10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook

Write a program to improve contrast of an image using histogram equalization. The

prototype of the function is as below: histogram_equalisation(input_Image,
no_of_bins); The function should return the enhanced image. Consider two low
contrast input images. Study the nature of the output image quality in each case by
varying the number of bins.

localhost:8888/notebooks/DIP/Assignment - 7.ipynb 1/6

10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook

localhost:8888/notebooks/DIP/Assignment - 7.ipynb 2/6

10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook

In [29]: import cv2

import numpy as np
import matplotlib.pyplot as plt
import os
​
def histogram_equalisation(input_image, no_of_bins=256):
"""Performs histogram equalization on a grayscale image.
​
Args:
input_image: The input grayscale image as a NumPy array.
no_of_bins (int, optional): The number of bins to use in the histog
​
Returns:
numpy.ndarray: The equalized image as a NumPy array.
​
Raises:
ValueError: If the input image is None.
"""
​
if input_image is None:
raise ValueError("Input image is None. Check if the image file path

hist, bins = np.histogram(input_image.flatten(), no_of_bins, [0, 256])

​
cdf = hist.cumsum()
​
cdf_normalized = cdf * hist.max() / cdf.max()
​
cdf_m = np.ma.masked_equal(cdf, 0)
​
cdf_m = (cdf_m - cdf_m.min()) * (no_of_bins - 1) / (cdf_m.max() - cdf_m
​
cdf = np.ma.filled(cdf_m, 0).astype('uint8')
​
input_image_normalized = np.interp(input_image.flatten(), bins[:-1], np
​
enhanced_image = cdf[input_image_normalized.astype('uint8')].reshape(in
​
return enhanced_image
​
def plot_histograms(image, title):
"""Plots the histogram and image for a given title.
​
Args:
image: The image as a NumPy array.
title (str): The title for the plot.
"""
​
plt.figure(figsize=(10, 4))
​
plt.subplot(1, 2, 1)
plt.imshow(image, cmap='gray')
plt.title(f'Image: {title}')
plt.axis('off')
​
plt.subplot(1, 2, 2)
plt.hist(image.flatten(), 256, [0, 256], color='r')
plt.title(f'Histogram: {title}')
plt.show()
​
image1_path = r'C:\Users\DELL\OneDrive\Pictures\7th sem 4-1\DIP\image1.7'
localhost:8888/notebooks/DIP/Assignment - 7.ipynb 3/6
10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook
image2_path = r'C:\Users\DELL\OneDrive\Pictures\7th sem 4-1\DIP\image2.7'
​
if not os.path.exists(image1_path):
raise FileNotFoundError(f"File {image1_path} not found. Please check th
​
if not os.path.exists(image2_path):
raise FileNotFoundError(f"File {image2_path} not found. Please check th
​
image1 = cv2.imread(image1_path, 0)
image2 = cv2.imread(image2_path, 0)
​
bins = [64, 128, 256]
​
for bin_count in bins:
enhanced_image1 = histogram_equalisation(image1.copy(), no_of_bins=bin_
enhanced_image2 = histogram_equalisation(image2.copy(), no_of_bins=bin_
​
print(f"Histogram Equalization with {bin_count} bins for Image 1")
plot_histograms(enhanced_image1, f"Image 1 (Bins: {bin_count})")
​
print(f"Histogram Equalization with {bin_count} bins for Image 2")
plot_histograms(enhanced_image2, f"Image 2 (Bins: {bin_count})")

Histogram Equalization with 64 bins for Image 1

Histogram Equalization with 64 bins for Image 2

localhost:8888/notebooks/DIP/Assignment - 7.ipynb 4/6

10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook

Histogram Equalization with 128 bins for Image 1

Histogram Equalization with 128 bins for Image 2

Histogram Equalization with 256 bins for Image 1

Histogram Equalization with 256 bins for Image 2

localhost:8888/notebooks/DIP/Assignment - 7.ipynb 5/6

10/21/24, 10:24 PM Assignment - 7 - Jupyter Notebook

In [ ]: ​

localhost:8888/notebooks/DIP/Assignment - 7.ipynb 6/6