[Dokhe, 4(6): June2015] ISSN: 2277-9655 (I2OR), Publication Impact Factor: 3.785 http: // www.ijesrt.com© International Journal of Engineering Sciences & Research Technology [560] IJESRT INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY GESTURE RECOGNITION BASED AC MOTOR SPEED CONTROL Miss. Dokhe Anita Dattatraya * , Prof. N. D. Kapale, Dr. D. N. Kyatanavar Department of E&TC, SRESCOE, Maharashtra, India ABSTRACT For increasing/decreasing the ceiling fan speed or for switching the lights ON/OFF mostly we need to get up and move towards the switch board. But the ones who are physically impaired, it’s difficult for them to do so. This system is targeted mainly to help people who are physically impaired& unable to operate the switch board easily for controlling the ceiling fan speed & turning the lights ON/OFF. It’s also possible to control these electronic equipment with the help of wireless technique like remote control. But the problem here is, due to different physical shapes of device and a variety of functional commands that each remote control features gives rise to numerous problems: the required remote control locating difficulties, the button layout confusion, the device replacement issue and so on. The proposed model for AC motor speed control of ceiling fan based on image processing is a recent innovative user interface that resolves the complications of using numerous remote controls for domestic appliances. Using one unified set of hand gestures, this system can interpret the hand gestures of user into pre-defined commands to control one or multiple devices at the same time. The experimental results are highly encouraging as the system is able to produces real-time responses and accurate recognition towards various set of gestures to perform the respective task. KEYWORDS: Firing Angle, Feature Extraction, Gesture Recognition, Image Processing Techniques, Segmentation, SIFT. I. INTRODUCTION Until now, Hand Gesture Recognition technology is implemented with the help of “Data Gloves” or “Color pins” which leads to increase in cost and the availability of these devices among majority of masses is negligible. Also, the use of additional devices increases the maintenance cost. Today to get a webcam is a very easy task, since it’s available easily in the market. In our project, we have implemented a hand gesture recognizer as shown in Fig. 1 which is capable of detecting a hand gesture, where webcam is used as an input device. In future, instead of using regulator or remote control for interacting with machines, it will be more comfortable and natural approach for us to communicate with bare hands without the interaction of any mediator. As a result of discussion until now, hand gesture recognition is asatisfactory solution, instead of using devices like Fig. 1 Hand Gesture Recognition System regulators, remote control & mechanical switches as input devices. Since, for gesture processing & recognition low power to process is required, which seems to be useful for simple consumer control devices. In image processing based hand gesture recognition system, the hand gesture is recorded by video camera. Then this input video is decomposed in such a way that we are able to extract the required set of features from the acquired image. The hand is separated from the background by using image processing technique. The separated handis recognized for different postures. Since, as we know a sequence of hand poster which is connected by continuously changing motions forms a gesture. Here a recognizer needs to be trained by using something called as grammar. The hand gesture is nothing but building up from the group of hand postures in various composition, just like a group of words make a phrase. The recognized gestures is used to drive applications like household appliances. The image processing technique for gesture recognition process can be decomposed into three main stages as follows:  Acquired image preprocessing and segmentation,  Feature extraction& classification, and