Affiliations: [a] University School of Information, Communication and Technology, GGSIPU, Dwarka, Delhi, India
| [b] Department of Computer Science, Bhagwan Parshuram Institute of Technology, Delhi, India
| [c] Bharati Vidyapeeth’s College of Engineering, Paschim Vihar, Delhi, India
Correspondence:
[*]
Corresponding author. Puneet Singh Lamba, University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha University, Sector 16 C, Dwarka, Delhi 110078, New Delhi, India. Tel.: +91 9810907138; E-mail: [email protected].
Abstract: Eye blink is a semi-autonomic rapid closing of eyelid. Eye blink is controlled by the autonomic nervous system of human brain. This normal and most important function of human eye can be embedded with some created (abnormal) sequences to indicate any unusual message. In this paper, a real time novel algorithm to reckon number of eye blinks (RTREB) in a video sequence using eye facet correlation (EFC) is proposed. The proposed RTREB approximates the eye landmark positions using EFC- an extricate variable value of eyelids clearly differentiating between opened and closed eyelid in a frame of a video sequence. The proposed RTREB is classified with existing classifiers SVM, QSVM, KNN and DTREE. Increased accuracy to 99.8% validates the effectiveness and correctness of RTREB.
