Page 194 - Algorithm Collections for Digital Signal Processing Applications using MATLAB

184 Appendix

Figure 1-21 Relationship between the crisp value and fuzzy membership

for the input variable Y in the example
Figure 1-22 Relationship between the crisp value and fuzzy membership
for the input variable Z in the example

Figure 1-23 Defuzzification in the example
Figure 1-24 Illustration of Ant colony
Figure 1-25 Matrix A (Ant colony)
Figure 1-26 Matrix B (Ant colony)
Figure 1-27 Iteration (vs) Best cost selected by the 4 ants
Figure 2-1 Clustering example with four clusters
Figure 2-2 Illustration of K-means algorithm
Figure 2-3 Data along with the final centroids obtained by k-means
algorithm
Figure 2-4 Illustration of Fuzzy k-means algorithm
Figure 2-5 Data and the final centroids obtained using Fuzzy k-means
algorithm
Figure 2-6 Illustration of change in the membership value in every
iteration
Figure 2-7 Illustration of Mean and Variance Normalization of the
speech signal

Figure 3-1 Hotelling transformation for binary image rotation
Figure 3-2 Vector space along with Eigen vectors
Figure 3-3 Vector space after KLT and the corresponding eigen vectors
Figure 3-4 Projection Illustration
Figure 3-5 Projection of the vector on the plane
Figure 3-6 Gram-Schmidt Orthogonalization procedure
Figure 3-7 Original signal used for Haar decomposition
Figure 3-8 Approximation co-efficients obtained using Haar
transformation
Figure 3-9 Detail co-efficients obtained using Haar transformation
Figure 3-10 Illustration of Inverse Haar transformation
Figure 3-11 Original signal used for Daubechies 4 wavelet
decomposition
Figure 3-12 Approximation co-efficients at different levels
Figure 3-13 Detail co-efficients at different levels
Figure 3-14 Illustration of Inverse Daubechies 4 transformation
Figure 4-1 Sample Ear images before and after
normalization
Figure 4-2 Eigen Ears corresponding to the largest
Eigen values