08-17-2017, 12:45 AM
source code for eye gaze detection in matlab
Facial expressions convey non-verbal cues, which play an important role in interpersonal relations. Automatic recognition of facial expressions can be an important component of natural human-machine interfaces; it may also be used in behavioural science and in clinical practice. Although humans recognise facial expressions virtually without effort or delay, reliable expression recognition by machine is still a challenge. We have developed a fast and efficient algorithm for facial expression recognition. The algorithm consists of three main stages: eye region locating stage, the eye detection stage and feature vectors extraction. In the first stage, an effective approach to fast location of the eye region is developed. In the second stage, eye edge contour searching directed by knowledge is introduced in detail. Regional image processing techniques are also described in the second stage. The main purpose of the first stage is to locate the eye region roughly. The algorithm employed in the second stage is restricted to application in just this region. It reduces the complexity of the first stage and improves the reliability in the second stage. Expression representation can be sensitive to translation, scaling, and rotation of the head in an image. To combat the effect of these unwanted transformations, the facial image may be geometrically standardised prior to classification. This normalisation is based on references provided by the eyes. Once eye regions has been detected, in the third stage an invariant coordinate system is generated and extracted feature vectors are used to train a neural network.
%
% Purpose : Find distinct points of the Pupils, Nostrils and Mouth in
% images taken from a video stream to get the Pupils' position in relation
% to the fixed position of Mouth and Nose
%
% A video input adaptor (webcam) has to be connected to the computer in
% order to run this program
%
% Author : Peter Aldrian, Uwe Meier, Andre Pura
% Date : August 12, 2009
% Version : 1.0
% --
% © 2009, Meier, University of Leoben, Leoben, Austria
% email: [email protected] [email protected] [email protected]
% --
close all;
clear all;
% set length of video stream (if set to 'inf' stop video by closing figure
frames = 100
% starting routine for video input
% Image Acquisition Toolbox has to be installed
vid=videoinput('winvideo',1,getResolution());
triggerconfig(vid,'manual');
set(vid,'ReturnedColorSpace','rgb' );
start(vid);
% start figure; for display purpose only
scrsz = get(0,'ScreenSize');
fig = figure('CloseRequestFcn',{@my_closereq,vid},'Position',scrsz);
for jj = 1 : frames
% get snapshot from video device
snapshot = getsnapshot(vid);
% delete this two lines after downloading the
% haarcascade_frontalface_alt2.xml -File
disp('Because of license restrictions you have to download the file "haarcascade_frontalface_alt2.xml" on your own.');
disp('Just google it or download it at http://mathworks.de/matlabcentral/fileexchange/19912.');
% main routine to detect distinct points for the eyes, nose and mouth
[T] = getPoints(snapshot);
% displaying snapshot and found points; for display purpose only
if T =-1
imshow(snapshot,'InitialMagnification','fit');
hold on;
for i=1:2:9
plot(T(i),T(i+1),'ro');
plot(T(i),T(i+1),'gx');
end
else
imshow(snapshot);
end
% pause needed, so matlab can draw figures;for display purpose only
pause(0.05);
hold off;
end
% stops video input
stop(vid);