Blinker can be an event to trigger
any action on user interface !
Eye analogue detection
The method is based on the model that the pixels corresponding to the eye in a face image are generally darker than the surrounding regions. As a first step, a filter to detect such pixels applied on a gray-scale image, generating eye-analogue pixels
Eye window detection
The eye-window detector receives as inputs the binary image representing eye analogue pixels. This node processes this image to reduce them to a single candidate for the eye. it set of blobs is filtered using parameters such as the expected height, width.
Main Output of Eye Detector
Eye detection and tracking is integral for attentive user interfaces. Towards this end, we are working on a low cost, reliable eye tracker. We also use eyes to extract higher level features such as pupil, iris and blink rates.