Scribd
Upload
6 views23 pages

Fuzzy Techinique For Intensity Transformation and Spatial Filter

Uploaded by

worku
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
6 views23 pages

Fuzzy Techinique For Intensity Transformation and Spatial Filter

Uploaded by

worku
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

Adama Science And Technology University

School of Electrical Engineering and Computing


Department of Computer Science and Engineering
Section-1, Group-2
Title:- Fuzzy Techniques for Intensity
Transformations and Spatial Filtering
prepared by
Name ID
Milki Dida Wodajo pgr/38320/17
Mubarek Ahmed Hussen pgr/38322/17
Tamirat Mulu Beressa
pgr/38325/17
Tigist Dereje Aweta
pgr/38328/17
Yeabsra Habtu Kumlachew pgr/38331/17
Outline
Introduction
 Intensity Transformations
 Spatial Filtering

Membership Functions
- Triangular Membership Function
- Trapezoidal Membership Function
- Gaussian Membership Function
- Sigmoidal Membership Function
- Bell-Shaped Membership Functionction

Spatial filters
Conclusions
Introduction

• What are Intensity Transformations?


 Techniques to manipulate image intensity values for enhancement or
feature extraction.
 Examples include enhancing contrast, highlighting details, or correcting
brightness levels.
• What is Spatial Filtering?
 Methods that modify pixel intensity based on its spatial neighborhood.
 Examples include noise reduction, edge detection, and feature
smoothing.
Introduction....
Role of Fuzzy Techniques:
 Fuzzy Techniques are widely used in image processing to handle
uncertainty and improve image quality through adaptive intensity
transformations and spatial filtering.
 These methods adjust pixel intensities based on membership
functions to enhance image clarity.
 Useful in situations where precise boundaries and values are
difficult to define.
Objectives
Explain fuzzy membership functions
Explore fuzzy methods for intensity transformation.
Apply fuzzy spatial filtering for image enhancement
Demonstrate practical applications with Python.
Understand the integration of fuzzy logic in real-
world image processing tasks.

01/19/20
25
Membership Functions Overview
Fuzzy Membership Functions are mathematical functions that
represent the degree to which an element belongs to a fuzzy set.
Common membership functions include:
- Triangular Membership Function
- Trapezoidal Membership Function
- Gaussian Membership Function
- Sigmoidal Membership Function
- Bell-Shaped Membership Function

01/19/20
25
Membership Functions ....

01/19/20
25
Triangular Membership Function
• Formula:

• Parameters: a, b, c
• Triangular membership functions are simple and linear
functions commonly used in fuzzy logic, making them
easy to implement.
Trapezoidal Membership Function

• Formula:

• Parameters: a, b, c, d
• Trapezoidal functions are similar to triangular ones but
have a flat top, making them suitable for ranges of values.
Gaussian Membership Function

• Formula:

• Parameters: mean, sigma


• Gaussian functions are smooth and widely used for
continuous data, ideal for real-world data.
Intensity Transformation with Fuzzy Logic

• Fuzzy logic can be applied to adjust pixel intensities in an


image.
• Steps:
- Map input pixel intensities to fuzzy values.
- Apply membership functions.
- Convert back to pixel intensities.
Required Libraries

OpenCV: Library for image and video processing.


NumPy: For numerical and matrix computations.
 Matplotlib’s pyplot: for plotting images and visualizing data.
 Google Colab-specific import that allows us to interact with
local file system. The files module helps upload and download
files to and from the Colab environment.

01/19/20
25
Uploading Images
Uploading with Google Colab:
Allows easy interaction for image processing
tasks.
Use the following code to upload an image:
 from google.colab import files
 uploaded = files.upload()
Displays a file upload widget to select an
image.
01/19/20
25
Code Example: Intensity Transformation

def triangular_membership(x, a, b, c):


return max(0, min((x-a)/(b-a), (c-x)/(c-b)))

def apply_intensity_transformation(image, func, params):


transformed = func(image, *params)
return transformed
Spatial Filtering with Fuzzy Logic

• Fuzzy spatial filtering involves modifying pixel values


based on their neighbors.
• Common applications:
• - Smoothing (noise reduction)
• - Sharpening (edge enhancement)
Code Example: Spatial Filtering
def fuzzy_filter(image, kernel, membership_func):
filtered_image = np.zeros_like(image)
for i in range(image.shape[0]):
for j in range(image.shape[1]):
neighbors = image[i-1:i+2, j-1:j+2]
fuzzy_values = membership_func(neighbors)
filtered_image[i, j] = np.mean(fuzzy_values)
return filtered_image
Results Visualization
Display results using plt.imshow() and with some
decoration labels
Example Code:
plt.figure(figsize=(12, 8))
plt.subplot(2, 3, 1)
plt.imshow(image, cmap='gray')
plt.title('Original Image')
plt.axis('off') # Hide axis ticks

Result: Side-by-side Comparison of the original image


and the transformed image after applying fuzzy intensity
transformations and fuzzy spatial filtering.
01/19/20
25
Full Pipeline Overview

Steps to process an image:


1.Upload image via Colab.
2.Apply intensity transformations (using each membership
function).
3.Apply spatial filters (using each membership function).
4.Visualize the processed images.

01/19/20
25
Advantages of Fuzzy Techniques

• Flexible and adaptive


• Handles uncertainty in image processing
• Improves image quality without hard thresholds
• Suitable for a wide range of applications
Challenges of Fuzzy Techniques

• Computational complexity
• Subjectivity in defining membership functions
• Difficulties in selecting appropriate parameters
Applications
Medical Imaging: Enhance X-rays, MRIs, and CT
scans.
Remote Sensing: Extract terrain features from satellite
imagery.
Industrial Automation: Detect product defects and
edges.
Photography: Improve image clarity and noise
reduction.
01/19/20
25
Conclusion
Intensity transformations improve contrast and
detail visibility.
Spatial filtering removes noise and highlights key
features.
Fuzzy techniques significantly enhance image
processing capabilities by handling uncertainty and
improving image clarity
Fuzzy techniques significantly enhance image
processing capabilities.
01/19/20
25
Thank You!!!

01/19/20
25

You might also like