You are on page 1of 1

ABSTRACT

This project titled “Gesture recognition using FPGA” implements

a system that can recognize hand gestures from a live video stream. The

gestures are captured using a digital camera. The analog output of the

camera is digitized using a Video Decoder Board which is a carrier for

the ADV7183B. It digitizes the received stream into a 4:2:2 YCrCb

format. The digitized outputs obtained are fed to the Virtex II Pro FPGA

kit. From the received video stream, the Luma components are extracted

and stored in the BRAM. Edge detection is performed using Sobel

operator and the feature vectors of the image are computed and

compared with the reference values in order to identify the gesture. As

an application of the system, a windows manager is implemented

wherein a user can essentially close, open and move windows using

hand gestures.

ii

You might also like