2. Motivation of work
Main objective at conference -> Network with other
participants
Golden opportunity that is often wasted
Build a new mobile platform that facilitates this
process
Finding and presenting essential information to the
user using augmented reality technologies
3. Motivation of work
In a conference:
Who should I talk to?
Who is that guy over there? He seems familiar.
How do I find out more about him?
How do I get an opportunity to talk to him?
How do I approach him?
4. Project Objectives
To create a mobile application that enables users to
network effectively with other participants in a
conference
Evaluate the usefulness of the system.
5. Approach
Platform: iPhone 4
Main Features:
(Who to talk to?)
Real-time mobile Facial Search
Conference booklet with QRCodes
(How to find out more about him?)
Facebook integration
(How to contact him?)
Real-time personalized message board
6. Research Topics
Balance between privacy concerns and ease of use
• Find out best possible way to gather information about
participants in a conference without intruding their
privacy but requiring minimal user input
• Can make use of existing social networks to get
participants information but needs to be appropriate
in a conference context
7. Research Topics (cont)
Usefulness of the various user search tools for
identifying people.
Textual Search
Facial Search
QR Search
8. Research Topics (cont)
Effectiveness of mobile tool for conference
networking purposes
Evaluation of system
Ease of use
Error frequency
Interface design
Task suitability
Satisfaction
Privacy concerns
10. Application Flowchart
Facebook
Login
Login
Account Normal
Settings Login
Conference
List
Textual Personal
Conference Message
Search
Details board
Participant Participant
Facial Search
List Details
QR Search
11. Core Feature: Facial Search
Allows user to easily identify other participants in the
conference using facial detection and facial
recognition technologies
Non-intrusive and appropriate in conference context
Training images can be obtained from social networks
to relieve user manual input
Results augmented on screen
12. General Approach
Grab image Augment
Facial Facial
from camera results on
Detection Recognition
frame screen
13. Challenges
Running speed on Mobile Devices
Most algorithms require fast CPU speed and high
memory
Accuracy
Accuracy is heavily dependent on pose and illumination
Obtaining Training Images
Get sufficient quality training images without heavy user
input
Capturing moving images
Distance factor
15. Current Progress
Face Detection
OpenCV
Implements Viola-Jones object detection framework
Makes use of Haar Classifier to describe and find general
facial features
Accuracy level for frontal view : 95%
Already tested on the phone – average of 1 to 2s
16. Current Progress
Face Recognition
1st Method: Face.com
->3rd party web-based recognition tool
Advantages:
Easy to use
Accuracy level: 70%
Disadvantages:
Not open source
Huge overhead to post image to web to get results
Slow
17. Current Progress
Face Recognition
2nd Method: Eigenfaces
-> Using PCA (Principal Component Analysis)
Advantages
Fast
Uses less memory
Disadvantages
Build from scratch
Proclaimed accuracy level: 60%
19. Timeline:
Mar Apr May Jun Jul Aug Sep Oct Nov
1 Research and Implementation
V Research on QR's current implementation
V Implement QR algorithm in ObjectiveC
V Implement QR tracking in the booklet
WJ System Design and Modelling
Building the framework and foundation of the
WJ application
2 Integration and Iteration
V Ensure Accuracy and Tweaks to QR tracking
WJ Adding extra features to Application
V & WJ Modifications to application based on tests
3 Usability and Thesis
V & WJ Carry out usability tests at conferences
V & WJ Thesis and Technical Paper
Right now, there is no easy way to get these answers. Our app hopes to be an integrated platform for users to obtain these kind of information that they need. Research shown that Form stronger memory associationsExample scenario:
For app to be useful and popular -> easy to use and fuss-freeWhere to go get the info?People are too busy. Too tedious to fill in data manually
Example scenarios: Familiar face, fast forward sessionsAccuracy problems ->search
People wear name tags but might be too far to see.Reasonable distance factor is about one room distance.