International Journal of Science and Research (IJSR) ISSN (Online): 2319-7064 Impact Factor (2012): 3.358 Volume 3 Issue 8, August 2014 www.ijsr.net Licensed Under Creative Commons Attribution CC BY Hand Gesture Recognition Application for Physically Disabled People D. Vishnu Vardhan 1 , P. Penchala Prasad 2 1 Assistant Professor, Department of ECE, JNTUA College of Engineering Pulivendula, Andhra Pradesh, India 2 PG scholar, Department of ECE, JNTUA College of Engineering Pulivendula, Andhra Pradesh, India Abstract: In the Proposed model, a communication system which converts signal languages, used by dumb people, Quadriplegia and paraplegia are disabilities that result from injuries to the spinal cord and neuromuscular disorders into speech. It is done based on a narrative hand gesture recognition technique. The solution approach consists of a hardware module and software module. In hardware module- The gesture recognition is done with the help of a sensor glove which consists of 5 accelerometer sensors, a microcontroller and that are best positioned in fingers upon analysis of American Sign Language Signs. The design of glove and the concept of decoding gestures by considering the axis orientation with respect to gravity and the corresponding voltage levels are discussed. The accelerations of a hand motion in three perpendicular directions are detected by accelerometers and acceleration values were transmitted to microcontroller. An automatic gesture recognition algorithm is developed to identify individual gestures in a sequence. As a final point, the gesture is recognized by comparing the acceleration values with the stored templates. According to recognized gesture, respective commands are played through speaker using voice chip. Keywords: MEMS Accelerometer, Microcontroller, Flux Sensor 1. Introduction Gesture recognition is the process by which gestures made by the user are used to convey the information or for device control. In everyday life, physical gestures are a powerful means of communication. A set of physical gesture may compose an entire language, as in sign languages. They can efficiently convey a rich set of facts and feelings. This project makes the modest suggestion that gesture-based input is such a beneficial technique to convey the information or for device control with the help of identification of specific human gesture Research into the uses of gesture in human computer interaction is embryonic, and we hope to have stimulated others to work out their ingenuity in developing effective gestures. A primary goal of Gesture recognition research is to create a system which can identify specific human gestures and use them to convey information or for device control. Interface by computers using gesture of the human body, classically hand movements. In gesture recognition technology, a camera reads the actions of the human body and communicates the data to computer that uses the gestures as input to control devices or applications. Gesture recognition is a topic in computer science and language technology with the goal of interpreting human gesture via mathematical algorithms. Gesture can create from any physical motion or state but commonly originate from the face or hand. Current focuses in the field contain emotion recognition from the face and hand gesture recognition. Several approaches have been made using cameras and computer vision algorithms to interpret sign language. Through, the identification and recognition of posture, proxemics, gait, and human behaviours is also the subject of gesture recognition techniques. 2. Proposed Model To overcome the limitations such as unexpected ambient optical noise, slower dynamic response, and relatively large data collections/processing of vision-based method, and to strike a balance between accuracy of collect data and cost of devices , a micro Inertial Measurement Unit is utilized in this project to detect the accelerations of hand motions in three dimensions. The proposed recognition system is executed based on MEMS acceleration sensors. Since bulky computation burden will be brought if gyroscope are used for inertial dimension, our current system is based on MEMS accelerometers only and gyroscope are not implemented for motion sensing Figure 1: shows accelerometers architecture of the proposed gesture recognition system based on MEMS accelerometer. The details of the individual steps are described below. The sensing device sense acceleration in three axes. Those sensed signals are restriction and given to the controller circuit. The controller balances the incoming signal values with the pre-stored values. Commands for each gesture were separately allotted to each channel in the voice chip. When the incoming acceleration value matches with pre-stored one corresponding channels will be enabled and the command be displayed. The same be played through the speaker after amplification since the signal from voice chip is very low. Figure 1: Proposed System 3. System Description The system is intended and built using the flex sensor, MEMS, PIC16F88 Micro controller. Our sensing device produces the analog values corresponding to the acceleration of three axes. Acceleration values for the eight gestures were placed in the lookup table in controller. Each incoming gestures values for all three axes be compared with every axis value in the table. The tolerance level for each axes Paper ID: 07081401 765