APPD: Adaptive and Precise Pupil Boundary Detection Using Entropy of Contour Gradients
Cihan Topal, Halil Ibrahim Cakir, Cuneyt Akinlar
In this study, we present an adaptive pupil boundary detection method that is able to infer whether entire pupil is in clearly visible by a modal heuristic. Thus, a faster detection is performed with the assumption of no occlusions. If the heuristic fails, a deeper search among extracted image features is executed to maintain accuracy. Furthermore, the algorithm can find out if there is no pupil as an aidful information for many applications. We prepare a dataset containing 3904 high resolution eye images collected from 12 subjects and perform an extensive set of experiments to obtain quantitative results in terms of localization, f-measure and timing. The proposed method outperforms three other state-of-the-art algorithms and can run up to 185 Hz in single-thread on a standard laptop computer.