LAB 1
% Read an image % Convert image to grayscale
img = imread('image.png'); gray_img = rgb2gray(img);
% Display the image % Display the grayscale image
imshow(img);title('Original Image'); figure;
imshow(gray_img);
title('Grayscale Image');
% Resize the image to half its original size % Rotate the image by 45 degrees
resized_img = imresize(img, 0.5); rotated_img = imrotate(img, 45);
% Display the resized image % Display the rotated image
figure; figure;
imshow(resized_img); imshow(rotated_img);
title('Resized Image (50%)'); title('Rotated Image by 45 degrees');
% Open a new figure
figure; % Crop the image (x, y, width, height)
plot(1:10, rand(1, 10), '-o'); cropped_img = imcrop(img, [50 50 200 200]);
xlabel('X-axis'); % Display the cropped image
ylabel('Y-axis'); figure;
title('Random Data Plot'); imshow(cropped_img);
grid on; title('Cropped Image');
LAB 2
% Apply Sobel edge detection % Create a random RGB image of size 256x256
edge_img = edge(rgb2gray(img), 'sobel'); random_rgb_img = uint8(randi([0, 255], 256, 256,
% Display the edge-detected image 3));
figure; % Display the RGB image
imshow(edge_img); title('Edge Detection'); imshow(random_rgb_img);
title('Random RGB Image');
% Save the image imwrite(random_rgb_img,
'rand_RGB_image.png’);
Title(‘radom RBG image’);
% Perform histogram equalization % Separate the red, green, and blue channels
equalized_img = histeq(rgb2gray(img)); red_channel = img(:, :, 1);
% Display the histogram-equalized image green_channel = img(:, :, 2);
figure; imshow(equalized_img); blue_channel = img(:, :, 3);
title('Histogram Equalization'); % Display the channels
figure;
subplot(1, 3, 1), imshow(red_channel),
title('Red Channel');
subplot(1, 3, 2),
imshow(green_channel),title('Green Channel');
subplot(1, 3, 3), imshow(blue_channel),
title('Blue Channel');
% Convert image to binary using a threshold % Create a random grayscale image of size 256x256
binary_img = imbinarize(rgb2gray(img), 0.5); random_gray_img = uint8(randi([0, 255], 256, 256));
% Display the binary image % Display the grayscale image
figure;
imshow(binary_img); imshow(random_gray_img);
title('Binary Image'); title('Random Grayscale Image');
LAB 3
%Image Resize % Example Shrink Image By Factor of Two
Imresize () Using Default Interpolation Method
% Resize image to specified dimensions I = imread('img.JPEG');
B2 = imresize(A, [200 300]); J = imresize(I, 0.5);
% Resize to 200 rows and 300 columns % Shrink the image by a factor of two.
figure; subplot (2,1,1);
imshow(B2); imshow(I);
title('Resized Image (200x300)'); title('original image');
% display original image subplot(2,1,2);
imshow(J);
% display shrinked image
title('shrinked image');
%Perform Shrinking of an image %Example Shrink Image Using bilinear-
% Read the input image Interpolation I = imread(‘img.JPEG’); J =
I = imread(‘Image.JPEG’); imresize(I, 0.2, ‘bilinear’) subplot (2,1,1);
% Shrink the image to 40% of its original imshow(I); title(‘original image’);
size using nearest-neighbor interpolation subplot(2,1,2); imshow(J); title(‘shrinked
J = imresize(I, 0.4, ‘nearest’); image’);
% Display the original and shrinked images
side by side
subplot(2,1,1);
imshow(I);
title(‘Original Image’);
subplot(2,1,2);
imshow(J);
title(‘Shrinked Image’);
%Example Shrink Image Using bicubic- Perform Zooming of an image
Neighbor Interpolation % Example Enlarge image using Nearest
% Read the input image Interpolation
I = imread(‘img.JPEG’); I = imread(‘img.JPEG’);
% Shrink the image to 60% of its original J = imresize(I, 2, ‘nearest’)
size using bicubic interpolation %Shrink the image to 40% of the original
J = imresize(I, 0.6, ‘bicubic’); size using nearest-neighbor interpolation.
% Display the original and shrinked images This is the fastest method, but it has the
side by side lowest quality.
subplot(2,1,1); Subplot (2,1,1);
imshow(I); imshow(I);
title(‘Original Image’); title(‘original image’);
subplot(2,1,2);
subplot(2,1,2); imshow(J);
imshow(J); title(‘shrinked image’);
title(‘Shrinked Image’);
%Example Enlarge Image Using Bilinear- %Example Enlarge Image Using Cubic-
Interpolation Interpolation
I = imread(‘img.JPEG’); I = imread(‘img.JPEG’);
J = imresize(I, 5, ‘bilinear’) J = imresize(I, 5, ‘cubic’);
subplot (2,1,1); %Shrink the image to 40% of the original
imshow(I); size using nearest-neighbor interpolation.
title(‘original image’); This is the fastest method, but it has the
subplot(2,1,2); lowest quality.
imshow(J); Subplot (2,1,1);
title(‘shrinked image’); imshow(I);
title(‘original image’);
subplot(2,1,2);
imshow(J);
title(‘shrinked image’);
Perform Cropping of an image % Example Crop Indexed Image Specifying
% Read the input image Crop Rectangle
I = imread(‘image.png’); I = imread(‘img.tif’);
I2 = imcrop(I,[75 68 130 112]);
% Example 1: Interactive cropping % Crop image, specifying crop rectangle.
figure; Subplot(1,2,1)
imshow(I); imshow(I)
title(‘Interactive Cropping – Select title(‘Original Image’)
Region’); % Display original image
Icropped1 = imcrop(I); % Allows user to subplot(1,2,2)
crop interactively imshow(I2)
figure; title(‘Cropped Image’) % Display cropped
imshow(Icropped1); image.
title(‘Cropped Image (Interactive)’);
% Example 2: Cropping using a specified
rectangle
rect = [50 50 200 150]; % [x, y, width,
height]
Icropped2 = imcrop(I, rect); % Cropping
the image
figure;
imshow(Icropped2);
title(‘Cropped Image (Rectangle)’);
LAB 4
% Read and display an image originalImage %Read and display an image
= imread('img.JPEG'); % Repalce originalImage = imread('image.jpg');
'your_image.jpg' with the actual iamge file %%Perform the 2D FFT on the image
path imshow(originalImage); title('original fftImage
Image'); =fft2(double(originalImage));
%% Define Parameters for Gaussian filter
sigma = 2; %%Define filter parameters
% Standard deviation of the guassian D0 = 40; %Cutoff frequency
distribution
Filtersize = 11; % size of the filter kernel % %%Create the frequency domain filter
Create a Gaussain kernel using fspecial (high-pass)
gaussianKernal = fspecial('gaussian', [x, y] =
filtersize, sigma); %Apply the Gaussian meshgrid(1:size(originalImage, 2),
filter to the image using 1:size(originalImage, 1));
centerX = ceil (size(originalImage,
imfilter filteredImage =
2) /2);
imfilter(originalImage, centerY = ceil (size(originalImage,
gaussianKernal, 'conv');
%Display the filtered image figure; 1) /2);
imshow(filteredImage);
title('Low-Pass Filtered Image (Gaussian)'); %%High-Pass filter
H = double(sqrt((x - centerX) .^2 +
(y - centerY) .^2) > D0);
%% Apply the filter in frequency
domain
filteredImage = real(ifft2(fftImage
.* H));
%% Display the original and filtered
image
figure;
subplot( 1, 2, 1);
imshow(originalImage);
title('Original Image');
subplot(1,2,2);
imshow(filteredImage, []);
title('High-pass Fltered Image');
LAB 5
I = checkerboard(8);
Deblur image using Wiener filter PSF = fspecial('gaussian',7,10);
I = im2double(imread('image.jpg')); V = .01;
imshow(I); BlurredNoisy =
title('Original Image'); imnoise(imfilter(I,PSF),'gaussian',0,V);
LEN = 21; NOISEPOWER = V*prod(size(I));
THETA = 11; [J LAGRA] =
PSF = fspecial('motion', LEN, THETA); deconvreg(BlurredNoisy,PSF,NOISEPOWER);
blurred = imfilter(I, PSF, 'conv', subplot(221); imshow(BlurredNoisy);
'circular'); title('A = Blurred and Noisy');
figure, imshow(blurred) subplot(222); imshow(J);
noise_mean = 0; title('[J LAGRA] = deconvreg(A,PSF,NP)');
noise_var = 0.0001; subplot(223);
blurred_noisy = imnoise(blurred, imshow(deconvreg(BlurredNoisy,PSF,[],LAGRA/
'gaussian', noise_mean, noise_var); 10));
figure, imshow(blurred_noisy) title('deconvreg(A,PSF,[],0.1*LAGRA)');
title('Simulate Blur and Noise') subplot(224);
estimated_nsr = 0; imshow(deconvreg(BlurredNoisy,PSF,[],LAGRA
wnr2 = deconvwnr(blurred_noisy, PSF, *10));
estimated_nsr); title('deconvreg(A,PSF,[],10*LAGRA)');
figure, imshow(wnr2)
title('Restoration of Blurred, Noisy
Image Using NSR = 0')
estimated_nsr = noise_var / var(I(:));
wnr3 = deconvwnr(blurred_noisy, PSF,
estimated_nsr);
figure, imshow(wnr3)
title('Restoration of Blurred, Noisy
Image Using Estimated NSR');
I = imread("board.tif");
I = imcrop(I,[2 50 255 255]); rng default;
imshow(I) I = checkerboard(8);
title("Original Image") PSF = fspecial('gaussian',7,10);
by-5. V = .0001;
PSF = fspecial("gaussian",5,5); BlurredNoisy =
blurred = imnoise(imfilter(I,PSF),'gaussian',0,V);
imfilter(I,PSF,"symmetric","conv"); WT = zeros(size(I));
V = 0.002; WT(5:end-4,5:end-4) = 1;
blurred_noisy = INITPSF = ones(size(PSF));
imnoise(blurred,"gaussian",0,V); [J P] =
imshow(blurred_noisy) deconvblind(BlurredNoisy,INITPSF,20,10*sqrt(
title("Blurred and Noisy Image") V),WT);
blur and decrease the number of subplot(221);imshow(BlurredNoisy);
iterations to 5. title('A = Blurred and Noisy');
luc1 = subplot(222);imshow(PSF,[]);
deconvlucy(blurred_noisy,PSF,5); title('True PSF');
imshow(luc1) subplot(223);imshow(J);
title("Restored Image") title('Deblurred Image');
subplot(224);imshow(P,[]);
title('Recovered PSF');
LAB 6
%1. Edge Detection Code: %. Line Detection using Hough Transform:
% Read, rotate, and display the image
% Importing the image and converting it to I = imread('image.tif');
grayscale rotI = imrotate(I, 33, 'crop');
I = rgb2gray(imread("flowers.jpg")); imshow(rotI);
% Displaying the original grayscale image
subplot(2, 4, 1), % Find the edges in the image using the
imshow(I); edge function
title("Gray Scale Image"); BW = edge(rotI, 'canny');
imshow(BW);
% Sobel Edge Detection
J = edge(I, 'Sobel'); % Compute the Hough transform of the
subplot(2, 4, 2), binary image returned by edge
imshow(J); [H, theta, rho] = hough(BW);
title("Sobel");
% Display the Hough transform
% Prewitt Edge detection figure;
K = edge(I, 'Prewitt'); imshow(imadjust(rescale(H)), [], 'XData',
subplot(2, 4, 3), theta, 'YData', rho, ...
imshow(K); 'InitialMagnification', 'fit');
title("Prewitt"); xlabel('\theta (degrees)');
ylabel('\rho');
% Robert Edge Detection axis on;
L = edge(I, 'Roberts'); axis normal;
subplot(2, 4, 4), hold on;
imshow(L); colormap(gca, hot);
title("Robert");
% Find the peaks in the Hough transform
% Log Edge Detection matrix using houghpeaks
M = edge(I, 'log'); P = houghpeaks(H, 5, 'threshold', ceil(0.3 *
subplot(2, 4, 5), max(H(:))));
imshow(M);
title("Log"); % Superimpose a plot on the image of the
transform that identifies the peaks
% Zerocross Edge Detection x = theta(P(:, 2));
M = edge(I, 'zerocross'); y = rho(P(:, 1));
subplot(2, 4, 6), plot(x, y, 's', 'color', 'black');
imshow(M);
title("Zerocross"); % Find lines in the image using houghlines
lines = houghlines(BW, theta, rho, P,
% Canny Edge Detection 'FillGap', 5, 'MinLength', 7);
N = edge(I, 'Canny');
subplot(2, 4, 7), % Create a plot that displays the original
imshow(N); image with the lines superimposed
title("Canny"); figure, imshow(rotI), hold on;
max_len = 0;
for k = 1:length(lines)
xy = [lines(k).point1; lines(k).point2];
plot(xy(:, 1), xy(:, 2), 'LineWidth', 2,
'Color', 'green');
% Plot beginnings and ends of lines
plot(xy(1, 1), xy(1, 2), 'x', 'LineWidth', 2,
'Color', 'yellow');
plot(xy(2, 1), xy(2, 2), 'x', 'LineWidth', 2,
'Color', 'red');
% Determine the endpoints of the
longest line segment
len = norm(lines(k).point1 -
lines(k).point2);
if len > max_len
max_len = len;
xy_long = xy;
end
end
% Highlight the longest line segment
plot(xy_long(:, 1), xy_long(:, 2),
'LineWidth', 2, 'Color', 'red');
LAB 7
% Read and Display the image % Load the image
RGB = imread("image.jpg"); rgb = imread('image.jpg');
imshow(RGB); imshow(rgb);
% Convert the RGB image to a grayscale % Compute the complement of the RGB
image and display the result image
I = rgb2gray(RGB); c = imcomplement(rgb);
imshow(I); imshow(c);
% Read the RGB Image % Read the input image
A = imread('image.jpg'); img = imread('image.jpg');
figure, imshow(A);
title('RGB Image'); % Convert the input image to grayscale
gray_img = rgb2gray(img);
% Represent the RGB image in [0 1] range
% Create an empty matrix for the RGB output
I = double(A) / 255; image
R = I(:,:,1); out_img = zeros(size(gray_img, 1),
G = I(:,:,2); size(gray_img, 2), 3);
B = I(:,:,3);
% Specify a colormap (e.g., jet)
% Hue Calculation colormap_name = 'jet';
numi = 1/2 * ((R - G) + (R - B)); color_map = colormap(colormap_name);
denom = sqrt((R - G).^2 + ((R - B) .* (G -
B))); % Extract RGB color channels from the
colormap
H = acosd(numi ./ (denom + 0.000001)); %
red = color_map(:, 1);
Avoid divide by zero
green = color_map(:, 2);
H(B > G) = 360 - H(B > G); % Adjust if B > G blue = color_map(:, 3);
H = H / 360; % Normalize to range [0 1]
% Map grayscale intensity values to RGB colors
% Saturation Calculation out_img(:, :, 1) = red(gray_img);
S = 1 - (3 ./ (sum(I, 3) + 0.000001)) .* min(I, out_img(:, :, 2) = green(gray_img);
[], 3); out_img(:, :, 3) = blue(gray_img);
% Intensity Calculation % Convert the output image to 8-bit unsigned
I = sum(I, 3) / 3; integer format
out_img = im2uint8(out_img);
% Combine HSI
HSI = zeros(size(A)); % Display the input image, grayscale image,
HSI(:,:,1) = H; and pseudo-color image
HSI(:,:,2) = S; subplot(1, 3, 1); imshow(img); title('Original
HSI(:,:,3) = I; Image');
subplot(1, 3, 2); imshow(gray_img);
figure, imshow(HSI);
title('Grayscale Image');
title('HSI Image');
subplot(1, 3, 3); imshow(out_img);
title('Pseudo-Color Image');
