• Sneha M
• Kirthika K M
• Sanjay M
• Sri Hari Raj R

Video-conferencing systems were invented for the purpose of long-distance communication and have become widely accessible due to the Internet and the growth of electronic devices such as PCs. However, the problem of the face of the user not being aligned correctly in a conference still requires a solution. Many facial analysis tasks like detection or recognition can be used to rectify this fault. These tasks require the use of facial landmarks. Media Pipe, a Machine Learning-based framework can generate landmarks and can perform these tasks. In this article we propose a simple solution which is based on using the media pipe framework, which tracks the movements of the iris and gives helpful alerts to improve the subjective feeling of eye contact.

Machine Learning, Graphics Processing Unit, Single Shot Detector Application Programming Interface Exchangeable Image File Format Computer Vision

"EYE CONTACT MAINTENANCE IN VIDEO CONFERENCES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.g543-g549, May-2022, Available :http://www.jetir.org/papers/JETIR2205762.pdf

"EYE CONTACT MAINTENANCE IN VIDEO CONFERENCES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppg543-g549, May-2022, Available at : http://www.jetir.org/papers/JETIR2205762.pdf