Thesis presentation easter

Preview:

DESCRIPTION

 

Citation preview

1

Augmented reality face recognition for mobile devices

Gerry HendrickxPromoter: Professor Erik Duval

Coordinator: Gonzalo Parra

2

Overview

• Recap• Implementation• Storyboard/Screen transition diagram• Evaluation• Demo• Problems• Todo• Planning• Statistics

3

Recap

4

Recap: ConceptAugmented reality face recognition for mobile devices…

Real world augmented with extra information, by using a camera

Extra information will be about people, by recognizing their faces

Camera of smartphone will be used to accomplish goals-> Extra information on screen

… with social network information

Extra information will be taken from social networks

5

Recap: Scenarios

1. Get contact info2. Create a face based contact book3. Quick access to slides/publications by

recognizing speaker4. Quick access to social network information

6

Recap: Technical info

• iOS – Face detection• iPhone• Face.com – Free, SDK, private namespace,…

7

Recap: Paper prototyping

• 3 iterations

8

Paper prototyping: Iteration 1

9

Paper prototyping: Iteration 1

10

Paper prototyping: Iteration 1

11

Paper prototyping: Iteration 2

• Elaboration of UI3• New functionality: History, Settings, Overview

12

Paper prototyping: Iteration 2

• Positive:– Clean UI– iOS style– The concept

• Negative:– Not enough home

buttons– Unclear contact icon– Not him/her button!

13

Paper prototyping: Iteration 3

• Adapted to negative points• Tested with prof Duval and 5 assistants• Should improve:– Incorrect button– Still too much clicking to get somewhere =>

Tabbed Bar– Delete person from history

14

Implementation

15

Implementation: MVCController View Model

SocialRecognizerViewController SocialRecognizerView UserModel

CameraViewController CameraView

OverviewViewController OverviewView RecognizedPerson

HistoryViewController HistoryView UserModel

SettingsViewController SettingsView UserModel

FBRequestWrapper

16

Implementation: Class diagram

17

Implementation: Class diagram

18

Implementation: FBRequestWrapper

– Singleton– Handles all requests from Facebook– Has delegate-methods

– Preferred way to implement it!

19

Implementation: CameraViewController

– Uses AVCaptureSession instead of UIImagePickerController

– Linked with Face.com through API– Uses iOS5 face detection to track faces– Redraws facebox each frame– Tried to be memory efficient

20

Implementation: UserModel

– Saves UID’s and names of friendsReduces # requests

– Saves list of recognized persons– Saves the settings

21

Implementation: RecognizedUser

– Saves UID and name of recognized person– Saves profile picture– Saves all other information received from

Facebook request

22

Storyboard/Screen transition Diagram

23

Storyboard/Screen transition Diagram

24

Demo

25

Storyboard

26

Storyboard

27

Storyboard

28

Evaluation

29

Evaluation: Iteration 1

– Tested with 7 smartphone users– 4 already tested the paper prototype– Current state of the app– Focus on face recognition

– Results and comments were saturated fast

30

Evaluation: Iteration 1

– Think aloud– Tasks– Extra questions about satisfaction– USE questionnaire

31

Evaluation: results

– Tapping the face is cumbersome– Statusinfo

32

Problems

33

Problems

– Knowing which face belongs to who– Tapping the face

– Augmented part is failing…

34

Todo

35

Todo

– Adapt to results evaluation– Implement history and settings– Training algorithm– Multiple social networks– Private namespace

Requires database

Which order???

36

Planning

37

Planning

38

Statistics

39

Statistics# Blog posts 21

# Comments on other blogs 10 (hcifetcher results: 3075)

# Tweets concerning thesis 81

Total # of hours worked 395

# of hours on literature study 20

# of hours on related work 10

# of hours on reports/blog posts 26

# of hours dedicated to other theses 18

# of hours on iOS learning 52

# of hours on design 35

# of hours on paper prototype testing 28

# of hours on paper prototype creating and evaluating

35

# of hours on implementation 166

# of hours on digital prototype testing 5

40

Thank you for listening!

Questions?