Smart Electronic Switching (ON/OFF) System Based on Real-time Detection of Hand Location in the Video Frames

Abstract

Human looking forward to living in a modern and comfortable environment like smart houses. In this study, an effective user-friendly smart home prototype designed with low cost. The prototype contains eight of Light Emitting Diode (LED) considered as home appliances and controlled in real-time using eight suggested hand cases. The hand cases have different position regarded to head and shoulder levels. The hand position is detected using a new suggested algorithm programmed in Matlab software. Viola-Jones method used to detect hand in a complex background (hand with a different background) by training computer using positive (hand) and negative (non-hand) image datasets. To make computer training faster and accurate, a new idea depends on a skin detection used before computer training to determine the location and size of all positive images automatically. The LEDs in prototype switched ON/OFF using the suggested hand cases in a fast time. Where the response time of LEDs to hand cases was 0.43 second.