2. INTRODUCTION
Hand-free Interfacing System.
Used only by users Eye movement.
Camera mounted on front.
Track the eye and infer its position.
Nokia N810 presents it.
Human Computer Interface(HCI) has
introduce Touchscreen.
3. Human-Phone Interaction
It present new Challenges need
to addressed driven by
1.Issues of Mobility
2.Factor of the Phone
3.Resource Limitations
Mobile Phone Environment are
Mobility and Hardware Support.
4. Mobility Challenges:
It moved through Unpredicted
Context.
Uncontrolled Movement
Hardware Challenges:
HPI does not rely on any External
Hardware.
It adopt lightweight machine
learning techniques to run properly.
5. EyePhone Design
The EyePhone algorithmic design
breaks down into following Pipeline
Phases they are:
1.Eye Detection Phase.
2.Open Eye Template Creation Phase.
3.Eye Tracking Phase.
4.Blink Detection Phase.
6. Pipeline Phase
Eye Detection Phase:
The eye pair is identified by the left
and right eye contours.
Left figure: example of eye contour pair returned
by the original algorithm running on a desktop
with a USB camera. The two white clusters
identify the eye pair.
Right figure: example of number of contours
returned by EyePhone on the Nokia N810. The
smaller dots are erroneously interpreted as eye
contours.
7. Open Eye Templates Creation:
It extract the template every time the eye
pair is lost. It rely different strategies.
It creates the template of user open eye
once at the beginning.
Template is saved in the persistent
memory and fetched when EyePhone is
invoked.
Lighting conditions might not be perfectly
suitable for other Environment.
8. Eye Tracking:
It based on template matching.
The search window is limited to a
region which is twice the size of
box enclosing the eye.
Threshold has been verified by
multiple experiments under
different condition.
9. CONCEPT IN NOKIA N810
Eye capture using the Nokia N810 front camera
running the EyePhone system. The inner white box
surrounding the right eye is used to discriminate the
nine positions of the eye on the phone’s display. The
outer box encloses the template matching region
10. Blink Detection:
Thresholding technique is applied.
There are two situation to deal:
1.Quality of camera is not good as
USB.
2.Closer to persons face using
desktop and USB camera.
11. Applications
Two Applications they are:
1.Eye Menu
2.Car Driver Safety
Eye Menu:
• It is customized by users.
• Eye mapped to one of Nine buttons.
• A button is highlighted when eye detects
the button.
• If we blinks the application is launched.
12. EYEMENU:
EyeMenu on the Nokia N900. While looking
the display, a button is highlighted if it matches
the eye position on the display. The highlighted
button is ready to be “clicked” with a blink of the
eye. In this example, the user is looking at the
SMS button and the SMS keypad is launched by
blinking the eye.
13. Car Safety Driver:
• It detect drivers drowsiness
and distraction in cars.
• Dedicated by sensors and
cameras
• It use for low-end cars by
clipping the phone on the car
dashboard.
14. CONCLUSION
• The EyePhone relies on eye
tracking and blink detection to
drive a mobile phone.
• EyePhone is a promising
approach to drive mobile
appplication as hand free manner