• RAJAPRABU A
• GEETHA A

Estimation of eye gesture recognition is useful in various human-computer interaction tasks. We propose a framework for the classification of eye gestures. In the first stage, the algorithm detects face, and from the detected face, eye regions are detected using Haar-cascaded classifiers. A Convolutional Neural Network is employed in this work for the classification of eye gestures. The detected eye-gesture frames are recognized as eye-close, eye-left and eye-right. This proposed work will be usefull in developing hands-free computer interfaces to replace the traditional input devices to create an intelligent Human-Computer Interaction and also usefull in Medical applications,Gaming and Robotic research. The proposed system has been tested and performance analysis is carried out for the model.

Human Computer Interaction, Eyegestures, Haar-cascadedclassifiers, Convolutional Neural Network, Robotic research.

"Eye Gesture Classification using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.535-540, December-2018, Available :http://www.jetir.org/papers/JETIR1812B68.pdf

"Eye Gesture Classification using Convolutional Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp535-540, December-2018, Available at : http://www.jetir.org/papers/JETIR1812B68.pdf