Real Time Static Hand Gesture Recognition System Using Hci For Recognition Of Numbers

Main Article Content

Prof J.R. Pansare
Jay Shrotriya, Rahul Durrani, Sonam Jaisinghani

Abstract

In this paper, we introduce a static hand gesture recognition system to recognize numbers from 0 to 9. This system uses a single camera
without any marker or glove on the hand. This work proposes an easy-to-use and inexpensive approach to recognize single handed static gestures
accurately. The system helps millions of deaf people to communicate with other normal people. It describes a hand gesture recognition system
(HGRS) which recognizes hand gestures in a vision based setup that includes capturing an image using a webcam. It is mainly divided into the
following stages: image capturing, image pre-processing, region extraction, feature extraction and matching and gesture recognition. The image is
first captured in RGB format. The image pre-processing module transforms the raw image into the desirable feature vector which mainly includes
converting the colour images into the HSV images and reducing noise. The region extraction module extracts the skin region from the whole image
and eliminates the forearm region giving the region of interest. The feature extraction module extracts a set of distinct parameters to represent each
gesture and distinguish the different gestures. Finally the features are matched and the corresponding gesture is recognized. 100 images for each hand
gesture representing different numbers are used to train the system and then it is tested for a different set of images. Images for the training set are
taken, keeping the hand at a distance of 15 inches from a 720p HD web camera.


Keywords: Region Extraction, Feature extraction, Histogram, Euclidean Distance, Gesture recognition

Downloads

Download data is not yet available.

Article Details

Section
Articles