Real Time Interface for Assistive E-Learning
Indhumathi R1, Geetha A2

1Indhumathi R, Research Scholar, Department of Computer and Information Science, Annamalai University, Annamalai Nagar, (Tamil Nadu), India.
2Geetha A, Associate Professor, Department of Computer Science and Engineering, Annamalai University, Annamalai Nagar, (Tamil Nadu), India.
Manuscript received on 03 June 2019 | Revised Manuscript received on 07 June 2019 | Manuscript published on 30 June 2019 | PP: 2434-2439 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7386068819/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Assistive system is any hardware or software designed to enable independence for disabled and older people. Technologies are growing up day to day. The disabled and elder people find very difficult to adopt new technologies. It is important to develop effectively available systems to accomplish their incorporation inside the new advances. Many researches are ongoing in assistive technology. This proposed work is concentrated on Assistive human computer interface. Nowadays technology has been improved in many areas particularly in learning. Everyone likes E-Learning i.e. learning by using electronic media. Basically two types of materials are used in E-Learning they are learning by video and learning by text reading. Our aim is used to create an application for effective Assistive E-Learning. The head gestures are used instead of traditional input devices. This work recognizes head gestures in real time to create a head interface between user and computers. It helps to automatically operate the applications such as click, scroll up and scroll down. The Haar cascaded classifier with rotation invariant approach is used to detect head gestures. The detected gestures are recognized as head-left, head-right, head-origin and head-down using Random Forest and Decision Tree. The proposed system has been tested in real time with adobe reader and performance analysis is carried out. The system is found to outperform other existing methods.
Keywords: Assistive Technology, Head Gestures Detection, Haar Cascaded Classifier, Random Forest, Decision Tree, E-Learning.

Scope of the Article: E-Learning.