SlideShare a Scribd company logo
1 of 38
Interaction Lab. Kumoh National Institute of Technology
TabletGaze : Unconstrained Appearance-based
Gaze Estimation in Mobile Tablets
:Computer Vision and Pattern Recognition 2016
Jeong JaeYeop
■Intro
■Rice TabletGaze dataset
■TabletGaze algorithms
■Results and analysis
■Discussion and conclusion
Agenda
Interaction Lab., Kumoh National Institue of Technology 2
Intro
Rice TabletGaze dataset
TabletGaze algorithms
Data Engineering Lab., Kumoh National Institue of Technology 3
■Gaze estimation in Mobile Tablets
 Commonplace connected mobile computing device
 User-tablet interaction
• Touch and sound
• Gaze is an emerging proxy of the user’s attention and intention
■ Hands-free human device interaction
■ Behavior studies
■ User authentication
Intro(1/4)
Interaction Lab., Kumoh National Institue of Technology 4
■Gaze estimation in Mobile Tablets
 Gaze estimation of tablets
• Without requiring any additional hardware
• Front-facing cameras
• Appearance-based methods
■ Not calibration stage
■ Mapping from appearance of eye region to gaze direction
Intro(2/4)
Interaction Lab., Kumoh National Institue of Technology 5
■A key challenge in tablet gaze estimation
 No constraint on
• How people use the tablet
• What kind of body posture people have when using tablet
• The user of the tablet
Intro(3/4)
Interaction Lab., Kumoh National Institue of Technology 6
■Tablet gaze estimation problem in three steps
 Collect dataset an unconstrained mobile gaze dataset of tablet
• 51 subjects
• Rice TabletGaze dataset
 TabletGaze Algorithms
• Feature extraction
• Dimensionality reduction
• Regression
 Analysis
Intro(4/4)
Interaction Lab., Kumoh National Institue of Technology 7
Rice TabletGaze dataset
TabletGaze algorithms
Results and analysis
Data Engineering Lab., Kumoh National Institue of Technology 8
■Rice TabletGaze dataset
 Unique, unconstrained characteristics in the mobile environment
• 51 subjects, each with 4 different body postures
• Released online
 The learned model can be used for other devices
• Transfer learning, domain adaptation
Rice TabletGaze dataset(1/10)
■Data collection
 Setup
• Samsung Galaxy Tab S 10.5
■ Screen size of 22.62 x 14.14 com (8.90 x 5.57 inches)
■ 35 gaze locations (points)
■ The raw data(videos) captured by the front-camera
■ Resolution – 1280 x 720
• 51 subjects
■ 12 female and 39 male
■ 26 of them wearing prescription glasses
■ 28 of the subjects are Caucasians, and the remaining 23 are Asians
■ The ages of subjects range from 20 to 40
Rice TabletGaze dataset(2/10)
Interaction Lab., Kumoh National Institue of Technology 10
■Data collection
 Four body postures
• Standing
• Sitting
• Slouching
• Lying
 Four recording session and four body posture
• 16 video sequences
• No restriction on
■ How the subject held the tablet
■ How they performed each body posture
 Natural lit office environment
Rice TabletGaze dataset(3/10)
Interaction Lab., Kumoh National Institue of Technology 11
■Data collection
 One data collection session
• Front-facing camera of the tablet begin recording a video
• Beep sound notified the beginning of the video
• Dot changing its location every three seconds and focus
■ Dot Randomize among 35 possible points
■ Free to blink
Rice TabletGaze dataset(4/10)
Interaction Lab., Kumoh National Institue of Technology 12
■Observations on the Rice TabletGaze dataset
 The entire face may not be visible in most of the image frames
• To quantify the extent of facial visibility, label each video in the dataset
■ The whole face
■ From mouth and above
■ From nose and above
■ From eyes and above
■ Even the eyes are no visible
• Manually reviewed 4 images
Rice TabletGaze dataset(5/10)
Interaction Lab., Kumoh National Institue of Technology 13
■Observations on the Rice TabletGaze dataset
 Body posture and facial visibility extent appear to be correlated
Rice TabletGaze dataset(6/10)
Interaction Lab., Kumoh National Institue of Technology 14
■Observations on the Rice TabletGaze dataset
 Glasses can cause reflection, and in many instances, the reflection
can be significant
Rice TabletGaze dataset(7/10)
Interaction Lab., Kumoh National Institue of Technology 15
■Sub-dataset Labeling
 The total amount of raw data
• 51 x 16 = 816 video sequences
• A portion of the data is not usable
■ Loss of concentration of subjects
■ Eye detector failure
■ Involuntary eye blinks and large motion blur
 Sub-dataset of 41 subjects to be used in experiments
Rice TabletGaze dataset(8/10)
Interaction Lab., Kumoh National Institue of Technology 16
■Sub-dataset Labeling
 Loss of concentration of subjects
• Refocus time
• Extract after 1.5 to 2.5 seconds when dot appears at a new location
• For the 35 videos chunk from extracted from each video
■ Inspect gaze drift more than 5 video chunk, if so, abandon the data
• Hard to determine the true gaze location
Rice TabletGaze dataset(9/10)
Interaction Lab., Kumoh National Institue of Technology 17
■Sub-dataset Labeling
 Eye detector failures
• Eyes are not visible in the image frame
• Strong reflection from glasses
• Occlusion from hair
• Poor illumination
 Use LoG(Laplacian of Gaussian) value
• Images of closed eyes
■ Higher mean intensity value given the disappearance of the dark pupil
• Blurred eye region image
■ Lower mean intensity value because motion blur weakens the edge information
Rice TabletGaze dataset(10/10)
Interaction Lab., Kumoh National Institue of Technology 18
TabletGaze algorithms
Results and analysis
Discussion and conclusion
Data Engineering Lab., Kumoh National Institue of Technology 19
■Overview
TabletGaze algorithms(1/6)
■Preprocessing
 Eye detector
• Two Harr feature CART-tree based cascade detectors
• False positive bounding boxes
■ Establish threshold for the size of the box (nostril)
■ Symmetric locations of the boxes (mouth)
• 100 x 15 resize
TabletGaze algorithms(2/6)
Interaction Lab., Kumoh National Institue of Technology 21
■Feature Calculation
 Feature extraction
• Contrast normalized pixel intensities
• LoG (Laplacian of Gaussian)
• LBP (Local Binary Pattern)
• HoG (Histogram of Oriented Gradients)
• mHoG (multilevel HoG)
■ Concatenate HoG features at different scales
TabletGaze algorithms(3/6)
Interaction Lab., Kumoh National Institue of Technology 22
■Feature Calculation
 Dimensionality reduction
• Feature is High dimensional and compromised by noise
• Mapping the features to a lower dimensional space
• CNN pooling
• LDA (Linear Discriminant Analysis)
• PCA (Principal Component Analysis)
TabletGaze algorithms(4/6)
Interaction Lab., Kumoh National Institue of Technology 23
■Feature Calculation
 LDA (Linear Discriminant Analysis)
• Intra-class scatter is maximized
• Inter-class scatter is minimized
 PCA(Principal Component Analysis)
TabletGaze algorithms(5/6)
Interaction Lab., Kumoh National Institue of Technology 24
■Regression
 The gaze labels of the data include two parts
• Horizontal and vertical coordinates on the tablet screen (x, y)
 Methods
• k-NN (k-Nearest Neighbors)
• RF (Random Forest)
■ Set of weak binary tree regressors
■ 100 trees
• GPR (Gaussian Process Regression)
• SVR (Support Vector Regression)
TabletGaze algorithms(6/6)
Interaction Lab., Kumoh National Institue of Technology 25
Results and analysis
Discussion and conclusion
Data Engineering Lab., Kumoh National Institue of Technology 26
■Error Metrics
 Previous works
• Angular error
■ Arctangent of the ratio between the distance from the subject’s eyes to screen
 This work
• Mean Error (ME)
■ 2D location on the tablet
Results and analysis(1/8)
■Comparisons for different features + regressors
 Use 100,000 images from 41 subjects using cross validation
• GPR, SVR are only used 15 subject data
Results and analysis(2/8)
Interaction Lab., Kumoh National Institue of Technology 28
■ Person-dependent and person-independent performance comparison
 in prior works appearance-based gaze estimation methods
• Person and session dependent
Results and analysis(3/8)
Interaction Lab., Kumoh National Institue of Technology 29
■Comparison with prior results
Results and analysis(4/8)
Interaction Lab., Kumoh National Institue of Technology 30
■Effect of training data size
 Groups of different sizes 𝐾
• 𝐾 : 2 ~ 41
 Use 𝐾 − 1 for training, one is test
 Randomly selecting a subset of data
 Repeat the same process 5 times and average
Results and analysis(5/8)
Interaction Lab., Kumoh National Institue of Technology 31
■Eyeglasses, race and posture
 Three experiments setups
• Experiment 1
■ The dataset was partitioned into 2 groups of wearing glasses and not
■ Training and testing are done separately for each group
• Experiment 2
■ Leave-one-subject-out cross validation for all data
■ ME is separated for each group
• Experiment 3
■ Combine data of half each group
Results and analysis(6/8)
Interaction Lab., Kumoh National Institue of Technology 32
■Eyeglasses, race and posture
Results and analysis(7/8)
Interaction Lab., Kumoh National Institue of Technology 33
■Continuous gaze tracking from videos
 Use temporal information
• Bilateral filter
Results and analysis(8/8)
Interaction Lab., Kumoh National Institue of Technology 34
Discussion and conclusion
Data Engineering Lab., Kumoh National Institue of Technology 35
■Discussion
 All of the evaluations of the algorithms are conducted on a desktop
 Pre-trained off-line and loaded onto the device
 RF + mHoG feature
• Real time gaze estimation
Discussion and conclusion(1/2)
■Conclusion
 Unconstrained mobile gaze estimation problem
• A large dataset is collected in an unconstrained environment
■ First dataset
■ Four different postures
• ME : 3.17±2.10 cm
Discussion and conclusion(2/2)
Interaction Lab., Kumoh National Institue of Technology 37
Q&A
Data Engineering Lab., Kumoh National Institue of Technology 38

More Related Content

What's hot

Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review경훈 김
 
deep learning from scratch chapter 6.backpropagation
deep learning from scratch chapter 6.backpropagationdeep learning from scratch chapter 6.backpropagation
deep learning from scratch chapter 6.backpropagationJaey Jeong
 
Deep learning based gaze detection system for automobile drivers using nir ca...
Deep learning based gaze detection system for automobile drivers using nir ca...Deep learning based gaze detection system for automobile drivers using nir ca...
Deep learning based gaze detection system for automobile drivers using nir ca...Jaey Jeong
 
Object Tracking By Online Discriminative Feature Selection Algorithm
Object Tracking By Online Discriminative Feature Selection AlgorithmObject Tracking By Online Discriminative Feature Selection Algorithm
Object Tracking By Online Discriminative Feature Selection AlgorithmIRJET Journal
 
nnU-Net: a self-configuring method for deep learning-based biomedical image s...
nnU-Net: a self-configuring method for deep learning-based biomedical image s...nnU-Net: a self-configuring method for deep learning-based biomedical image s...
nnU-Net: a self-configuring method for deep learning-based biomedical image s...ivaderivader
 
Testing Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveTesting Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveLionel Briand
 
Can we predict the quality of spectrum-based fault localization?
Can we predict the quality of spectrum-based fault localization?Can we predict the quality of spectrum-based fault localization?
Can we predict the quality of spectrum-based fault localization?Lionel Briand
 
Keynote SBST 2014 - Search-Based Testing
Keynote SBST 2014 - Search-Based TestingKeynote SBST 2014 - Search-Based Testing
Keynote SBST 2014 - Search-Based TestingLionel Briand
 
Enabling Automated Software Testing with Artificial Intelligence
Enabling Automated Software Testing with Artificial IntelligenceEnabling Automated Software Testing with Artificial Intelligence
Enabling Automated Software Testing with Artificial IntelligenceLionel Briand
 
A comparison of SIFT, PCA-SIFT and SURF
A comparison of SIFT, PCA-SIFT and SURFA comparison of SIFT, PCA-SIFT and SURF
A comparison of SIFT, PCA-SIFT and SURFCSCJournals
 
Scalable and Cost-Effective Model-Based Software Verification and Testing
Scalable and Cost-Effective Model-Based Software Verification and TestingScalable and Cost-Effective Model-Based Software Verification and Testing
Scalable and Cost-Effective Model-Based Software Verification and TestingLionel Briand
 
Practical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataPractical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataLionel Briand
 
A practical guide for using Statistical Tests to assess Randomized Algorithms...
A practical guide for using Statistical Tests to assess Randomized Algorithms...A practical guide for using Statistical Tests to assess Randomized Algorithms...
A practical guide for using Statistical Tests to assess Randomized Algorithms...Lionel Briand
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Lionel Briand
 
AI in SE: A 25-year Journey
AI in SE: A 25-year JourneyAI in SE: A 25-year Journey
AI in SE: A 25-year JourneyLionel Briand
 

What's hot (18)

Centertrack and naver airush 2020 review
Centertrack and naver airush 2020 reviewCentertrack and naver airush 2020 review
Centertrack and naver airush 2020 review
 
deep learning from scratch chapter 6.backpropagation
deep learning from scratch chapter 6.backpropagationdeep learning from scratch chapter 6.backpropagation
deep learning from scratch chapter 6.backpropagation
 
Deep learning based gaze detection system for automobile drivers using nir ca...
Deep learning based gaze detection system for automobile drivers using nir ca...Deep learning based gaze detection system for automobile drivers using nir ca...
Deep learning based gaze detection system for automobile drivers using nir ca...
 
Object Tracking By Online Discriminative Feature Selection Algorithm
Object Tracking By Online Discriminative Feature Selection AlgorithmObject Tracking By Online Discriminative Feature Selection Algorithm
Object Tracking By Online Discriminative Feature Selection Algorithm
 
nnU-Net: a self-configuring method for deep learning-based biomedical image s...
nnU-Net: a self-configuring method for deep learning-based biomedical image s...nnU-Net: a self-configuring method for deep learning-based biomedical image s...
nnU-Net: a self-configuring method for deep learning-based biomedical image s...
 
Face detection system design seminar
Face detection system design seminarFace detection system design seminar
Face detection system design seminar
 
Testing Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal PerspectiveTesting Machine Learning-enabled Systems: A Personal Perspective
Testing Machine Learning-enabled Systems: A Personal Perspective
 
End of Year Presentation
End of Year PresentationEnd of Year Presentation
End of Year Presentation
 
Can we predict the quality of spectrum-based fault localization?
Can we predict the quality of spectrum-based fault localization?Can we predict the quality of spectrum-based fault localization?
Can we predict the quality of spectrum-based fault localization?
 
Keynote SBST 2014 - Search-Based Testing
Keynote SBST 2014 - Search-Based TestingKeynote SBST 2014 - Search-Based Testing
Keynote SBST 2014 - Search-Based Testing
 
Enabling Automated Software Testing with Artificial Intelligence
Enabling Automated Software Testing with Artificial IntelligenceEnabling Automated Software Testing with Artificial Intelligence
Enabling Automated Software Testing with Artificial Intelligence
 
A comparison of SIFT, PCA-SIFT and SURF
A comparison of SIFT, PCA-SIFT and SURFA comparison of SIFT, PCA-SIFT and SURF
A comparison of SIFT, PCA-SIFT and SURF
 
Scalable and Cost-Effective Model-Based Software Verification and Testing
Scalable and Cost-Effective Model-Based Software Verification and TestingScalable and Cost-Effective Model-Based Software Verification and Testing
Scalable and Cost-Effective Model-Based Software Verification and Testing
 
Practical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test DataPractical Constraint Solving for Generating System Test Data
Practical Constraint Solving for Generating System Test Data
 
A practical guide for using Statistical Tests to assess Randomized Algorithms...
A practical guide for using Statistical Tests to assess Randomized Algorithms...A practical guide for using Statistical Tests to assess Randomized Algorithms...
A practical guide for using Statistical Tests to assess Randomized Algorithms...
 
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
Automatic Test Suite Generation for Key-Points Detection DNNs using Many-Obje...
 
AI in SE: A 25-year Journey
AI in SE: A 25-year JourneyAI in SE: A 25-year Journey
AI in SE: A 25-year Journey
 
Ag04606202206
Ag04606202206Ag04606202206
Ag04606202206
 

Similar to Tablet gaze unconstrained appearance based gaze estimation in mobile tablets

Neural networks for semantic gaze analysis in xr settings
Neural networks for semantic gaze analysis in xr settingsNeural networks for semantic gaze analysis in xr settings
Neural networks for semantic gaze analysis in xr settingsJaey Jeong
 
hands on machine learning Chapter 6&7 decision tree, ensemble and random forest
hands on machine learning Chapter 6&7 decision tree, ensemble and random foresthands on machine learning Chapter 6&7 decision tree, ensemble and random forest
hands on machine learning Chapter 6&7 decision tree, ensemble and random forestJaey Jeong
 
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...Diako Mardanbegi
 
Diagnosis Support by Machine Learning Using Posturography Data
Diagnosis Support by Machine Learning Using Posturography DataDiagnosis Support by Machine Learning Using Posturography Data
Diagnosis Support by Machine Learning Using Posturography DataTeruKamogashira
 
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...sugiuralab
 
Improving Genetic Algorithm (GA) based NoC mapping algorithm using a formal ...
Improving Genetic Algorithm (GA)  based NoC mapping algorithm using a formal ...Improving Genetic Algorithm (GA)  based NoC mapping algorithm using a formal ...
Improving Genetic Algorithm (GA) based NoC mapping algorithm using a formal ...Vinita Palaniveloo
 
Reading Group 2014
Reading Group 2014Reading Group 2014
Reading Group 2014Emir Muñoz
 
PGL SUM Video Summarization
PGL SUM Video SummarizationPGL SUM Video Summarization
PGL SUM Video SummarizationVasileiosMezaris
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for visionJaey Jeong
 
Gaze supported 3 d object manipulation in virtual reality
Gaze supported 3 d object manipulation in virtual realityGaze supported 3 d object manipulation in virtual reality
Gaze supported 3 d object manipulation in virtual realityJaey Jeong
 
DutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLDutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLBigML, Inc
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data ExtractionDasha Herrmannova
 
deep learning from scratch chapter 5.learning related skills
deep learning from scratch chapter 5.learning related skillsdeep learning from scratch chapter 5.learning related skills
deep learning from scratch chapter 5.learning related skillsJaey Jeong
 
Usability_Presentation
Usability_PresentationUsability_Presentation
Usability_PresentationXuan Guo
 
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...Rafael Ferreira da Silva
 

Similar to Tablet gaze unconstrained appearance based gaze estimation in mobile tablets (20)

Neural networks for semantic gaze analysis in xr settings
Neural networks for semantic gaze analysis in xr settingsNeural networks for semantic gaze analysis in xr settings
Neural networks for semantic gaze analysis in xr settings
 
hands on machine learning Chapter 6&7 decision tree, ensemble and random forest
hands on machine learning Chapter 6&7 decision tree, ensemble and random foresthands on machine learning Chapter 6&7 decision tree, ensemble and random forest
hands on machine learning Chapter 6&7 decision tree, ensemble and random forest
 
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...
EyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Usin...
 
Eye Tracking for Predicting ADHD
Eye Tracking for Predicting ADHDEye Tracking for Predicting ADHD
Eye Tracking for Predicting ADHD
 
Diagnosis Support by Machine Learning Using Posturography Data
Diagnosis Support by Machine Learning Using Posturography DataDiagnosis Support by Machine Learning Using Posturography Data
Diagnosis Support by Machine Learning Using Posturography Data
 
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
 
Erfaringer med Remote Usability Testing af Jan Stage, AAU
Erfaringer med Remote Usability Testing af Jan Stage, AAUErfaringer med Remote Usability Testing af Jan Stage, AAU
Erfaringer med Remote Usability Testing af Jan Stage, AAU
 
Improving Genetic Algorithm (GA) based NoC mapping algorithm using a formal ...
Improving Genetic Algorithm (GA)  based NoC mapping algorithm using a formal ...Improving Genetic Algorithm (GA)  based NoC mapping algorithm using a formal ...
Improving Genetic Algorithm (GA) based NoC mapping algorithm using a formal ...
 
Reading Group 2014
Reading Group 2014Reading Group 2014
Reading Group 2014
 
PGL SUM Video Summarization
PGL SUM Video SummarizationPGL SUM Video Summarization
PGL SUM Video Summarization
 
Design of Experiments
Design of ExperimentsDesign of Experiments
Design of Experiments
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for vision
 
Kaggle kenneth
Kaggle kennethKaggle kenneth
Kaggle kenneth
 
Gaze supported 3 d object manipulation in virtual reality
Gaze supported 3 d object manipulation in virtual realityGaze supported 3 d object manipulation in virtual reality
Gaze supported 3 d object manipulation in virtual reality
 
DutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in MLDutchMLSchool 2022 - History and Developments in ML
DutchMLSchool 2022 - History and Developments in ML
 
Machine Learning for Data Extraction
Machine Learning for Data ExtractionMachine Learning for Data Extraction
Machine Learning for Data Extraction
 
deep learning from scratch chapter 5.learning related skills
deep learning from scratch chapter 5.learning related skillsdeep learning from scratch chapter 5.learning related skills
deep learning from scratch chapter 5.learning related skills
 
Video Thumbnail Selector
Video Thumbnail SelectorVideo Thumbnail Selector
Video Thumbnail Selector
 
Usability_Presentation
Usability_PresentationUsability_Presentation
Usability_Presentation
 
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...
Toward Fine-Grained Online Task Characteristics Estimation in Scientific Work...
 

Recently uploaded

TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providermohitmore19
 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...OnePlan Solutions
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...gurkirankumar98700
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfkalichargn70th171
 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...panagenda
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...MyIntelliSource, Inc.
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Steffen Staab
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerThousandEyes
 
Clustering techniques data mining book ....
Clustering techniques data mining book ....Clustering techniques data mining book ....
Clustering techniques data mining book ....ShaimaaMohamedGalal
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...ICS
 
How To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsHow To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsAndolasoft Inc
 
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AIABDERRAOUF MEHENNI
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...OnePlan Solutions
 
Active Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfActive Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfCionsystems
 
5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdfWave PLM
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...kellynguyen01
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comFatema Valibhai
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️anilsa9823
 

Recently uploaded (20)

TECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service providerTECUNIQUE: Success Stories: IT Service provider
TECUNIQUE: Success Stories: IT Service provider
 
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
Tech Tuesday-Harness the Power of Effective Resource Planning with OnePlan’s ...
 
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
(Genuine) Escort Service Lucknow | Starting ₹,5K To @25k with A/C 🧑🏽‍❤️‍🧑🏻 89...
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
 
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
W01_panagenda_Navigating-the-Future-with-The-Hitchhikers-Guide-to-Notes-and-D...
 
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
Steps To Getting Up And Running Quickly With MyTimeClock Employee Scheduling ...
 
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
Shapes for Sharing between Graph Data Spaces - and Epistemic Querying of RDF-...
 
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected WorkerHow To Troubleshoot Collaboration Apps for the Modern Connected Worker
How To Troubleshoot Collaboration Apps for the Modern Connected Worker
 
Clustering techniques data mining book ....
Clustering techniques data mining book ....Clustering techniques data mining book ....
Clustering techniques data mining book ....
 
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
The Real-World Challenges of Medical Device Cybersecurity- Mitigating Vulnera...
 
How To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.jsHow To Use Server-Side Rendering with Nuxt.js
How To Use Server-Side Rendering with Nuxt.js
 
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS LiveVip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
Vip Call Girls Noida ➡️ Delhi ➡️ 9999965857 No Advance 24HRS Live
 
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AISyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
SyndBuddy AI 2k Review 2024: Revolutionizing Content Syndication with AI
 
Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...Advancing Engineering with AI through the Next Generation of Strategic Projec...
Advancing Engineering with AI through the Next Generation of Strategic Projec...
 
Active Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdfActive Directory Penetration Testing, cionsystems.com.pdf
Active Directory Penetration Testing, cionsystems.com.pdf
 
5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf5 Signs You Need a Fashion PLM Software.pdf
5 Signs You Need a Fashion PLM Software.pdf
 
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
Short Story: Unveiling the Reasoning Abilities of Large Language Models by Ke...
 
HR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.comHR Software Buyers Guide in 2024 - HRSoftware.com
HR Software Buyers Guide in 2024 - HRSoftware.com
 
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online  ☂️
CALL ON ➥8923113531 🔝Call Girls Kakori Lucknow best sexual service Online ☂️
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 

Tablet gaze unconstrained appearance based gaze estimation in mobile tablets

  • 1. Interaction Lab. Kumoh National Institute of Technology TabletGaze : Unconstrained Appearance-based Gaze Estimation in Mobile Tablets :Computer Vision and Pattern Recognition 2016 Jeong JaeYeop
  • 2. ■Intro ■Rice TabletGaze dataset ■TabletGaze algorithms ■Results and analysis ■Discussion and conclusion Agenda Interaction Lab., Kumoh National Institue of Technology 2
  • 3. Intro Rice TabletGaze dataset TabletGaze algorithms Data Engineering Lab., Kumoh National Institue of Technology 3
  • 4. ■Gaze estimation in Mobile Tablets  Commonplace connected mobile computing device  User-tablet interaction • Touch and sound • Gaze is an emerging proxy of the user’s attention and intention ■ Hands-free human device interaction ■ Behavior studies ■ User authentication Intro(1/4) Interaction Lab., Kumoh National Institue of Technology 4
  • 5. ■Gaze estimation in Mobile Tablets  Gaze estimation of tablets • Without requiring any additional hardware • Front-facing cameras • Appearance-based methods ■ Not calibration stage ■ Mapping from appearance of eye region to gaze direction Intro(2/4) Interaction Lab., Kumoh National Institue of Technology 5
  • 6. ■A key challenge in tablet gaze estimation  No constraint on • How people use the tablet • What kind of body posture people have when using tablet • The user of the tablet Intro(3/4) Interaction Lab., Kumoh National Institue of Technology 6
  • 7. ■Tablet gaze estimation problem in three steps  Collect dataset an unconstrained mobile gaze dataset of tablet • 51 subjects • Rice TabletGaze dataset  TabletGaze Algorithms • Feature extraction • Dimensionality reduction • Regression  Analysis Intro(4/4) Interaction Lab., Kumoh National Institue of Technology 7
  • 8. Rice TabletGaze dataset TabletGaze algorithms Results and analysis Data Engineering Lab., Kumoh National Institue of Technology 8
  • 9. ■Rice TabletGaze dataset  Unique, unconstrained characteristics in the mobile environment • 51 subjects, each with 4 different body postures • Released online  The learned model can be used for other devices • Transfer learning, domain adaptation Rice TabletGaze dataset(1/10)
  • 10. ■Data collection  Setup • Samsung Galaxy Tab S 10.5 ■ Screen size of 22.62 x 14.14 com (8.90 x 5.57 inches) ■ 35 gaze locations (points) ■ The raw data(videos) captured by the front-camera ■ Resolution – 1280 x 720 • 51 subjects ■ 12 female and 39 male ■ 26 of them wearing prescription glasses ■ 28 of the subjects are Caucasians, and the remaining 23 are Asians ■ The ages of subjects range from 20 to 40 Rice TabletGaze dataset(2/10) Interaction Lab., Kumoh National Institue of Technology 10
  • 11. ■Data collection  Four body postures • Standing • Sitting • Slouching • Lying  Four recording session and four body posture • 16 video sequences • No restriction on ■ How the subject held the tablet ■ How they performed each body posture  Natural lit office environment Rice TabletGaze dataset(3/10) Interaction Lab., Kumoh National Institue of Technology 11
  • 12. ■Data collection  One data collection session • Front-facing camera of the tablet begin recording a video • Beep sound notified the beginning of the video • Dot changing its location every three seconds and focus ■ Dot Randomize among 35 possible points ■ Free to blink Rice TabletGaze dataset(4/10) Interaction Lab., Kumoh National Institue of Technology 12
  • 13. ■Observations on the Rice TabletGaze dataset  The entire face may not be visible in most of the image frames • To quantify the extent of facial visibility, label each video in the dataset ■ The whole face ■ From mouth and above ■ From nose and above ■ From eyes and above ■ Even the eyes are no visible • Manually reviewed 4 images Rice TabletGaze dataset(5/10) Interaction Lab., Kumoh National Institue of Technology 13
  • 14. ■Observations on the Rice TabletGaze dataset  Body posture and facial visibility extent appear to be correlated Rice TabletGaze dataset(6/10) Interaction Lab., Kumoh National Institue of Technology 14
  • 15. ■Observations on the Rice TabletGaze dataset  Glasses can cause reflection, and in many instances, the reflection can be significant Rice TabletGaze dataset(7/10) Interaction Lab., Kumoh National Institue of Technology 15
  • 16. ■Sub-dataset Labeling  The total amount of raw data • 51 x 16 = 816 video sequences • A portion of the data is not usable ■ Loss of concentration of subjects ■ Eye detector failure ■ Involuntary eye blinks and large motion blur  Sub-dataset of 41 subjects to be used in experiments Rice TabletGaze dataset(8/10) Interaction Lab., Kumoh National Institue of Technology 16
  • 17. ■Sub-dataset Labeling  Loss of concentration of subjects • Refocus time • Extract after 1.5 to 2.5 seconds when dot appears at a new location • For the 35 videos chunk from extracted from each video ■ Inspect gaze drift more than 5 video chunk, if so, abandon the data • Hard to determine the true gaze location Rice TabletGaze dataset(9/10) Interaction Lab., Kumoh National Institue of Technology 17
  • 18. ■Sub-dataset Labeling  Eye detector failures • Eyes are not visible in the image frame • Strong reflection from glasses • Occlusion from hair • Poor illumination  Use LoG(Laplacian of Gaussian) value • Images of closed eyes ■ Higher mean intensity value given the disappearance of the dark pupil • Blurred eye region image ■ Lower mean intensity value because motion blur weakens the edge information Rice TabletGaze dataset(10/10) Interaction Lab., Kumoh National Institue of Technology 18
  • 19. TabletGaze algorithms Results and analysis Discussion and conclusion Data Engineering Lab., Kumoh National Institue of Technology 19
  • 21. ■Preprocessing  Eye detector • Two Harr feature CART-tree based cascade detectors • False positive bounding boxes ■ Establish threshold for the size of the box (nostril) ■ Symmetric locations of the boxes (mouth) • 100 x 15 resize TabletGaze algorithms(2/6) Interaction Lab., Kumoh National Institue of Technology 21
  • 22. ■Feature Calculation  Feature extraction • Contrast normalized pixel intensities • LoG (Laplacian of Gaussian) • LBP (Local Binary Pattern) • HoG (Histogram of Oriented Gradients) • mHoG (multilevel HoG) ■ Concatenate HoG features at different scales TabletGaze algorithms(3/6) Interaction Lab., Kumoh National Institue of Technology 22
  • 23. ■Feature Calculation  Dimensionality reduction • Feature is High dimensional and compromised by noise • Mapping the features to a lower dimensional space • CNN pooling • LDA (Linear Discriminant Analysis) • PCA (Principal Component Analysis) TabletGaze algorithms(4/6) Interaction Lab., Kumoh National Institue of Technology 23
  • 24. ■Feature Calculation  LDA (Linear Discriminant Analysis) • Intra-class scatter is maximized • Inter-class scatter is minimized  PCA(Principal Component Analysis) TabletGaze algorithms(5/6) Interaction Lab., Kumoh National Institue of Technology 24
  • 25. ■Regression  The gaze labels of the data include two parts • Horizontal and vertical coordinates on the tablet screen (x, y)  Methods • k-NN (k-Nearest Neighbors) • RF (Random Forest) ■ Set of weak binary tree regressors ■ 100 trees • GPR (Gaussian Process Regression) • SVR (Support Vector Regression) TabletGaze algorithms(6/6) Interaction Lab., Kumoh National Institue of Technology 25
  • 26. Results and analysis Discussion and conclusion Data Engineering Lab., Kumoh National Institue of Technology 26
  • 27. ■Error Metrics  Previous works • Angular error ■ Arctangent of the ratio between the distance from the subject’s eyes to screen  This work • Mean Error (ME) ■ 2D location on the tablet Results and analysis(1/8)
  • 28. ■Comparisons for different features + regressors  Use 100,000 images from 41 subjects using cross validation • GPR, SVR are only used 15 subject data Results and analysis(2/8) Interaction Lab., Kumoh National Institue of Technology 28
  • 29. ■ Person-dependent and person-independent performance comparison  in prior works appearance-based gaze estimation methods • Person and session dependent Results and analysis(3/8) Interaction Lab., Kumoh National Institue of Technology 29
  • 30. ■Comparison with prior results Results and analysis(4/8) Interaction Lab., Kumoh National Institue of Technology 30
  • 31. ■Effect of training data size  Groups of different sizes 𝐾 • 𝐾 : 2 ~ 41  Use 𝐾 − 1 for training, one is test  Randomly selecting a subset of data  Repeat the same process 5 times and average Results and analysis(5/8) Interaction Lab., Kumoh National Institue of Technology 31
  • 32. ■Eyeglasses, race and posture  Three experiments setups • Experiment 1 ■ The dataset was partitioned into 2 groups of wearing glasses and not ■ Training and testing are done separately for each group • Experiment 2 ■ Leave-one-subject-out cross validation for all data ■ ME is separated for each group • Experiment 3 ■ Combine data of half each group Results and analysis(6/8) Interaction Lab., Kumoh National Institue of Technology 32
  • 33. ■Eyeglasses, race and posture Results and analysis(7/8) Interaction Lab., Kumoh National Institue of Technology 33
  • 34. ■Continuous gaze tracking from videos  Use temporal information • Bilateral filter Results and analysis(8/8) Interaction Lab., Kumoh National Institue of Technology 34
  • 35. Discussion and conclusion Data Engineering Lab., Kumoh National Institue of Technology 35
  • 36. ■Discussion  All of the evaluations of the algorithms are conducted on a desktop  Pre-trained off-line and loaded onto the device  RF + mHoG feature • Real time gaze estimation Discussion and conclusion(1/2)
  • 37. ■Conclusion  Unconstrained mobile gaze estimation problem • A large dataset is collected in an unconstrained environment ■ First dataset ■ Four different postures • ME : 3.17±2.10 cm Discussion and conclusion(2/2) Interaction Lab., Kumoh National Institue of Technology 37
  • 38. Q&A Data Engineering Lab., Kumoh National Institue of Technology 38