Pupil center detection for infrared irradiation eye image using CNN

This research proposes a convolutional neural network based pupil center detection method from an eye image which is captured by a wearable eye camera. This paper investigates the detection accuracy by applying several preprocessing, such as edge detection, and binarization. We find the preprocess method in order to speed up the computation time. We collected approximately 8,000 eye images with six subjects, and evaluated the performance, and confirmed that the proposed method obtained higher detection accuracy and have the potential to apply for a real-time application.