A Driver Pattern Recognition System was
developed, using concepts based on the concept of a nondisruptive machine. The machine uses a small
monochrome safety camera that points directly to the
driver's face and monitors the driver's eyes to detect
fatigue. In such a case when fatigue is detected, the
driver is alerted with a warning signal and if the driver
is distracted he will also warn the driver to be careful.
This report explains how the eyes can be found, and how
to determine if the eyes are open or closed. The advanced
algorithm differs from any currently published
documents which is the main objective of the project.
The device deals with finding facial edges using
information obtained from the binary version of the
image, which reduces the area where the eyes will be.
When the surface area is defined, the eyes are obtained
by measuring the horizontal area. Recalling the
knowledge that the circuits of the eyes on the face bring
about a great change in strength, The eyes are obtained
by experiencing major changes in facial pressure. When
the eyes are in a good position, measuring the distances
between the size changes in the eye area determines
whether the eyes are open or closed. The long distance is
associated with blindfolds. If the eyes are found closed
with five consecutive frames, the machine assumes the
driver is asleep and sends an alarm. Also, the system can
detect when the eyes are not available and operate under
appropriate lighting conditions
Keywords : Binarisation, OpenCV, Detection Algorithm, Noise Removal.