The Problem

The Problem

Sana Naghipour, Saba Naghipour, Phani Chavali , Ed Richter, and Arye Nehorai
Preston M. Green Department of Electrical and Systems Engineering

Abstract
The Eye tracker project is a research initiative to enable people,
who are suffering from Amyotrophic Lateral Sclerosis (ALS), to
use prosthetic limbs using their eyes by tracking the movement
of the pupil. The project will be implemented in two main
phases. The idea is to mount an infrared camera onto a pair of
sunglasses and capture the movement of the pupil, and move
the limbs using the control signal generated, based on the pupil
movements. In this semester, we focused on developing
software tools for tracking the motion of the eye. In the next
semester, we will build the hardware necessary to control the
prosthetic limbs.

Overview
Goal
To track the location of the pupil, in a live video stream using
image processing techniques.

Experimental Setup

Procedure Description
We implement our project in the following steps.

Image Acquisition

We use Labview to capture the video using an infrared camera. There is
support for recording of videos with several frame rates, and formats.
After obtaining the video, we perform sequential frame by frame
processing.

Discarding Color information

We convert the images from all the frames into to their corresponding
gray scale images. To do this, we average the pixel values in all the
three color channel to obtain a gray scale image.

Low pass filtering

b) Labview instrument

a) Experimental Setup

We use low-pass filtering to remove the sharp edges in each image.
This also helps to remove the undesired background light in the
image.

Some Examples

Approach
First Phase : development of the software for pupil tracking
Second Phase : building the hardware necessary to capture
the images of the eye and transfer the images to a processing
unit
Applications
Help ALS patients in various tasks such as communication,
writing emails, drawing, making music.
Challenges
The challenges include but are not limited to developing
algorithms that are: (i) fast, which obtain good frame rate (ii)
robust, that are insensitive to lighting conditions and facial
irregularities.

We scale down the filtered images to obtain lower resolution images.
This serves two purposes. First, since the dimension of the image
decreases, scaling improves the processing time. Second, the
averaging effect removes the undesired background light.

Template Matching

We used a template matching algorithm to segment the darkest region of
the image. Since after discarding the color information and, low-pass
filtering, the pupil corresponds to the darkest spot in the eye, this
method was used. We used a small patch of dark pixels as a
template. The matching is done using exhaustive search over the
entire image. Once a match is found, the centroid of the this block
was determined to the pupil location. For the experiments, we used a
block size of 5 x 5 pixels.

The picture is taken from the website:
http://www.eyewritter.org. The image shows pair of infrared
cameras mounted on sunglasses to detect the pupil
movements of the patient.

Scaling

Determining the search space

Since the exhaustive search over the entire image to find a match is
computationally intensive, we propose an adaptive search method.
Using this method, we choose the search space based on the pupil
location from earlier frame. In this manner, using the past information,
we were able to greatly reduce the complexity of the search. We
used a search space of 75 X 75 pixels around the pupil location from
the last frame.

Conclusion
An algorithm for estimating the position and the movement of the pupil is
implemented using a template matching method. In the future, we will build the
necessary hardware that uses the algorithm for prosthetic limb control.

References
1.

http://www.eyewriter.org

2.

P. W. Hallinan, Recognizing human eyes, in: SPIE Proceedings,Vol. 1570:
Geometric Methods in Computer Vision, 1991, pp. 212{226.

Recently Viewed Presentations

  • Arthropods

    Arthropods

    Honey Silk Characteristics: How are they helpful? Honey Silk Plant pollination Characteristics: How are they helpful? Honey Silk Plant pollination Decomposition Characteristics: How are they helpful? Honey Silk Plant pollination Decomposition Kill harmful insects Insects How do Arthropods (Insects) adapt...
  • Three Levels of "Knowing Another Person" Dan McAdams

    Three Levels of "Knowing Another Person" Dan McAdams

    What is Personality? Personality Lab January 14, 2011 Three Levels of "Knowing Another Person" Dan McAdams Personality Traits - psychology of the stranger The Five Factor Model aka The Big 5 Neurotic vs. Emotionally Stable Extraversion vs. Introversion Openness to...
  • Elevating your writing

    Elevating your writing

    Please note: Do not begin with the sentence, "In The Great Gatsby . . .. Do introduce your thesis logically; some people had too much plot summary (this is not a book report), while others had not enough.
  • OUTPUT HARDWARE ERDINA PRAHASTUTI (23339) / 47 NOVI

    OUTPUT HARDWARE ERDINA PRAHASTUTI (23339) / 47 NOVI

    Gas-plasma display : seperti suatu bohlam/gelembung neon, di mana tampilan menggunakan suatu gas yang memancarkan cahaya di depan suatu arus elektrik. Itu adalah, teknologi yang menggunakan sebagian besar gas neon dan electroda di atas dan di bawah gas itu. Ketika...
  • Early Middle Ages

    Early Middle Ages

    FOUR copies (print 1 or 2 extras to be safe) Print TONIGHT to avoid another library "disaster" Cannot pass cycle 4 without handing it in Harsh deductions for all late papers H.W. #3 The Renaissance: Art & Values Renaissance ideas...
  • TITLE

    TITLE

    It might help to jot down a word or two first about that feeling. Draw a rough rectangle. Depict your idea in a very simple sketch. Outline the major shapes. Ignore smaller shapes and details. Try squinting to see only...
  • Chapter 5 Skeletal System - Pearl Public School District

    Chapter 5 Skeletal System - Pearl Public School District

    Chapter 5 Skeletal System Organization Bones is composed of osseous tissue. Bones comprise the skeleton. The skeleton functions in: Support Protection Movement Storage Organization The skeleton is comprised of 206 bones divided into sections: Axial: head, neck, and trunk TOTAL:...
  • Emerging Technologies and Advanced Materials: Industry Perspectives on

    Emerging Technologies and Advanced Materials: Industry Perspectives on

    (100 times more than in Si) highest current density at room T (100 times of copper) longest mean free path at room T (micron range) ... and theoretical approaches used to explore physical processes associated with the spin-wave propagation in...