Implementation of 3D Hand Gesture Recognition System using FPGA

In this paper, a VLSI design with dual-camera to construct the depth map and recognize hand gestures was proposed. The proposed system adopts adaptive depth filter which can separate foreground to segment the interesting object under complicated environment. We also proposed dynamic gesture recognition by using depth and coordinate information. The system contains one static gesture and two dynamic gestures and has been implemented in FPGA and the average accuracy with each gesture is 83.98%.