ritwikraha

ritwikraha

ritwikraha

ritwikraha

for id = 1:32
	sdata = load(strcat('s',num2str(id),'.mat'));
	sdata = sdata.data;
	slabels = load(strcat('s',num2str(id),'.csv'));
	[~,idx] = sort(slabels(:,2));
	sortedlabels = slabels(idx,:);
	sorteddata = sdata(idx,:,:);

ritwikraha

ritwikraha

import cv2
import numpy as np
import dlib

cap = cv2.VideoCapture(0)

detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")

while True:

ritwikraha

ritwikraha

%Applying bandpass filter to filter out the unwanted signal <4 and >30Hz
yy1=bandpass(SSS1,[4 30],128);
%Apply DWT at 5 level of decomposition
waveletFunction = 'db2';
[C,L] = wavedec(yy1,5,waveletFunction);
cD11 = detcoef(C,L,1);                   
cD21 = detcoef(C,L,2);                  
cD31 = detcoef(C,L,3);                   
cD41 = detcoef(C,L,4);                  
cD51 = detcoef(C,L,5);                  

ritwikraha

se = strel(3,3);
basic_gradient = imdilate(I,se)- imerode(I,se);
external_gradient= I-basic_gradient;
peakpsnr = psnr(external_gradient,I);

ritwikraha

% plotting the power spectral density of the image available
% using the psd plot to obtain further information
psd = imagesc(log10(abs(fftshift(fft2(I))).^2))
mesh(psd);