EMOTION RECOGNITION USING DCT AND GABOR WAVELET

ADVANTAGES
1.DCT does a better job of concentrating energy into lower coefficients
2. it has properties of decorrelation ,energy ,compactionand separatibility
DISADVANTAGE
1.sensitive to changes in illumination direction
2.correlation from pixel of neighbouring block is neglected
3. The dimension of feature vector obtained from Gabor filter is very huge so
the time for performing Gabor feature extraction is very
high.
MEASUREMENT
When we apply the DCT for feature extraction from the
N*N image then we get a 2D coefficient matrix in this
matrix high frequency components are located at the top
left corner of the matrix and the low frequency
component are located at the bottom right corner of the
matrix. And for the coefficient selection static coefficient
selection approach is used in this approach zigzag
scanning
The advantage of a gabor filter are concentration on
important components of face such as eyes, nose, mouth
etc.gabor features are invariance to
illumination,rotation,scale and transform and have
optimal localization property in frequency and spatial
domain. But the disadvantage is not to represent fac

EMOTION RECOGNITION USING GABOR WAVELET AND LPB
Advantages
1.lpb captures small appearance details while gabor feature encodes facial shape over a
Broad range of scales
DISADVANTAGES
1.both feature sets are high dimensional to avoid this we run dimension redsuction
Techniques such as (pca) principal componenet analysis and (NMF)

EMOTION recognition using active appearance model(aam)
advantages
1.active appearance model enables us to effectively and efficiently update the model
parameters
2.it is used to overcome large variation in shape and texture that human face presents
Namely deformation and illumination changes
Diasadvantages
One of the main drawbacks of the approach is the amount of labelled training
examples required to build a good model. These can be very time consuming

Measurements
In face recognition application, accurate face alignment has determinative effect. Active
Appearance Model (AAM) is one of the most studied methods for accurate locating objects.
When applying Active Appearance Model, firstly we collect enough face images with various
shapes as training set. Then we use a set of points to annotate face shape, so face shape can
be represented by the coordinates of these landmarks

WHY LPB IS BETTER
1.DUE TO ITS TOLERANCE OF ILLUMINATIONAL CHANGES
2. DUE TO ITS COMPUTIONAL SIMPLICITY
3. IT IS MORE DISCRIMINATIVE


MEASUREMENT
The LBP feature vector, in its simplest form, is created in the following manner:
Divide the examined window into cells (e.g. 16x16 pixels for each cell).
For each pixel in a cell, compare the pixel to each of its 8 neighbors (on its left-
top, left-middle, left-bottom, right-top, etc.). Follow the pixels along a circle, i.e.
clockwise or counter-clockwise.
Where the center pixel's value is greater than the neighbor's value, write "1".
Otherwise, write "0". This gives an 8-digit binary number (which is usually
converted to decimal for convenience).
Compute the histogram, over the cell, of the frequency of each "number"
occurring (i.e., each combination of which pixels are smaller and which are
greater than the center).
Optionally normalize the histogram.
Concatenate (normalized) histograms of all cells. This gives the feature vector for
the window.
The feature vector can now be processed using the Support vector machine or some
other machine-learning algorithm to classify images. Such classifiers can be used for
face recognition or texture analysis.