Implementation to eye motion tracking system using convolutional neural network

Convolutional neural network를 이용한 눈동자 모션인식 시스템 구현

  • Lee, Seung Jun (Dept. of Electrical, Electronic, Control Eng. and IITC, Hankyong National University) ;
  • Heo, Seung Won (Dept. of Electrical, Electronic, Control Eng. and IITC, Hankyong National University) ;
  • Lee, Hee Bin (Dept. of Electrical, Electronic, Control Eng. and IITC, Hankyong National University) ;
  • Yu, Yun Seop (Dept. of Electrical, Electronic, Control Eng. and IITC, Hankyong National University)
  • 이승준 (한경대학교 전기전자제어공학과, IITC) ;
  • 허승원 (한경대학교 전기전자제어공학과, IITC) ;
  • 이희빈 (한경대학교 전기전자제어공학과, IITC) ;
  • 유윤섭 (한경대학교 전기전자제어공학과, IITC)
  • Published : 2018.05.31

Abstract

An artificial neural network design that traces the pupil for the disables suffering from Lou Gehrig disease is introduced. It grasps the position of the pupil required for the communication system. Tensorflow is used for generating and learning the neural network, and the pupil position is determined through the learned neural network. Convolution neural network(CNN) which consists of 2 stages of convolution layer and 2 layers of complete connection layer is implemented for the system.

본 논문은 몸을 움직이지 못하는 루게릭병 환자들을 위해 눈동자를 추적하여 의사소통 시스템에 필요한 눈동자의 위치를 파악해주는 인공신경망 설계에 대해 소개한다. Tensorflow를 이용해 신경망 생성 및 학습하고 학습된 신경망을 통하여 눈동자의 위치를 파악한다. 본 논문에서는 컨볼루션계층 2단계와 완전연결계층 2단계로 구성된 Convolution Neural Network(CNN)을 사용해서 구현했다.

Keywords