Image Fusion

1
Image Fusion

• A Fuzzy Logic Approach
• By
• Ajit K. Pandey
• Cpe 521
• Instructor Dr. Powsiri Klinkhachorn

2
Introduction to Image fusion

• Image Fusion deals with combining different
  sources of information.
• The information are signals delivered by
  different sensors and images from various
  modalities.
• The fusion concepts and methods gather tools like
  weighted average, neural networks, sub-band
  filtering, and rules based knowledge.
• Fuzzy Logic and graph Pyramid methods recently
  find applications in Image Fusion.

3
Evolution Of Image fusion

• Simple image fusion attempts
• Pyramid-decomposition-based image fusion
• Wavelet-transform-based image fusion
• Pixel Based Image Fusion

4
Applications of Image Fusion

• Image Fusion has become a topic of great interest
  to a variety of engineers working in different
  disciplines.
• It is being used for medical applications.
• It's also being researched in automotive
  industries to enhance the vision of road so as to
  see a better image during a rainy or a foggy
  weather.

5
Image fusion examples

• Multi-focus image fusion
• Digital camera application
• Concealed weapon detection
• Battle field monitoring

6
Why Fuzzy?

• Fuzzy approaches are used where there is
  uncertainty and no mathematical relations are
  easily available.
• It improves the reliability by taking care of the
  redundant information.
• It improves the capability as it keeps
  complementary information.

7
Concept

• I propose the use of Fuzzy approach for pixel
  level image fusion.
• This approach forms an alternative to a large
  number of conventional approaches, which are
  based on a host of empirical relations.
• Empirical approaches are time consuming and
  result in a low correlation.

8
Algorithm for Pixel level Image fusion

• Read first image in variable M1 and find its size
  (rows z1, columns S1).
• Read second image in variable M2 and find its
  size (rows z2, columns s2).
• Variables MI and M2 are images in matrix form
  where each pixel value is in the range from
  0-255. Here we are using Gray Color map.
• Compare rows and columns of both input images. If
  the two images are not of the same size, select
  the portion which are of same size.

9
Algorithm contd

• Convert the images in column form which has
  Cz1s1 entries.
• Make a fis (Fuzzy) file, which has two input
  images.
• Decide number and type of membership functions
  for both the input images by tuning the
  membership functions. Input images in antecedent
  are resolved to a degree of membership ranging 0
  to 255.
• Make rules for input images, which resolve the
  two antecedents to a single number from 0 to 255.

10
Contd

• For num1 to C in steps of one, apply
  fuzzification using the rules developed above on
  the corresponding pixel values of the input
  images which gives a fuzzy set represented by a
  membership function and results in output image
  in column format.
• Convert the column form to matrix form and
  display the Fused Image.

11
Example

• Figure shows the two images of the same object
  from to different sources.
• remoteA and remoteB are taken as the two input
  images to be fused.
• Each image is stored as a matrix that contains
  their pixel values in the range of 0 to 255.

12
Output Image

• Finally we get the fused image from the Fuzzy
  based Image fusion system as shown

13
Outcome

• Fuzzy algorithms have been implemented to fuse a
  variety of images. The results of fusion process
  proposed are given in terms of Entropy and
  Variance.
• The fusions have been implemented for medical
  images and remote sensing images.

14
Summary

• Image fusion deals with integrating data obtained
  from different sources of information for
  intelligent systems.
• The two images of the same object from different
  sources are fused using fuzzy algorithm.
• Fusion provides output as a single image from a
  set of input images.
• Empirical approaches are time consuming and
  result in a low correlation.
• The military applications include automated
  target recognition, battlefield surveillance,
  intelligent mobility, etc.

15
Thank you