Automatic ocular version evaluation in images using random forest
作者：
Highlights：
• This work proposes an innovative automatic method for ocular version evaluation.
• Location of the eye steps used Histograms of Oriented Gradients and Random Forest.
• The sclera was segmented using statistical characteristics and the Random Forest.
• Version measure uses markers circles for each of the nine eye gaze positions exams.
• The method achieved a 92.41% accuracy in the dataset with 147 images of 21 patients.
摘要
•This work proposes an innovative automatic method for ocular version evaluation.•Location of the eye steps used Histograms of Oriented Gradients and Random Forest.•The sclera was segmented using statistical characteristics and the Random Forest.•Version measure uses markers circles for each of the nine eye gaze positions exams.•The method achieved a 92.41% accuracy in the dataset with 147 images of 21 patients.
论文关键词：Version test,Eye movement,Strabismus,Histogram of oriented gradient,Random forest
论文评审过程：Received 30 July 2020, Revised 3 December 2020, Accepted 2 March 2021, Available online 14 March 2021, Version of Record 1 April 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114847
