherapy market analysis to 2020
Global & usa cancer immunotherapy market analysis to 2020
Research Hub
 
โครงงานคอม
โครงงานคอมโครงงานคอม
โครงงานคอมSon ClubHot
 
Global transdermal drug delivery market to 2017
Global transdermal drug delivery market to 2017Global transdermal drug delivery market to 2017
Global transdermal drug delivery market to 2017
Research Hub
 
презентация1
презентация1презентация1
презентация1
Інна Мартовіцька
 
The Evolving Culture-scape and Employee Expectation
The Evolving Culture-scape and Employee ExpectationThe Evolving Culture-scape and Employee Expectation
The Evolving Culture-scape and Employee Expectation
JWTINSIDE
 
Social Media ROI - Social Media Rockstar 3
Social Media ROI - Social Media Rockstar 3Social Media ROI - Social Media Rockstar 3
Social Media ROI - Social Media Rockstar 3
kiar media
 
Evalution 2
Evalution 2Evalution 2
Evalution 2
Frankie Christou
 
America - fotografii de epocă
America - fotografii de epocăAmerica - fotografii de epocă
America - fotografii de epocăFrumoasa Verde
 
Operating caregiving equipment, tools and paraphernalia
Operating caregiving equipment, tools and paraphernaliaOperating caregiving equipment, tools and paraphernalia
Operating caregiving equipment, tools and paraphernalia
Angie Filler
 
Social Media Trends & Innovations
Social Media Trends & InnovationsSocial Media Trends & Innovations
Social Media Trends & Innovations
Carmelon Digital Marketing
 

Viewers also liked (13)

Solar Ordinance Feasibility Study
Solar Ordinance Feasibility StudySolar Ordinance Feasibility Study
Solar Ordinance Feasibility Study
 
Nicolas bocanegra trabajo 1
Nicolas bocanegra trabajo 1Nicolas bocanegra trabajo 1
Nicolas bocanegra trabajo 1
 
ชื่อ นาย รชต โชคชัย
ชื่อ นาย รชต โชคชัย ชื่อ นาย รชต โชคชัย
ชื่อ นาย รชต โชคชัย
 
Global & usa cancer immunotherapy market analysis to 2020
Global & usa cancer immunotherapy market analysis to 2020Global & usa cancer immunotherapy market analysis to 2020
Global & usa cancer immunotherapy market analysis to 2020
 
โครงงานคอม
โครงงานคอมโครงงานคอม
โครงงานคอม
 
Global transdermal drug delivery market to 2017
Global transdermal drug delivery market to 2017Global transdermal drug delivery market to 2017
Global transdermal drug delivery market to 2017
 
презентация1
презентация1презентация1
презентация1
 
The Evolving Culture-scape and Employee Expectation
The Evolving Culture-scape and Employee ExpectationThe Evolving Culture-scape and Employee Expectation
The Evolving Culture-scape and Employee Expectation
 
Social Media ROI - Social Media Rockstar 3
Social Media ROI - Social Media Rockstar 3Social Media ROI - Social Media Rockstar 3
Social Media ROI - Social Media Rockstar 3
 
Evalution 2
Evalution 2Evalution 2
Evalution 2
 
America - fotografii de epocă
America - fotografii de epocăAmerica - fotografii de epocă
America - fotografii de epocă
 
Operating caregiving equipment, tools and paraphernalia
Operating caregiving equipment, tools and paraphernaliaOperating caregiving equipment, tools and paraphernalia
Operating caregiving equipment, tools and paraphernalia
 
Social Media Trends & Innovations
Social Media Trends & InnovationsSocial Media Trends & Innovations
Social Media Trends & Innovations
 

Similar to TagSense: Leveraging Smartphones For Automatic Image Tagging

Tagsense ppt
Tagsense pptTagsense ppt
Tagsense ppt
ushanagaraj
 
Computer Based Human Gesture Recognition With Study Of Algorithms
Computer Based Human Gesture Recognition With Study Of AlgorithmsComputer Based Human Gesture Recognition With Study Of Algorithms
Computer Based Human Gesture Recognition With Study Of Algorithms
IOSR Journals
 
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptxDeep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
pmgdscunsri
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
Kavika Roy
 
01Introduction.pptx - C280, Computer Vision
01Introduction.pptx - C280, Computer Vision01Introduction.pptx - C280, Computer Vision
01Introduction.pptx - C280, Computer Vision
butest
 
Motion capture document
Motion capture documentMotion capture document
Motion capture document
harini501
 
IRJET- Advance Driver Assistance System using Artificial Intelligence
IRJET- Advance Driver Assistance System using Artificial IntelligenceIRJET- Advance Driver Assistance System using Artificial Intelligence
IRJET- Advance Driver Assistance System using Artificial Intelligence
IRJET Journal
 
Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network
ijcga
 
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
IRJET Journal
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor network
ijcga
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition system
Divya Sushma
 
Gesturerecognition
GesturerecognitionGesturerecognition
Gesturerecognition
Mariya Khan
 
Mining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart PhoneMining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart Phone
IIRindia
 
Mining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart PhoneMining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart Phone
IIRindia
 
Image retrieval and re ranking techniques - a survey
Image retrieval and re ranking techniques - a surveyImage retrieval and re ranking techniques - a survey
Image retrieval and re ranking techniques - a survey
sipij
 
What is Computer Vision?
What is Computer Vision?What is Computer Vision?
What is Computer Vision?
Kavika Roy
 
Image recognition
Image recognitionImage recognition
Image recognition
Harika Nalla
 
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
Editor IJMTER
 
imagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdfimagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdf
SUBHASHREESUDHANSUSE
 
Human Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLABHuman Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLAB
NIET Journal of Engineering & Technology (NIETJET)
 

Similar to TagSense: Leveraging Smartphones For Automatic Image Tagging (20)

Tagsense ppt
Tagsense pptTagsense ppt
Tagsense ppt
 
Computer Based Human Gesture Recognition With Study Of Algorithms
Computer Based Human Gesture Recognition With Study Of AlgorithmsComputer Based Human Gesture Recognition With Study Of Algorithms
Computer Based Human Gesture Recognition With Study Of Algorithms
 
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptxDeep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
Deep Learning For Computer Vision- Day 3 Study Jams GDSC Unsri.pptx
 
Everything You Need to Know About Computer Vision
Everything You Need to Know About Computer VisionEverything You Need to Know About Computer Vision
Everything You Need to Know About Computer Vision
 
01Introduction.pptx - C280, Computer Vision
01Introduction.pptx - C280, Computer Vision01Introduction.pptx - C280, Computer Vision
01Introduction.pptx - C280, Computer Vision
 
Motion capture document
Motion capture documentMotion capture document
Motion capture document
 
IRJET- Advance Driver Assistance System using Artificial Intelligence
IRJET- Advance Driver Assistance System using Artificial IntelligenceIRJET- Advance Driver Assistance System using Artificial Intelligence
IRJET- Advance Driver Assistance System using Artificial Intelligence
 
Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network
 
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
IRJET- Comparative Study of Different Techniques for Text as Well as Object D...
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor network
 
Facial recognition system
Facial recognition systemFacial recognition system
Facial recognition system
 
Gesturerecognition
GesturerecognitionGesturerecognition
Gesturerecognition
 
Mining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart PhoneMining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart Phone
 
Mining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart PhoneMining and Clustering the Feature Similarities of Images on Smart Phone
Mining and Clustering the Feature Similarities of Images on Smart Phone
 
Image retrieval and re ranking techniques - a survey
Image retrieval and re ranking techniques - a surveyImage retrieval and re ranking techniques - a survey
Image retrieval and re ranking techniques - a survey
 
What is Computer Vision?
What is Computer Vision?What is Computer Vision?
What is Computer Vision?
 
Image recognition
Image recognitionImage recognition
Image recognition
 
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
FACE EXPRESSION IDENTIFICATION USING IMAGE FEATURE CLUSTRING AND QUERY SCHEME...
 
imagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdfimagerecognition-191220044946 (1).pdf
imagerecognition-191220044946 (1).pdf
 
Human Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLABHuman Face Detection And Identification Of Facial Expressions Using MATLAB
Human Face Detection And Identification Of Facial Expressions Using MATLAB
 

Recently uploaded

学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
171ticu
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
co23btech11018
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
IJECEIAES
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
TaghreedAltamimi
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
171ticu
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
gowrishankartb2005
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
VANDANAMOHANGOUDA
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
bijceesjournal
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
SakkaravarthiShanmug
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
KrishnaveniKrishnara1
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
Madan Karki
 
integral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdfintegral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdf
gaafergoudaay7aga
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
IJECEIAES
 
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURSCompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
RamonNovais6
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
AjmalKhan50578
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
Hitesh Mohapatra
 
Applications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdfApplications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdf
Atif Razi
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
UReason
 

Recently uploaded (20)

学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样学校原版美国波士顿大学毕业证学历学位证书原版一模一样
学校原版美国波士顿大学毕业证学历学位证书原版一模一样
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
 
Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...Advanced control scheme of doubly fed induction generator for wind turbine us...
Advanced control scheme of doubly fed induction generator for wind turbine us...
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
Software Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.pptSoftware Quality Assurance-se412-v11.ppt
Software Quality Assurance-se412-v11.ppt
 
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样官方认证美国密歇根州立大学毕业证学位证书原版一模一样
官方认证美国密歇根州立大学毕业证学位证书原版一模一样
 
Material for memory and display system h
Material for memory and display system hMaterial for memory and display system h
Material for memory and display system h
 
ITSM Integration with MuleSoft.pptx
ITSM  Integration with MuleSoft.pptxITSM  Integration with MuleSoft.pptx
ITSM Integration with MuleSoft.pptx
 
Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...Comparative analysis between traditional aquaponics and reconstructed aquapon...
Comparative analysis between traditional aquaponics and reconstructed aquapon...
 
cnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classicationcnn.pptx Convolutional neural network used for image classication
cnn.pptx Convolutional neural network used for image classication
 
22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt22CYT12-Unit-V-E Waste and its Management.ppt
22CYT12-Unit-V-E Waste and its Management.ppt
 
spirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptxspirit beverages ppt without graphics.pptx
spirit beverages ppt without graphics.pptx
 
integral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdfintegral complex analysis chapter 06 .pdf
integral complex analysis chapter 06 .pdf
 
Embedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoringEmbedded machine learning-based road conditions and driving behavior monitoring
Embedded machine learning-based road conditions and driving behavior monitoring
 
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURSCompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
 
Generative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of contentGenerative AI leverages algorithms to create various forms of content
Generative AI leverages algorithms to create various forms of content
 
Applications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdfApplications of artificial Intelligence in Mechanical Engineering.pdf
Applications of artificial Intelligence in Mechanical Engineering.pdf
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
 

TagSense: Leveraging Smartphones For Automatic Image Tagging

  • 1. TagSense: Leveraging Smartphones For Automatic Image Tagging PRESENTED BY: VIJAY MALI GUIDED BY: PROF. P. D. GANJEWAR
  • 2. Overview::-  Motivation  Introduction  Scope Of TagSense  System Architecture  Design And Methodology  Performance Evaluation  Flowchart  Limitations of TagSense  Conclusion
  • 3. Motivation::-  Human Tagging: Time Consuming And Boring  Advantages over facial recognition  Could save humans from the task of manually tagging photos  Could be paired with facial recognition to make a robust solution  Today’s smartphones have powerful built-in sensors People always carry their phones.
  • 4. Introduction::-  It is a mobile phone–based collaborative system that senses the people, activity and context in a picture and merges them to create tags .  These tags are organized into a “When-Where-Who-What” format, ultimately creating an automatic description for picture
  • 5. Scope Of TagSense::-  Picture 1: November 21, NasherMuseum, indoor, Romit, Sushma, Naveen, Souvik, Justin, Xuan, standing, talking.  Picture 2: December 4, hdsonhall, outdoor, Xuan, standing, snowing.
  • 7. Design And Methodology::-  When is the picture taken? Time and date Time of day (afternoon, evening, night …) Weather  Where is the picture taken? GPS ‐ Reverse lookup Light sensor (indoor/outdoor)  What are they doing? Accelerometer Acoustic Vocabulary of activities recognized by phone sensors (standing, walking, talking …)
  • 9. Who Is In The Picture? Possible Opportunities::- 1. Accelerometer based motion signatures 2. Complementary compass directions 3. Correlating visual and acceleration
  • 10. 1. Accelerometer Based Motion Signature  When subject pose for a picture, phones exhibit a motion signature .  TagSense find such a signature around the time of picture click.
  • 11. 2. Complementary Compass Direction  The posing signature will be absent in some cases.  In such cases the direction of their compasses will be roughly complementary to the camera’s facing direction.
  • 12. 3. Correlating Visual And Acceleration (a) First snap shot (b) Second snap shot (c)Optical flow of each pixel
  • 13. 3. Correlating Visual And Acceleration  Taking several snapshots after shutter click  Motion vector can be obtained by optical flow from adjacent snapshots  Correlate with accelerometer readings to find who (d) Motion vectors for two objects (c)Optical flow of each pixel
  • 16. Limitations of Tagsense::-  TagSense vocabulary of tags is quite limited.  It does not generate effective sentenced captions.  TagSense methods for tagging people are complex.  TagSense cannot tag kids as they are not likely to have phones.
  • 17. Conclusion::-  Mobile phones are becoming inseparable from humans and are replacing traditional cameras.  TagSense leverages this trend to automatically tag pictures with people and their activities  TagSense has somewhat lower precision and comparable fall-out but significantly higher recall than iPhoto/Picasa.
  • 18. References::-  Chuan Qin, Xuan Bao, Romit Roy Choudhury and Nelakuditi,” TagSense: leveraging smartphones for automatic image tagging”, IEEE Transcation on mobile computing, vol 13, No 1, January 2014.  (Part1) TagSense A Smartphone‐based Approach to Automatic Image Tagging – YouTube, Chuan Qin  (Part2) TagSense A Smartphone‐based Approach to Automatic Image Tagging – YouTube, Chuan Qin