 # Image Fusion Technique Based on PCA and Fuzzy Logic Part 2 Essay

Decent Essays
mage fusion based on fuzzy sets
The fuzzy logic approach is widely used in image process-ing. The fuzzy logic gives decision rules and fusion motivation for image fusion . the two inputs images are converted into membership values based on a set of predefined MFs, where the degree of membership of each input pixel to a fuzzy set is determined. Then, the fusion operators are applied to the fuzzified images. The fusion results are then converted back into pixel values using defuzzification.
1) Fuzzy sets: The fuzzy sets are used to describe the gray levels of the input images. we have two inputs and one output. the two inputs are ; the first input is the Pan image and the second input is the first principal component( PC
1
) of the MS
The Mamdani fuzzy inference is widely used in applications, because of it has the simple structure of defuzzification method Mamdani type min-imum sum mean of maximum which is used.Defuzzification refers to the way a crisp value is extracted from a fuzzy set as a representative value. The fuzzy rules in the form IF-THEN is used .The If-Then type fuzzy rules converts the fuzzy input to the fuzzy output.
These rules are designed in the form of combination of inputs (Pan and pc
1
) represents as : (z) = max(x;y) =)fL;M!Mg (11) where x and y represenst pixel gray level values of Pan and
PC
1 images respectively.The meaning of equation (11) that the pan gray level is low and the gray level of pc
1
is meduim then the gray level of the fused image is meduim. we have 25 rules to fuse the pan image and PC
1
we summerize as following :
TABLE I
FUZZY RULES OF IMAGE FUSION FUZZY LOGIC
VL L M H VH
L L M H VH
M M M H VH
H H H H VH
VH VH VH VH VH
The algorithm of image fusion by using fuzzy sets is implemented as the following:
Algorithm 2fuzzy logic image fusion algorithm
1: Input: M1 and M2
2: read first image in variable M1 ( Pan image) and calculate its size (rows : m1 and columns: n1)
3: read second image in variable M2 ( PC
1
); and calculate its size (rows : m2 and columns: n2)
4: M1and M2 Variables are images in matrix form where each pixel value is in the range from 0-255.
5: Compare the size of both input images. If the two images are not of the