Eye Blink and Hand Gesture detection For Aid of Paralyzed Patients
Ashutosh Mishra#, Aves Momin*, Akash Nirala^, Prof. Vaishali Yeole
Computer department
Smt. Indira Gandhi College of Engineering
(University of Mumbai)
Navi Mumbai, India
Abstract— Paralysis is the Absolute loss of muscle function in any part of the body. It usually happens when there is Issue with the passage of messages among the muscles and the brain. Some paralyzed people aren’t able to move their single part of the body except eyes. Hence, the main aim of this project is to make a real time interactive system that can assist the paralyzed by giving commands to control appliances such as lights, fans etc. Various Image processing approaches have been performed in order to detect the eye blinks. In this system, the face tracking is accomplished by using a set of trained Haar cascade classifiers, and . In this system hand gesture is also given for patient convenience in which a flex sensor is used which works on the principle of change in the internal resistance and to detect the angle made by the user’s hand at any given time. The flexes made by hand in different combinations amount to a gesture and this gesture can be converted into a text display to aid paralyzed patients.
Keywords: Computer Vision, Internet of Thing, Hand Gesture
I..INTRODUCTION
Paralysis can be defined as complete loss of muscle functionality for either 1 or more muscle groups. Paralysis Could cause loss of feeling or Function in the affected areas. Paralysis Could be localized and generalised based on type, or it could follow a specific Pattern in Patients. Most paralysis is caused due to damage in nervous system are Constantly Occurring in nature; however Various forms in periodic paralysis are there, Paralysis is most often caused by damage to the nervous system, especially the spinal cord. Major causes of paralysis are stroke, trauma along with nerve injury. According to the survey by Christopher and Dana Reeve foundation, Almost one in every fifty people are paralyzed . Fully paralyzed patients may need 24-hour support. But in the present day and age, it is not possible for anyone to be available at all times. So, in those situations where the patient is alone in a room, he/she could use help if required Such as switch on/off a light, a fan or any other appliance.
Hence, our Project Paral-Eye will help the patient to be self-sufficient to a certain Level. There are Various applications which can be Done Using from eye blink detection and these aren’t limited for usage by only paralyzed Patients. An efficient, real time blink detection algorithm can be used for Various purpose. Paral-eye can be used for Operating on/off appliances such as a television or a microwave oven.. All this can be accomplished with just a very less eye blinks. Various Ways have been devised for face tracking.CamShift Facial tracking Haar face Cascade algorithm and face tracking using Eigenface are some of these. There are techniques Used for blink detection as well. Some of them are software based i.e by using image processing, and a few are hardware-oriented using sensors. Various image processing techniques includes blink detection using the contour extractions, Gabor filter, and eye blink detection using Median blur filtering.
The Aim of this paper is to propose a system that will assist the paralyzed patient along with other types. It does so by tracking the person’s eye and counting the blinks and also using hand gestures,which employs this count to control various appliances and play pre-recorded audio messages. Although a number of studies have been implemented for eye blink detection, there are no applications which are Created to actually use the blink detection to practical Use.The principal contribution of this paper is the conceptualization of a system which will help the paralyzed and disabled to achieve some level of Functionality . Moreover, the algorithm provided by has been improved by implementing face tracking, so as to reduce the effect caused by movements in the background.
eye-blink-hand-gesture-detection
FREE DOWNLOAD
@ engpaper.com published paper
PUBLICATION PROCEDURE WITH US ENGPAPER.COM
ENGPAPER.COM PUBLISHED PAPERS