Estimation of visual axis during sleep by analyzing infrared video using artificial neural network
Yuji Yahata, Syoji Kobashi, Shigeyuki Kan, Masaya Misaki, Katsuya Kondo, Satoru Miyauchi, Yutaka Hata · 2007
Measuring visual axis on the eye closure will play one of important roles to investigate the brain function during sleep. It has been investigated using a simultaneous measurement system composed of functional MRI and infrared-video which takes palpebra images with eye closure. Although there are some methods for measuring visual axis from video images, they cannot be applied to estimate visual axis with eye closure because their methods are based on tracing pupil reflection or Purkinje image. This paper proposes a novel method for fully- automatically estimating visual axis with eye closure using infrared-video. The method evaluates intensity profile on palpebra using artificial neural network (ANN). The ANN is preliminary trained using visual axes detected from MR image of eyeball. The experimental results showed that the proposed method detected visual axes of right and left eyes within the errors of 1.30±3.34 (RMSE±SD) deg and 1.12±3.70 deg, respectively.