Pupill Detection Based On Computer Vision A Brief Review
Download as PDF
DOI: 10.23977/csic2022.018
Corresponding Author
Hao Tian
ABSTRACT
Pupil detection is an important research direction in the field of computer vision and it plays a key role in many applications such as eye tracking, strabismus diagnosis and iris recognition. So far, many researchers have proposed different sorts of pupil detection methods, which have been divided into four categories in this paper, including shape features-based pupil detection, projection-based pupil detection, traditional machine learning-based pupil detection and deep learning-based pupil detection. Some specific methods have been listed in each part and elaborated. This study also analyzes the advantages and disadvantages of these methods and explains the existing problems of pupil detection, then points out the development trend of pupil detection and finally makes a summary.
KEYWORDS
Pupil detection eye tracking strabismus diagnosis iris recognition existing problems development trend