QUESTIONS AND ANSWERS FOR IMAGE PROCESSING – NAAN MUDHALVAN

1. How to Load and Display an Image in MATLAB?

clc; clear all; close all;

% Load an image
img = imread('image.jpg');
% Display the image
imshow(img);

2. How to Blur an Image in MATLAB?

clc; clear all; close all;

% Load the image
img = imread('image.jpg');
% Apply Gaussian blur
blurred_img = imgaussfilt(img, 2);
% Display the blurred image
imshow(blurred_img);

3. How to Enhance Image Contrast using Histogram Equalization in MATLAB?

clc; clear all; close all;

img = imread('image.jpg');
gray_img = rgb2gray(img); % Convert to grayscale
filtered_img = medfilt2(gray_img); % Apply median filtering
enhanced_img = histeq(filtered_img); % Perform histogram equalization

subplot(1, 2, 1);
imshow(enhanced_img);
title('Enhanced Image');

subplot(1, 2, 2);
imhist(enhanced_img);
title('Histogram');

4. How to Apply a Sobel Filter for Edge Detection in MATLAB?

clc; clear all; close all;
% Load the image
img = imread('image.jpg');

% Convert to grayscale
img_gray = rgb2gray(img);
 % Apply Sobel filter
edge_img = edge(img_gray, 'Sobel');

% Display all three images

subplot(1,3,1);
imshow(img);
title('Original Image');

subplot(1,3,2);
imshow(img_gray);
title('Grayscale Image');

subplot(1,3,3);
imshow(edge_img);
title('Edge-detected Image');

5. How to Apply Fourier Transform to an Image in MATLAB?

clc; clear all; close all;

% Load the image
img = imread('image.jpg');
% Convert to grayscale
img_gray = rgb2gray(img);
% Compute Fourier Transform
fft_img = fft2(img_gray);
% Display the magnitude spectrum
magnitude_spectrum = log(1 + abs(fftshift(fft_img)));
imshow(magnitude_spectrum, []);
% Print results
disp('Max value in magnitude spectrum:');
disp(max(magnitude_spectrum(:)));
disp('Min value in magnitude spectrum:');
disp(min(magnitude_spectrum(:)));

6. How can you import an image, apply a Gaussian filter to it, print the mean value and
standard deviation of the filtered imagein MATLAB?

clc; clear all; close all;

% Import the image

 img = imread('image.jpg');

% Convert the image to grayscale

img_gray = rgb2gray(img);

% Define Gaussian parameters

kernel_size = 5; % Size of the kernel (odd number)
sigma = 2; % Standard deviation of the Gaussian distribution

% Create Gaussian kernel

gaussian_kernel = fspecial('gaussian', kernel_size, sigma);

% Apply Gaussian filter

filtered_img = imfilter(img_gray, gaussian_kernel, 'conv', 'replicate');

% Display the filtered image

imshow(filtered_img);
title('Filtered Image');

% Compute some features (e.g., mean and standard deviation)

mean_val = mean(filtered_img(:));
std_dev = std(double(filtered_img(:)));

% Print the computed features

fprintf('Mean value of filtered image: %f\n', mean_val);
fprintf('Standard deviation of filtered image: %f\n', std_dev);

7. How to Identify Lane Boundaries in an Image using MATLAB?

clc; clear all; close all;

% Load the image
img = imread('road_image.jpg');
% Convert to grayscale
img_gray = rgb2gray(img);
% Apply edge detection
edge_img = edge(img_gray, 'Canny');
% Identify lane boundaries using Hough transform
[H,theta,rho] = hough(edge_img);
peaks = houghpeaks(H,5);
lines = houghlines(edge_img,theta,rho,peaks);
% Draw the detected lines on the image
imshow(img), hold on
for k = 1:length(lines)
xy = [lines(k).point1; lines(k).point2];
plot(xy(:,1),xy(:,2),'LineWidth',2,'Color','green');
end

8. How to Perform Image Filtering and defiltering in MATLAB?

clc; clear all; close all;

 % Load the image
img = imread('image.jpg');

% Define a filter
filter = fspecial('average', [5 5]);

% Apply the filter

filtered_img = imfilter(img, filter);

% Display the filtered image

subplot(1, 2, 1);
imshow(filtered_img);
title('Filtered Image');

% Define the inverse filter (deconvolution)

inv_filter = fspecial('unsharp', 0.5);

% Apply the inverse filter (deconvolution)

deconvolved_img = deconvwnr(filtered_img, inv_filter, 0.01);

% Display the deconvolved image

subplot(1, 2, 2);
imshow(deconvolved_img);
title('Deconvolved Image');

9. How to PerformImage Thresholding in MATLAB?

clc; clear all; close all;

% Read the image
img = imread('image.jpg');

% Convert to grayscale if necessary

if size(img, 3) == 3
img = rgb2gray(img);
end

% Define the threshold value

threshold_value = 128;

% Performthresholding
binary_img = img>threshold_value;

% Display the original and thresholded images

subplot(1,2,1), imshow(img), title('Original Image');
subplot(1,2,2), imshow(binary_img), title('Thresholded Image');
10. How to Perform Image Restoration ?

clc; clear all; close all;

% Read the noisy image
noisy_img = imread('image.jpg');

% Convert to grayscale if necessary

if size(noisy_img, 3) == 3
noisy_img = rgb2gray(noisy_img);
end

% Define the size of the Gaussian filter

filter_size = 5;

% Define the standard deviation of the Gaussian filter

sigma = 2;

% Apply Gaussian filter for image restoration

restored_img = imgaussfilt(noisy_img, sigma);

% Display the original and restored images

subplot(1,2,1), imshow(noisy_img), title('Noisy Image');
subplot(1,2,2), imshow(restored_img), title('Restored Image');

11. How to Import and Manipulate Excel Data in MATLAB?

clc; clear all; close all;

% Import Excel data
data = xlsread('data.xlsx');
% Perform manipulation
manipulated_data = data * 2;
% Display the manipulated data
disp(manipulated_data);

12. How to Convert an Image from RGB to Grayscale in MATLAB?

clc; clear all; close all;

% Load the RGB image
rgb_img = imread('rgb_image.jpg');
% Convert to grayscale
gray_img = rgb2gray(rgb_img);
% Display the grayscale image
imshow(gray_img);
13. How to Perform Image Segmentation using Otsu's Method in MATLAB?

clc; clear all; close all;

% Load the grayscale image
img = imread('image.jpg');
% Convert to grayscale if necessary
if size(img, 3) == 3
img = rgb2gray(img);
end
% Perform segmentation using Otsu's method
threshold = graythresh(img);
binary_img = imbinarize(img, threshold);
% Display the segmented image
imshow(binary_img);

14. How to Perform Image Segmentation using Watershed Algorithm in MATLAB?

clc; clear all; close all;

% Load the grayscale image
img = imread('image.jpg');
% Convert to grayscale if necessary
if size(img, 3) == 3
img = rgb2gray(img);
end
% Compute gradient magnitude
gradient_mag = imgradient(img);
% Perform watershed segmentation
marker = imextendedmin(gradient_mag, 0.2);
marker = imimposemin(-gradient_mag, marker);
labels = watershed(marker);
% Display the segmented image
imshow(label2rgb(labels));

15. How to Perform Template Matching in MATLAB?

clc; clear all; close all;

input = imread('image.jpg');
mask =imread('image1.jpg');
gleam = @(I) (1/3) * ((double(I(:,:,1))/255).^(1/2.2) + ...
(double(I(:,:,2))/255).^(1/2.2) + ...
(double(I(:,:,3))/255).^(1/2.2));
normalize = @(I) (I-min(min(I)))/(max(max(I))-min(min(I)));
g_input = gleam(input);
g_mask = gleam(mask);
gd_input = conv2(g_input, [-1 0 1; -1 0 1; -1 0 1]/3, 'same') + ...
conv2(g_input, [-1 -1 -1; 0 0 0; 1 1 1]/3, 'same');
gd_mask = conv2(g_mask, [-1 0 1; -1 0 1; -1 0 1]/3, 'same') + ...
conv2(g_mask, [-1 -1 -1; 0 0 0; 1 1 1]/3, 'same');
gd_mask = rot90(gd_mask, 2);
convolved = conv2(gd_input, gd_mask, 'valid');
[min_value, min_index] = min(convolved(:));
 [min_row, min_col] = ind2sub(size(convolved), min_index);
figure; imshow(normalize(convolved)); hold on;
rectangle('Position', [min_col-32+2 min_row-32+2 64 64], 'EdgeColor', [1 0 0]);
figure; imshow(input*0.75+64); hold on;
rectangle('Position', [min_col+2 min_row+2 64 64], ...
'EdgeColor', [0.5 0 0], ...
'LineWidth', 3, ...
'LineStyle', ':');

16. How to Perform Image Segmentation using Region Growing in MATLAB?

clc; clear all; close all;
gray1=imread('1.jpg'); %to read img 1
gray=rgb2gray(gray1)
figure();
imshow(gray)
title('Original Image');
% gray=rgb2gray(var);
so=edge(gray,'sobel'); %type -1 sobel edge detection
ca=edge(gray,'canny'); %type -2 canny edge detection
% subplot(3,1,2)
figure();
imshow(so);
title('SO Edge Detection');
% subplot(3,1,3)
figure();
imshow(ca);
title('ca Edge Detection');

17. Create Simple Neural Network in MATLAB?

clc; clear all; close all;

% Define the input data

X = [0 0; 0 1; 1 0; 1 1]; % Input features
Y = [0; 1; 1; 0]; % Target outputs

% Create a feedforward neural network

net = feedforwardnet(10); % 10 neurons in the hidden layer
 % Train the neural network
net = train(net, X', Y');

% Test the neural network with new data

output = net(X');

% Display the output

disp('Predicted Output:');
disp(output);

18. How to Perform Image Segmentation using K-Means Clustering in MATLAB?

clc; clear all; close all;

% Load the image
img = imread('image.jpg');
% Reshape the image into a 2D array
[rows, cols, ~] = size(img);
X = reshape(img, rows * cols, []);
% Perform K-Means clustering
K = 3; % Number of clusters
[idx, centers] = kmeans(double(X), K);
% Reshape the clustered image
segmented_img = reshape(idx, rows, cols);
% Display the segmented image
imshow(segmented_img, []); colormap(gca, 'parula');

19. How to Extract Features using Harris Corner Detection in MATLAB?

clc; clear all; close all;

% Load the grayscale image
img = imread('image.jpg');
% Convert to grayscale
img_gray = rgb2gray(img);
% Perform Harris corner detection
corners = detectHarrisFeatures(img_gray);
% Display the detected corners
imshow(img); hold on;
plot(corners);

20. How to plot boundary box on object present in the image using MATLAB?

clc; clear all; close all;

% Read the image

image = imread('image.jpg');

% Convert the image to grayscale

image_gray = rgb2gray(image);
% Perform edge detection
edges = edge(image_gray, 'Canny');

% Perform connected component analysis

cc = bwconncomp(edges);

% Get bounding boxes of connected components

bounding_boxes = regionprops(cc, 'BoundingBox');

% Draw bounding boxes on the original image

imshow(image);
hold on;
fori = 1:numel(bounding_boxes)
rectangle('Position', bounding_boxes(i).BoundingBox, 'EdgeColor', 'r', 'LineWidth', 2);
end
title('Bounding Box Detection');
hold off;