Abstract
The necessity for the classification of open and closed eyes is increasing in various fields, including analysis of eye fatigue in 3D TVs, analysis of the psychological states of test subjects, and eye status tracking-based driver drowsiness detection. Previous studies have used various methods to distinguish between open and closed eyes, such as classifiers based on the features obtained from image binarization, edge operators, or texture analysis. However, when it comes to eye images with different lighting conditions and resolutions, it can be difficult to find an optimal threshold for image binarization or optimal filters for edge and texture extraction. In order to address this issue, we propose a method to classify open and closed eye images with different conditions, acquired by a visible light camera, using a deep residual convolutional neural network. After conducting performance analysis on both self-collected and open databases, we have determined that the classification accuracy of the proposed method is superior to that of existing methods.
Highlights
Information regarding whether an eye is open or closed is used for gaze tracking systems [1], and various multimodal computer interfaces
By comparing the performance of the proposed method with fuzzy system-based methods, histogram of oriented gradient (HOG)-support vector machine (SVM) based methods, and various convolutional neural network (CNN) models, we demonstrate its superiority to these other models
database 1 (DB1) was created in an environment with a person watching TV indoors, with images taken at
Summary
Information regarding whether an eye is open or closed is used for gaze tracking systems [1], and various multimodal computer interfaces. An important use-case for detecting closed eyes is in the area of eye-tracking signal processing, where blinks might be seen as noise to the signal [5]. To overcome this problem, they proposed a blink detection algorithm which is tailored towards head-mounted eye trackers and is robust to calibration-based variations such as eye rotation and translation [5]. The necessity for the use of this classification in various applications is increasing, e.g., eye fatigue analysis in 3D TVs, psychological state analysis of experiment subjects, and driver drowsiness detection
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
