Answers are grounded in this paper and cite their sources.
Eyeglasses detection represents an important step for glasses removal. In addition, eyeglasses cause real problems for ocular and facial recognition due to glasses reflection, shadow, and frame occlusion. This paper describes a comparative study for eyeglasses frame detection using different convolutional Neural Network (CNN) structures that have been applied on two different regions of interest (ROI), namely, Frame Bridge and extended ocular region. The best CNN model obtained an overall accuracy of 99.96% for ROI consisting of Frame Bridge.
No takes yet. Share an insight, caveat, or question.
Mohammad et al. (2018) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: