G.H. Raisoni College of Engineering & Management, Amravati

SEMINAR ON

HUMAN-MACHINE INTERACTION USING HAND

GESTUREPresented by

Mr. M.D. HarsuleM.E.(II year -Electronics & Telecommunication)

GUIDED BY Dr. P.V. Ingole

(Principal, G.H. Raisoni College of Engineering & Management, Amravati)

INTRODUCTION:Hand gestures recognition (HGR) is one of the main

areas of research for the engineers, scientists and bioinformatics. HGR is the natural way of Human Machine interaction and today many researchers in the World are working on different application to make interactions more easy, natural and convenient without wearing any extra device.

If by using HGR there is interaction between Human and computer further HGR can be used to control various equipments or can be used to instruct a computer.

Software Used MATLAB R2010a Embedded C

Camera Nowadays Digital cameras are easily

available and cheaper device

Image processing became a convenient method for applications

Microcontroller based Home appliances switching system

Hardware Requirements

Application Architecture Design

Train set: Some training sets of images, each one

containing three or more images. Each set originates from a single image for

testing.Test Set: From databases and they can be tested

extensively Feature extraction is very important

Parts of Commands

Image Processing

Step1 The first thing for the program to do is to

read the image database. A for loop is used to read an entire folder

of images and store them in MATLAB’s memory.

The folder is selected by the user from menus.

A menu will firstly pop-up asking user whether he want to run the algorithm on test or train sets

Algorithm of Image detection

Step2 Resize all the images that were read in

Step1 to 150x140 pixels. This size seems the optimal for offering

enough detail while keeping the processing time low.

Algorithm Continuous….

Step3. to find the edges. For that filters may be used feature extracted from the images it had to

offer enough discrimination among them operators threshold values and some other

parameters can be set as well

Algorithm Continuous….

Step 4 Dividing the two resulting matrices

(images) dx and dy element by element taking the atan ( tan−1 ). This will give the

gradient orientation

Algorithm Continuous….

Step 5 Then the MATLAB function im2col is called

to rearrange the image blocks into columns.

This is not a necessary step Using because want to display identified

gesture

Algorithm Continuous….

Step 6 Converting the column matrix with the

radian values to degrees. This way we can scan the vector for values

ranging from 0ο to 90ο . This is because for real elements of X, atan(X) is in the range -180 to +180.

At the same time we are using the neural network itself as this vector would be the input to the network. The smaller the vector the faster the processing.

Algorithm Continuous….

Thanks