the eye regions of laptop users. To achieve this, the iris and eye corners are detected by processing the images captured by the standard internal webcam of a laptop. In addition, an artificial neural network (ANN) is used for determining the eye region. Hereby, the iris and eye corners can be detected in the determined eye region. In the study, 107 user images are captured by using a laptop's internal camera under different light intensities, environments, viewpoints, and positions. These images are used for the training of the ANN. Two different methods are used for the iris detection. In the first, circular Hough transform (CHT) is employed for iris detection in the determined eye region. In the second, the right and the left iris regions are determined by using two different ANNs respectively and then CHT is employed for the iris. Higher success rates are achieved by the second method. In the next stage of the study, two different methods, weighted variance projection (WVPF) function and lowest valued pixels (LVP), are used for the detection of the eye corners. It is demonstrated that the second method has a higher performance than the first.
Eye region detection, eye corner detection, iris detection, webcam images
TURAN, BÜLENT and ESKİKURT, HALİL İBRAHİM
"Iris and eye corner detection by processing internal webcam images,"
Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 24:
4, Article 70.
Available at: https://journals.tubitak.gov.tr/elektrik/vol24/iss4/70