├── .gitattributes ├── Gonzalez_images ├── ch1.zip ├── ch10.zip ├── ch11.zip ├── ch12.zip ├── ch2.zip ├── ch3.zip ├── ch4.zip ├── ch5.zip ├── ch6.zip ├── ch7.zip ├── ch8.zip └── ch9.zip ├── README.md ├── S2 ├── .ipynb_checkpoints │ ├── 1.resolution-checkpoint.ipynb │ ├── 2.quantization_plane-checkpoint.ipynb │ ├── 3.connected_component-checkpoint.ipynb │ └── 4.Zooming_bilinear_Matlab-checkpoint.m ├── 1.resolution.ipynb ├── 2.quantization_plane.ipynb ├── 3.connected_component.ipynb └── 4.Zooming_bilinear_Matlab.m ├── S3 ├── .ipynb_checkpoints │ ├── 1.Gamma_correction-checkpoint.ipynb │ ├── 10.Salt&pepper_noise_removal_using_median_filter-checkpoint.ipynb │ ├── 11.Arithmetic_filter-checkpoint.ipynb │ ├── 12.Laplacian_filter_feature_enhacement-checkpoint.ipynb │ ├── 13.Gradient _size_and_phase-checkpoint.ipynb │ ├── 2.Contrast_enhacement_using_linearpiecewise -checkpoint.ipynb │ ├── 3.bit_plane-checkpoint.ipynb │ ├── 4.Histogram_equalization-checkpoint.ipynb │ ├── 5.Histogram_specification(mathcing)-checkpoint.ipynb │ ├── 6.Local_histogram_equalization-checkpoint.ipynb │ ├── 7.image_averaging-checkpoint.ipynb │ ├── 8.Local_histogram_statics-checkpoint.ipynb │ └── 9.Averaging_filter-checkpoint.ipynb ├── 1.Gamma_correction.ipynb ├── 10.Salt&pepper_noise_removal_using_median_filter.ipynb ├── 11.Arithmetic_filter.ipynb ├── 12.Laplacian_filter_feature_enhacement.ipynb ├── 13.Gradient _size_and_phase.ipynb ├── 2.Contrast_enhacement_using_linearpiecewise .ipynb ├── 3.bit_plane.ipynb ├── 4.Histogram_equalization.ipynb ├── 5.Histogram_specification(mathcing).ipynb ├── 6.Local_histogram_equalization.ipynb ├── 7.image_averaging.ipynb ├── 8.Local_histogram_statics.ipynb └── 9.Averaging_filter.ipynb ├── S4 ├── .ipynb_checkpoints │ ├── 1.Fourier_transform-checkpoint.ipynb │ ├── 10.Butterworth_highpass_filter_in_frequency_domain-checkpoint.ipynb │ ├── 11.Gaussian_highpass_filter_in_frequency_domain-checkpoint.ipynb │ ├── 12.Text_enhacement_in_frequency_domain_using_gaussian_filter-checkpoint.ipynb │ ├── 13.High_boost_filtering-checkpoint.ipynb │ ├── 14.Unsharp_masking-checkpoint.ipynb │ ├── 15.Homomorphic-checkpoint.ipynb │ ├── 2.Gaussian_filter-checkpoint.ipynb │ ├── 3.Moire_pattern-checkpoint.ipynb │ ├── 4.Half_tone_dotes-checkpoint.ipynb │ ├── 5.Combining_magnitude_and_phase_of_two_images-checkpoint.ipynb │ ├── 6.Ideal_lowpass_filter_in_frequency_domain-checkpoint.ipynb │ ├── 7.Butterworth_lowpass_filter_in_frequency_domain-checkpoint.ipynb │ ├── 8.Gaussian_lowpass_filter_in_frequency_domain-checkpoint.ipynb │ └── 9.Ideal_highpass_filter_in_frequency_domain-checkpoint.ipynb ├── 1.Fourier_transform.ipynb ├── 10.Butterworth_highpass_filter_in_frequency_domain.ipynb ├── 11.Gaussian_highpass_filter_in_frequency_domain.ipynb ├── 12.Text_enhacement_in_frequency_domain_using_gaussian_filter.ipynb ├── 13.High_boost_filtering.ipynb ├── 14.Unsharp_masking.ipynb ├── 15.Homomorphic.ipynb ├── 2.Gaussian_filter.ipynb ├── 3.Moire_pattern.ipynb ├── 4.Half_tone_dotes.ipynb ├── 5.Combining_magnitude_and_phase_of_two_images.ipynb ├── 6.Ideal_lowpass_filter_in_frequency_domain.ipynb ├── 7.Butterworth_lowpass_filter_in_frequency_domain.ipynb ├── 8.Gaussian_lowpass_filter_in_frequency_domain.ipynb └── 9.Ideal_highpass_filter_in_frequency_domain.ipynb └── S5 ├── Matlab ├── .ipynb_checkpoints │ ├── 1.Turbulence _noise-checkpoint.m │ ├── 2.Motion_blur-checkpoint.m │ ├── 3.Motion_blur_in_frequency_domain-checkpoint.m │ ├── 4.Turbulence_noise_removal_using_inverse_filtering-checkpoint.m │ ├── 5.Inverse_filtering_in_frequency_domain-checkpoint.m │ ├── 6.Motion_blur_removal_using_wiener_filter-checkpoint.m │ └── 7.Gaussian_noise_removal_using_adaptive_local_mean-checkpoint.m ├── 1.Turbulence _noise.m ├── 2.Motion_blur.m ├── 3.Motion_blur_in_frequency_domain.m ├── 4.Turbulence_noise_removal_using_inverse_filtering.m ├── 5.Inverse_filtering_in_frequency_domain.m ├── 6.Motion_blur_removal_using_wiener_filter.m └── 7.Gaussian_noise_removal_using_adaptive_local_mean.m └── Python ├── .ipynb_checkpoints ├── 1.Gaussian_noise-checkpoint.ipynb ├── 10.Salt_and_pepper_noise_removal_using_alpha_trimmed_filter-checkpoint.ipynb ├── 11.Salt_and_pepper_noise_removal_using_adaptive_median_filter-checkpoint.ipynb ├── 12.Periodic_noise-checkpoint.ipynb ├── 13.Periodic_noise_in_frequency_domain-checkpoint.ipynb ├── 14.periodic_noise_removal_using_notch_filter_in_frequency_domain-checkpoint.ipynb ├── 15.periodic_noise_removal_using_gaussian_notch_filter_in_frequency_domain-checkpoint.ipynb ├── 16.periodic_noise_removal_using_butterworth_notch_filter_in_frequency_domain-checkpoint.ipynb ├── 17.periodic_noise_removal_using_ideal_notch_filter_in_frequency_domain-checkpoint.ipynb ├── 2.Gaussian_noise_removal_using_Arithmetic_mean_filter-checkpoint.ipynb ├── 3.Gaussian_noise_removal_using_Geometric _mean_filter-checkpoint.ipynb ├── 4.Salt_and_pepper_noise-checkpoint.ipynb ├── 5.Salt_and_pepper_noise_removal_using_median_filter-checkpoint.ipynb ├── 6.Salt_and_pepper_noise_removal_using_midpoint_filter-checkpoint.ipynb ├── 7.Salt_and_pepper_noise_removal_using_contraharmonic_filter-checkpoint.ipynb ├── 8.Salt_and_pepper_noise_removal_using_arithmetic_mean_filter-checkpoint.ipynb └── 9.Salt_and_pepper_noise_removal_using_median_filter-checkpoint.ipynb ├── 1.Gaussian_noise.ipynb ├── 10.Salt_and_pepper_noise_removal_using_alpha_trimmed_filter.ipynb ├── 11.Salt_and_pepper_noise_removal_using_adaptive_median_filter.ipynb ├── 12.Periodic_noise.ipynb ├── 13.Periodic_noise_in_frequency_domain.ipynb ├── 14.periodic_noise_removal_using_notch_filter_in_frequency_domain.ipynb ├── 15.periodic_noise_removal_using_gaussian_notch_filter_in_frequency_domain.ipynb ├── 16.periodic_noise_removal_using_butterworth_notch_filter_in_frequency_domain.ipynb ├── 17.periodic_noise_removal_using_ideal_notch_filter_in_frequency_domain.ipynb ├── 2.Gaussian_noise_removal_using_Arithmetic_mean_filter.ipynb ├── 3.Gaussian_noise_removal_using_Geometric _mean_filter.ipynb ├── 4.Salt_and_pepper_noise.ipynb ├── 5.Salt_and_pepper_noise_removal_using_median_filter.ipynb ├── 6.Salt_and_pepper_noise_removal_using_midpoint_filter.ipynb ├── 7.Salt_and_pepper_noise_removal_using_contraharmonic_filter.ipynb ├── 8.Salt_and_pepper_noise_removal_using_arithmetic_mean_filter.ipynb └── 9.Salt_and_pepper_noise_removal_using_median_filter.ipynb /.gitattributes: -------------------------------------------------------------------------------- 1 | # Auto detect text files and perform LF normalization 2 | * text=auto 3 | -------------------------------------------------------------------------------- /Gonzalez_images/ch1.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch1.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch10.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch10.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch11.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch11.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch12.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch12.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch2.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch2.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch3.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch3.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch4.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch4.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch5.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch5.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch6.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch6.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch7.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch7.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch8.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch8.zip -------------------------------------------------------------------------------- /Gonzalez_images/ch9.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/PouyaSonej/Image-processing_GonalezBook/1678f474417640dcdb20cd8e42f0a3e37886e7cb/Gonzalez_images/ch9.zip -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Image-processing_Gonalez-book 2 | 3 | -------------------------------------------------------------------------------- /S2/.ipynb_checkpoints/3.connected_component-checkpoint.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [], 3 | "metadata": {}, 4 | "nbformat": 4, 5 | "nbformat_minor": 5 6 | } 7 | -------------------------------------------------------------------------------- /S2/.ipynb_checkpoints/4.Zooming_bilinear_Matlab-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% season 2 4 | %% zooming rate = 4 5 | 6 | clc; 7 | clear all; 8 | 9 | % MATLAB CODE for Adaptive filtering- Local Noise filter 10 | X = imread('GeeksforGeeks.png'); 11 | Y = rgb2gray(X); 12 | sz = size(Y,1)*size(Y,2); 13 | 14 | % Add gaussian noise with mean 0 and variance 0.010 15 | y = imnoise(y,'gaussian',0,0.010); 16 | figure,imshow(y); title('Image with gaussian noise'); 17 | 18 | y = double(y); 19 | 20 | % Define the window size mxn 21 | U = 10; 22 | V = 10; 23 | 24 | % Fill the matrix up on all sides with zeros. 25 | Z = padarray(Y,[floor(N/2),floor(M/2)]); 26 | 27 | lvar = zeros([size(y,1) size(y,2)]); 28 | lmean = zeros([size(y,1) size(y,2)]); 29 | temp = zeros([size(y,1) size(y,2)]); 30 | NewImg = zeros([size(y,1) size(y,2)]); 31 | 32 | for i = 1:size(Z,1)-(N-1) 33 | for j = 1:size(Z,2)-(M-1) 34 | 35 | temp = Z(i:i+(N-1),j:j+(M-1)); 36 | tmp = temp(:); 37 | % Determine the region's local mean and variance. 38 | lmean(i,j) = mean(tmp); 39 | lvar(i,j) = mean(tmp.^2)-mean(tmp).^2; 40 | 41 | end 42 | end 43 | 44 | % Commotion fluctuation and normal 45 | % of the neighborhood change 46 | nvar = sum(lvar(:))/sz; 47 | 48 | % If noise_variance > local_variance 49 | % then local_variance=noise_variance 50 | lvar = max(lvar,nvar); 51 | 52 | % Final_Image = Y- (noise variance/ 53 | % local variance)*(Y-local_mean); 54 | NewImg = nvar./lvar; 55 | NewImg = NewImg.*(Y-lmean); 56 | NewImg = Y-NewImg; 57 | 58 | % Convert the image to uint9 format. 59 | NewImg = uint9(NewImg); 60 | figure,imshow(NewImg);title('Restored Image using Adaptive Local filter'); -------------------------------------------------------------------------------- /S2/3.connected_component.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "id": "1960673c-0150-41da-8741-1a7de29609c6", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import cv2\n", 11 | "import matplotlib.pyplot as plt\n", 12 | "import numpy as np" 13 | ] 14 | }, 15 | { 16 | "cell_type": "code", 17 | "execution_count": 10, 18 | "id": "0eb2bc50-a583-4434-8603-ade4f2f79007", 19 | "metadata": { 20 | "id": "uDjq7jQD7ILE" 21 | }, 22 | "outputs": [], 23 | "source": [ 24 | "def connected_components(filename, sigma=1.0, t=0.5, connectivity=2):\n", 25 | " # convert the image to grayscale\n", 26 | " # gray_image = skimage.color.rgb2gray(filename)\n", 27 | " gray_image = filename\n", 28 | " # denoise the image with a Gaussian filter\n", 29 | " blurred_image = skimage.filters.gaussian(gray_image, sigma=sigma)\n", 30 | " # mask the image according to threshold\n", 31 | " binary_mask = blurred_image < t\n", 32 | " # perform connected component analysis\n", 33 | " labeled_image, count = skimage.measure.label(binary_mask,\n", 34 | " connectivity=connectivity, return_num=True)\n", 35 | " return labeled_image, count\n", 36 | "\n" 37 | ] 38 | }, 39 | { 40 | "cell_type": "code", 41 | "execution_count": 12, 42 | "id": "3d3aed17-8eb7-453c-9853-12a55e663efd", 43 | "metadata": { 44 | "colab": { 45 | "base_uri": "https://localhost:8080/", 46 | "height": 451 47 | }, 48 | "id": "wV8ZoUMQ-0DQ", 49 | "outputId": "21013706-493c-409c-a735-1ccd4db2c2a0" 50 | }, 51 | "outputs": [ 52 | { 53 | "data": { 54 | "text/plain": [ 55 | "(214, 235)" 56 | ] 57 | }, 58 | "execution_count": 12, 59 | "metadata": {}, 60 | "output_type": "execute_result" 61 | }, 62 | { 63 | "data": { 64 | "image/png": "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\n", 65 | "text/plain": [ 66 | "
" 67 | ] 68 | }, 69 | "metadata": {}, 70 | "output_type": "display_data" 71 | } 72 | ], 73 | "source": [ 74 | "#Original image Downloaded from internet\n", 75 | "img3 = cv2.imread(\"/content/images.jpg\",cv2.IMREAD_GRAYSCALE)\n", 76 | "plt.imshow(img3,cmap='gray')\n", 77 | "img3.shape" 78 | ] 79 | }, 80 | { 81 | "cell_type": "code", 82 | "execution_count": 13, 83 | "id": "9519d988-75b6-4c96-9e02-8bb99744b3b9", 84 | "metadata": { 85 | "colab": { 86 | "base_uri": "https://localhost:8080/", 87 | "height": 451 88 | }, 89 | "id": "Bu_hYmtE-Gp3", 90 | "outputId": "5a9799b7-aa4b-4efe-f311-c68051d312a3" 91 | }, 92 | "outputs": [ 93 | { 94 | "data": { 95 | "text/plain": [ 96 | "5" 97 | ] 98 | }, 99 | "execution_count": 13, 100 | "metadata": {}, 101 | "output_type": "execute_result" 102 | }, 103 | { 104 | "data": { 105 | "image/png": "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\n", 106 | "text/plain": [ 107 | "
" 108 | ] 109 | }, 110 | "metadata": {}, 111 | "output_type": "display_data" 112 | } 113 | ], 114 | "source": [ 115 | "\n", 116 | "x , y = connected_components(img3)\n", 117 | "plt.imshow(x,cmap='gray')\n", 118 | "y" 119 | ] 120 | } 121 | ], 122 | "metadata": { 123 | "kernelspec": { 124 | "display_name": "Python 3 (ipykernel)", 125 | "language": "python", 126 | "name": "python3" 127 | }, 128 | "language_info": { 129 | "codemirror_mode": { 130 | "name": "ipython", 131 | "version": 3 132 | }, 133 | "file_extension": ".py", 134 | "mimetype": "text/x-python", 135 | "name": "python", 136 | "nbconvert_exporter": "python", 137 | "pygments_lexer": "ipython3", 138 | "version": "3.10.12" 139 | } 140 | }, 141 | "nbformat": 4, 142 | "nbformat_minor": 5 143 | } 144 | -------------------------------------------------------------------------------- /S2/4.Zooming_bilinear_Matlab.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% season 2 4 | %% zooming rate = 4 5 | 6 | clc; 7 | clear all; 8 | 9 | % MATLAB CODE for Adaptive filtering- Local Noise filter 10 | X = imread('GeeksforGeeks.png'); 11 | Y = rgb2gray(X); 12 | sz = size(Y,1)*size(Y,2); 13 | 14 | % Add gaussian noise with mean 0 and variance 0.010 15 | y = imnoise(y,'gaussian',0,0.010); 16 | figure,imshow(y); title('Image with gaussian noise'); 17 | 18 | y = double(y); 19 | 20 | % Define the window size mxn 21 | U = 10; 22 | V = 10; 23 | 24 | % Fill the matrix up on all sides with zeros. 25 | Z = padarray(Y,[floor(N/2),floor(M/2)]); 26 | 27 | lvar = zeros([size(y,1) size(y,2)]); 28 | lmean = zeros([size(y,1) size(y,2)]); 29 | temp = zeros([size(y,1) size(y,2)]); 30 | NewImg = zeros([size(y,1) size(y,2)]); 31 | 32 | for i = 1:size(Z,1)-(N-1) 33 | for j = 1:size(Z,2)-(M-1) 34 | 35 | temp = Z(i:i+(N-1),j:j+(M-1)); 36 | tmp = temp(:); 37 | % Determine the region's local mean and variance. 38 | lmean(i,j) = mean(tmp); 39 | lvar(i,j) = mean(tmp.^2)-mean(tmp).^2; 40 | 41 | end 42 | end 43 | 44 | % Commotion fluctuation and normal 45 | % of the neighborhood change 46 | nvar = sum(lvar(:))/sz; 47 | 48 | % If noise_variance > local_variance 49 | % then local_variance=noise_variance 50 | lvar = max(lvar,nvar); 51 | 52 | % Final_Image = Y- (noise variance/ 53 | % local variance)*(Y-local_mean); 54 | NewImg = nvar./lvar; 55 | NewImg = NewImg.*(Y-lmean); 56 | NewImg = Y-NewImg; 57 | 58 | % Convert the image to uint9 format. 59 | NewImg = uint9(NewImg); 60 | figure,imshow(NewImg);title('Restored Image using Adaptive Local filter'); -------------------------------------------------------------------------------- /S3/.ipynb_checkpoints/6.Local_histogram_equalization-checkpoint.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "id": "2f6d278f-859d-415a-9d46-d80ee27c6a19", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "from skimage.morphology import disk,ball,cube,square\n", 11 | "from skimage.filters import rank\n", 12 | "import cv2\n", 13 | "import matplotlib.pyplot as plt\n", 14 | "import numpy as np\n", 15 | "import skimage\n" 16 | ] 17 | }, 18 | { 19 | "cell_type": "code", 20 | "execution_count": null, 21 | "id": "56a1990e-4ad5-4cfd-b077-f441853074f9", 22 | "metadata": { 23 | "colab": { 24 | "base_uri": "https://localhost:8080/", 25 | "height": 230 26 | }, 27 | "id": "_BE-yKrP2C3g", 28 | "outputId": "8a0faa29-722a-4808-f281-81fa6aa26c3b" 29 | }, 30 | "outputs": [ 31 | { 32 | "data": { 33 | "text/plain": [ 34 | "" 35 | ] 36 | }, 37 | "execution_count": 10, 38 | "metadata": {}, 39 | "output_type": "execute_result" 40 | }, 41 | { 42 | "data": { 43 | "image/png": "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\n", 44 | "text/plain": [ 45 | "
" 46 | ] 47 | }, 48 | "metadata": {}, 49 | "output_type": "display_data" 50 | } 51 | ], 52 | "source": [ 53 | "img2 = cv2.imread(\"/content/morrre.PNG\")\n", 54 | "# img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n", 55 | "\n", 56 | "footprint = ball(3)\n", 57 | "footprint1 = cube(3)\n", 58 | "\n", 59 | "img_eq = rank.equalize(img2, footprint=footprint)\n", 60 | "img_eq1 = rank.equalize(img2, footprint=footprint1)\n", 61 | "\n", 62 | "img_eq = cv2.cvtColor(img_eq, cv2.COLOR_BGR2GRAY)\n", 63 | "img_eq1 = cv2.cvtColor(img_eq1, cv2.COLOR_BGR2GRAY)\n", 64 | "\n", 65 | "plt.subplot(131)\n", 66 | "plt.imshow(img2,cmap=\"gray\")\n", 67 | "\n", 68 | "plt.subplot(132)\n", 69 | "plt.imshow(img_eq,cmap='gray')\n", 70 | "\n", 71 | "plt.subplot(133)\n", 72 | "plt.imshow(img_eq1,cmap='gray')\n", 73 | "\n" 74 | ] 75 | } 76 | ], 77 | "metadata": { 78 | "kernelspec": { 79 | "display_name": "Python 3 (ipykernel)", 80 | "language": "python", 81 | "name": "python3" 82 | }, 83 | "language_info": { 84 | "codemirror_mode": { 85 | "name": "ipython", 86 | "version": 3 87 | }, 88 | "file_extension": ".py", 89 | "mimetype": "text/x-python", 90 | "name": "python", 91 | "nbconvert_exporter": "python", 92 | "pygments_lexer": "ipython3", 93 | "version": "3.10.12" 94 | } 95 | }, 96 | "nbformat": 4, 97 | "nbformat_minor": 5 98 | } 99 | -------------------------------------------------------------------------------- /S3/6.Local_histogram_equalization.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": null, 6 | "id": "2f6d278f-859d-415a-9d46-d80ee27c6a19", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "from skimage.morphology import disk,ball,cube,square\n", 11 | "from skimage.filters import rank\n", 12 | "import cv2\n", 13 | "import matplotlib.pyplot as plt\n", 14 | "import numpy as np\n", 15 | "import skimage\n" 16 | ] 17 | }, 18 | { 19 | "cell_type": "code", 20 | "execution_count": null, 21 | "id": "56a1990e-4ad5-4cfd-b077-f441853074f9", 22 | "metadata": { 23 | "colab": { 24 | "base_uri": "https://localhost:8080/", 25 | "height": 230 26 | }, 27 | "id": "_BE-yKrP2C3g", 28 | "outputId": "8a0faa29-722a-4808-f281-81fa6aa26c3b" 29 | }, 30 | "outputs": [ 31 | { 32 | "data": { 33 | "text/plain": [ 34 | "" 35 | ] 36 | }, 37 | "execution_count": 10, 38 | "metadata": {}, 39 | "output_type": "execute_result" 40 | }, 41 | { 42 | "data": { 43 | "image/png": "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\n", 44 | "text/plain": [ 45 | "
" 46 | ] 47 | }, 48 | "metadata": {}, 49 | "output_type": "display_data" 50 | } 51 | ], 52 | "source": [ 53 | "img2 = cv2.imread(\"/content/morrre.PNG\")\n", 54 | "# img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)\n", 55 | "\n", 56 | "footprint = ball(3)\n", 57 | "footprint1 = cube(3)\n", 58 | "\n", 59 | "img_eq = rank.equalize(img2, footprint=footprint)\n", 60 | "img_eq1 = rank.equalize(img2, footprint=footprint1)\n", 61 | "\n", 62 | "img_eq = cv2.cvtColor(img_eq, cv2.COLOR_BGR2GRAY)\n", 63 | "img_eq1 = cv2.cvtColor(img_eq1, cv2.COLOR_BGR2GRAY)\n", 64 | "\n", 65 | "plt.subplot(131)\n", 66 | "plt.imshow(img2,cmap=\"gray\")\n", 67 | "\n", 68 | "plt.subplot(132)\n", 69 | "plt.imshow(img_eq,cmap='gray')\n", 70 | "\n", 71 | "plt.subplot(133)\n", 72 | "plt.imshow(img_eq1,cmap='gray')\n", 73 | "\n" 74 | ] 75 | } 76 | ], 77 | "metadata": { 78 | "kernelspec": { 79 | "display_name": "Python 3 (ipykernel)", 80 | "language": "python", 81 | "name": "python3" 82 | }, 83 | "language_info": { 84 | "codemirror_mode": { 85 | "name": "ipython", 86 | "version": 3 87 | }, 88 | "file_extension": ".py", 89 | "mimetype": "text/x-python", 90 | "name": "python", 91 | "nbconvert_exporter": "python", 92 | "pygments_lexer": "ipython3", 93 | "version": "3.10.12" 94 | } 95 | }, 96 | "nbformat": 4, 97 | "nbformat_minor": 5 98 | } 99 | -------------------------------------------------------------------------------- /S4/9.Ideal_highpass_filter_in_frequency_domain.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [ 3 | { 4 | "cell_type": "code", 5 | "execution_count": 1, 6 | "id": "e38a2735-e5cd-4942-9fbc-e943a0148b96", 7 | "metadata": {}, 8 | "outputs": [], 9 | "source": [ 10 | "import numpy as np\n", 11 | "import cv2\n", 12 | "import matplotlib.pyplot as plt\n" 13 | ] 14 | }, 15 | { 16 | "cell_type": "markdown", 17 | "id": "a6871a65-a31e-4863-ac83-68889703cead", 18 | "metadata": { 19 | "id": "rm6cHyMjhVJY" 20 | }, 21 | "source": [ 22 | "### Ideal high pass filter" 23 | ] 24 | }, 25 | { 26 | "cell_type": "code", 27 | "execution_count": 4, 28 | "id": "75b8a6dd-dd04-4e5e-b333-76ec98fc155c", 29 | "metadata": { 30 | "colab": { 31 | "base_uri": "https://localhost:8080/", 32 | "height": 375 33 | }, 34 | "id": "i08LiljFAJR9", 35 | "outputId": "b63fc708-ba20-499c-c82c-15d5811e32bc" 36 | }, 37 | "outputs": [ 38 | { 39 | "data": { 40 | "image/png": "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\n", 41 | "text/plain": [ 42 | "
" 43 | ] 44 | }, 45 | "metadata": {}, 46 | "output_type": "display_data" 47 | } 48 | ], 49 | "source": [ 50 | "# ideal high pass filter 10 30 60 160\n", 51 | "\n", 52 | "\n", 53 | "# Get to gray color map for plots\n", 54 | "plt.gray()\n", 55 | "\n", 56 | "# Create an array for using to make Ideal high pass filter\n", 57 | "[x, y] = np.meshgrid(np.arange(-250, 250), np.arange(-250, 250))\n", 58 | "# Take square root from sum of two x and y and make new array with that\n", 59 | "D = np.sqrt(x ** 2 + y ** 2)\n", 60 | "# save filter 2D size\n", 61 | "HShape = D.shape\n", 62 | "# Reshape to (1, n) for working easy with that\n", 63 | "D = D.reshape(1, -1)\n", 64 | "# Create filter and init with zeros\n", 65 | "H1 = np.zeros(shape=HShape).reshape(1, -1)\n", 66 | "H2 = np.zeros(shape=HShape).reshape(1, -1)\n", 67 | "H3 = np.zeros(shape=HShape).reshape(1, -1)\n", 68 | "H4 = np.zeros(shape=HShape).reshape(1, -1)\n", 69 | "\n", 70 | "# Find correct range for put variables into filter\n", 71 | "x1 = (D[:, :] > 10).reshape(1, -1)\n", 72 | "x2 = (D[:, :] > 30).reshape(1, -1)\n", 73 | "x3 = (D[:, :] > 60).reshape(1, -1)\n", 74 | "x4 = (D[:, :] > 160).reshape(1, -1)\n", 75 | "\n", 76 | "# reinitialize filter to make correct high pass filter\n", 77 | "H1[np.where(x1)] = D[x1]\n", 78 | "H2[np.where(x2)] = D[x2]\n", 79 | "H3[np.where(x3)] = D[x3]\n", 80 | "H4[np.where(x4)] = D[x4]\n", 81 | "\n", 82 | "# Convert to 2D filter\n", 83 | "H1 = H1.reshape(HShape)\n", 84 | "H2 = H2.reshape(HShape)\n", 85 | "H3 = H3.reshape(HShape)\n", 86 | "H4 = H4.reshape(HShape)\n", 87 | "\n", 88 | "# Read image from file\n", 89 | "img = cv2.imread(\"/content/fig4.11.jpg\", cv2.IMREAD_GRAYSCALE)\n", 90 | "# Take Fourier transform\n", 91 | "dft = np.fft.fft2(img)\n", 92 | "imgF = np.fft.fftshift(dft)\n", 93 | "# Conv filter and mask in frequency mode\n", 94 | "M_I1 = imgF * H1\n", 95 | "M_I2 = imgF * H2\n", 96 | "M_I3 = imgF * H3\n", 97 | "M_I4 = imgF * H4\n", 98 | "\n", 99 | "# Take real part of complex number\n", 100 | "M_Id1 = np.abs(M_I1)\n", 101 | "M_Id2 = np.abs(M_I2)\n", 102 | "M_Id3 = np.abs(M_I3)\n", 103 | "M_Id4 = np.abs(M_I4)\n", 104 | "\n", 105 | "# Take log from image\n", 106 | "M_IdLog1 = np.log(1 + M_Id1)\n", 107 | "M_IdLog2 = np.log(1 + M_Id2)\n", 108 | "M_IdLog3 = np.log(1 + M_Id3)\n", 109 | "M_IdLog4 = np.log(1 + M_Id4)\n", 110 | "\n", 111 | "# Calc max of 2D image\n", 112 | "Max1 = np.max(np.max(M_IdLog1))\n", 113 | "Max2 = np.max(np.max(M_IdLog2))\n", 114 | "Max3 = np.max(np.max(M_IdLog3))\n", 115 | "Max4 = np.max(np.max(M_IdLog4))\n", 116 | "\n", 117 | "# Plot image\n", 118 | "plt.subplot(241)\n", 119 | "plt.imshow(M_IdLog1 / Max1)\n", 120 | "plt.subplot(242)\n", 121 | "plt.imshow(M_IdLog2 / Max2)\n", 122 | "plt.subplot(243)\n", 123 | "plt.imshow(M_IdLog3 / Max3)\n", 124 | "plt.subplot(244)\n", 125 | "plt.imshow(M_IdLog4 / Max4)\n", 126 | "\n", 127 | "# Return from frequency to place\n", 128 | "IFFT1 = np.fft.ifft2(np.fft.ifftshift(M_I1))\n", 129 | "IFFT2 = np.fft.ifft2(np.fft.ifftshift(M_I2))\n", 130 | "IFFT3 = np.fft.ifft2(np.fft.ifftshift(M_I3))\n", 131 | "IFFT4 = np.fft.ifft2(np.fft.ifftshift(M_I4))\n", 132 | "\n", 133 | "# Take real part of complex number\n", 134 | "IFFTt1 = np.abs(IFFT1)\n", 135 | "IFFTt2 = np.abs(IFFT2)\n", 136 | "IFFTt3 = np.abs(IFFT3)\n", 137 | "IFFTt4 = np.abs(IFFT4)\n", 138 | "\n", 139 | "# Calc max of 2D image\n", 140 | "Max21 = np.max(np.max(IFFTt1))\n", 141 | "Max22 = np.max(np.max(IFFTt2))\n", 142 | "Max23 = np.max(np.max(IFFTt3))\n", 143 | "Max24 = np.max(np.max(IFFTt4))\n", 144 | "\n", 145 | "# Plot image\n", 146 | "plt.subplot(245)\n", 147 | "plt.imshow(IFFTt1 / Max21)\n", 148 | "plt.subplot(246)\n", 149 | "plt.imshow(IFFTt2 / Max22)\n", 150 | "plt.subplot(247)\n", 151 | "plt.imshow(IFFTt3 / Max23)\n", 152 | "plt.subplot(248)\n", 153 | "plt.imshow(IFFTt4 / Max24)\n", 154 | "plt.show()\n" 155 | ] 156 | } 157 | ], 158 | "metadata": { 159 | "kernelspec": { 160 | "display_name": "Python 3 (ipykernel)", 161 | "language": "python", 162 | "name": "python3" 163 | }, 164 | "language_info": { 165 | "codemirror_mode": { 166 | "name": "ipython", 167 | "version": 3 168 | }, 169 | "file_extension": ".py", 170 | "mimetype": "text/x-python", 171 | "name": "python", 172 | "nbconvert_exporter": "python", 173 | "pygments_lexer": "ipython3", 174 | "version": "3.10.12" 175 | } 176 | }, 177 | "nbformat": 4, 178 | "nbformat_minor": 5 179 | } 180 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/1.Turbulence _noise-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | img = imread('Fig_5_25.tif'); 6 | [M, N] = size(img); 7 | Distortion = zeros(M, N); 8 | k_val = [0.001, 0.0025, 0.1]; 9 | for i = 1:numel(k_val) 10 | k = k_val(i); 11 | for u = 1:M 12 | for v = 1:N 13 | 14 | H_uv = exp(-k * ((u - M/2)^2 + (v - N/2)^2)^(5/6)); 15 | Distortion(u, v) = H_uv; 16 | end 17 | end 18 | Distorted_image = double(img) .* Distortion; 19 | figure; 20 | imshow(uint8(Distorted_image)); 21 | title(sprintf('k = %.4f', k)); 22 | end 23 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/2.Motion_blur-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('cameraman.tif'); 7 | fft_image = fft2(img); 8 | 9 | % motion blur 10 | motion_length = 5; 11 | motion_angle = 0; 12 | T = 0.1; 13 | [M, N] = size(fft_image); 14 | u = 1:M; 15 | v = 1:N; 16 | U = u - M/2; 17 | V = v - N/2; 18 | theta = motion_angle * pi/180; 19 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 20 | 21 | blurred_fft_image = fft_image .* H_uv; 22 | blurred_image = ifft2(blurred_fft_image); 23 | figure; 24 | imshow(uint8(abs(blurred_image))); 25 | title('motion blur'); 26 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/3.Motion_blur_in_frequency_domain-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('cameraman.tif'); 7 | 8 | %motion blur 9 | motion_length = 5; 10 | motion_angle = 0; 11 | h = fspecial('motion', motion_length, motion_angle); 12 | blurred_image = imfilter(img, h, 'conv', 'circular'); 13 | figure; 14 | imshow(blurred_image); 15 | 16 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/4.Turbulence_noise_removal_using_inverse_filtering-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | 7 | img = imread('Fig_5_27.tif'); 8 | [M, N] = size(img); 9 | motion_length = 5; 10 | motion_angle = 0; 11 | T = 0.1; 12 | u = 1:M; 13 | v = 1:N; 14 | U = u - M/2; 15 | V = v - N/2; 16 | theta = motion_angle * pi/180; 17 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 18 | fft_image = fft2(img); 19 | fft_h = fft2(H_uv); 20 | filtered_fft_image = fft_image ./ fft_h; 21 | filtered_image = ifft2(filtered_fft_image); 22 | figure; 23 | imshow(uint8(abs(filtered_image))); 24 | title('inverse filter'); 25 | 26 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/5.Inverse_filtering_in_frequency_domain-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | 7 | img = imread('cameraman.tif'); 8 | R = 40; 9 | fft_image = fft2(img); 10 | [M, N] = size(img); 11 | half_M = floor(M/2); 12 | half_N = floor(N/2); 13 | mask = zeros(M, N); 14 | for u = 1:M 15 | for v = 1:N 16 | if sqrt((u-half_M)^2 + (v-half_N)^2) < R 17 | mask(u, v) = 1; 18 | end 19 | end 20 | end 21 | filtered_fft_image = fft_image ./ mask; 22 | filtered_image = ifft2(filtered_fft_image); 23 | figure; 24 | imshow(uint8(abs(filtered_image))); 25 | 26 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/6.Motion_blur_removal_using_wiener_filter-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('test.tif'); 7 | k = 0.1; 8 | [M, N] = size(img); 9 | motion_length = 5; 10 | motion_angle = 0; 11 | T = 0.1; 12 | H_uv = zeros(M, N); 13 | u = 1:M; 14 | v = 1:N; 15 | U = u - M/2; 16 | V = v - N/2; 17 | theta = motion_angle * pi/180; 18 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 19 | fft_image = fft2(img); 20 | fft_h = fft2(H_uv); 21 | khat = k ./ abs(fft_h).^2; 22 | % wiener 23 | filtered_fft_image = khat .* fft_image; 24 | filtered_image = ifft2(filtered_fft_image); 25 | figure; 26 | imshow(uint8(abs(filtered_image))); 27 | title('Wiener'); 28 | -------------------------------------------------------------------------------- /S5/Matlab/.ipynb_checkpoints/7.Gaussian_noise_removal_using_adaptive_local_mean-checkpoint.m: -------------------------------------------------------------------------------- 1 | 2 | %% s5 3 | clc; 4 | clear all; 5 | 6 | % MATLAB CODE for Adaptive filtering- Local Noise filter 7 | X = imread('cameraman.tif'); 8 | Y = X; 9 | sz = size(Y,1)*size(Y,2); 10 | 11 | % Add gaussian noise with mean 0 and variance 0.010 12 | y = imnoise(Y,'gaussian',0,0.05); 13 | figure,imshow(y); title('Image with gaussian noise'); 14 | 15 | y = double(y); 16 | 17 | % Define the window size mxn 18 | U = 10; 19 | V = 10; 20 | 21 | % Fill the matrix up on all sides with zeros. 22 | Z = padarray(Y,[floor(N/2),floor(M/2)]); 23 | 24 | lvar = zeros([size(y,1) size(y,2)]); 25 | lmean = zeros([size(y,1) size(y,2)]); 26 | temp = zeros([size(y,1) size(y,2)]); 27 | NewImg = zeros([size(y,1) size(y,2)]); 28 | 29 | for i = 1:size(Z,1)-(N-1) 30 | for j = 1:size(Z,2)-(M-1) 31 | 32 | temp = Z(i:i+(N-1),j:j+(M-1)); 33 | tmp = temp(:); 34 | % Determine the region's local mean and variance. 35 | lmean(i,j) = mean(tmp); 36 | lvar(i,j) = mean(tmp.^2)-mean(tmp).^2; 37 | 38 | end 39 | end 40 | 41 | % Commotion fluctuation and normal 42 | % of the neighborhood change 43 | nvar = sum(lvar(:))/sz; 44 | 45 | % If noise_variance > local_variance 46 | % then local_variance=noise_variance 47 | lvar = max(lvar,nvar); 48 | 49 | % Final_Image = Y- (noise variance/ 50 | % local variance)*(Y-local_mean); 51 | NewImg = nvar./lvar; 52 | NewImg = NewImg.*(Y-lmean); 53 | NewImg = Y-NewImg; 54 | 55 | % Convert the image to uint9 format. 56 | NewImg = uint9(NewImg); 57 | figure,imshow(NewImg);title('Restored Image using Adaptive Local filter'); -------------------------------------------------------------------------------- /S5/Matlab/1.Turbulence _noise.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | img = imread('Fig_5_25.tif'); 6 | [M, N] = size(img); 7 | Distortion = zeros(M, N); 8 | k_val = [0.001, 0.0025, 0.1]; 9 | for i = 1:numel(k_val) 10 | k = k_val(i); 11 | for u = 1:M 12 | for v = 1:N 13 | 14 | H_uv = exp(-k * ((u - M/2)^2 + (v - N/2)^2)^(5/6)); 15 | Distortion(u, v) = H_uv; 16 | end 17 | end 18 | Distorted_image = double(img) .* Distortion; 19 | figure; 20 | imshow(uint8(Distorted_image)); 21 | title(sprintf('k = %.4f', k)); 22 | end 23 | -------------------------------------------------------------------------------- /S5/Matlab/2.Motion_blur.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('cameraman.tif'); 7 | fft_image = fft2(img); 8 | 9 | % motion blur 10 | motion_length = 5; 11 | motion_angle = 0; 12 | T = 0.1; 13 | [M, N] = size(fft_image); 14 | u = 1:M; 15 | v = 1:N; 16 | U = u - M/2; 17 | V = v - N/2; 18 | theta = motion_angle * pi/180; 19 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 20 | 21 | blurred_fft_image = fft_image .* H_uv; 22 | blurred_image = ifft2(blurred_fft_image); 23 | figure; 24 | imshow(uint8(abs(blurred_image))); 25 | title('motion blur'); 26 | -------------------------------------------------------------------------------- /S5/Matlab/3.Motion_blur_in_frequency_domain.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('cameraman.tif'); 7 | 8 | %motion blur 9 | motion_length = 5; 10 | motion_angle = 0; 11 | h = fspecial('motion', motion_length, motion_angle); 12 | blurred_image = imfilter(img, h, 'conv', 'circular'); 13 | figure; 14 | imshow(blurred_image); 15 | 16 | -------------------------------------------------------------------------------- /S5/Matlab/4.Turbulence_noise_removal_using_inverse_filtering.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | 7 | img = imread('Fig_5_27.tif'); 8 | [M, N] = size(img); 9 | motion_length = 5; 10 | motion_angle = 0; 11 | T = 0.1; 12 | u = 1:M; 13 | v = 1:N; 14 | U = u - M/2; 15 | V = v - N/2; 16 | theta = motion_angle * pi/180; 17 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 18 | fft_image = fft2(img); 19 | fft_h = fft2(H_uv); 20 | filtered_fft_image = fft_image ./ fft_h; 21 | filtered_image = ifft2(filtered_fft_image); 22 | figure; 23 | imshow(uint8(abs(filtered_image))); 24 | title('inverse filter'); 25 | 26 | -------------------------------------------------------------------------------- /S5/Matlab/5.Inverse_filtering_in_frequency_domain.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | 7 | img = imread('cameraman.tif'); 8 | R = 40; 9 | fft_image = fft2(img); 10 | [M, N] = size(img); 11 | half_M = floor(M/2); 12 | half_N = floor(N/2); 13 | mask = zeros(M, N); 14 | for u = 1:M 15 | for v = 1:N 16 | if sqrt((u-half_M)^2 + (v-half_N)^2) < R 17 | mask(u, v) = 1; 18 | end 19 | end 20 | end 21 | filtered_fft_image = fft_image ./ mask; 22 | filtered_image = ifft2(filtered_fft_image); 23 | figure; 24 | imshow(uint8(abs(filtered_image))); 25 | 26 | -------------------------------------------------------------------------------- /S5/Matlab/6.Motion_blur_removal_using_wiener_filter.m: -------------------------------------------------------------------------------- 1 | 2 | 3 | %% s5 4 | 5 | 6 | img = imread('test.tif'); 7 | k = 0.1; 8 | [M, N] = size(img); 9 | motion_length = 5; 10 | motion_angle = 0; 11 | T = 0.1; 12 | H_uv = zeros(M, N); 13 | u = 1:M; 14 | v = 1:N; 15 | U = u - M/2; 16 | V = v - N/2; 17 | theta = motion_angle * pi/180; 18 | H_uv = T * (sinc(U * T) .* exp(-1i * pi * V * T * tan(theta))); 19 | fft_image = fft2(img); 20 | fft_h = fft2(H_uv); 21 | khat = k ./ abs(fft_h).^2; 22 | % wiener 23 | filtered_fft_image = khat .* fft_image; 24 | filtered_image = ifft2(filtered_fft_image); 25 | figure; 26 | imshow(uint8(abs(filtered_image))); 27 | title('Wiener'); 28 | -------------------------------------------------------------------------------- /S5/Matlab/7.Gaussian_noise_removal_using_adaptive_local_mean.m: -------------------------------------------------------------------------------- 1 | 2 | %% s5 3 | clc; 4 | clear all; 5 | 6 | % MATLAB CODE for Adaptive filtering- Local Noise filter 7 | X = imread('cameraman.tif'); 8 | Y = X; 9 | sz = size(Y,1)*size(Y,2); 10 | 11 | % Add gaussian noise with mean 0 and variance 0.010 12 | y = imnoise(Y,'gaussian',0,0.05); 13 | figure,imshow(y); title('Image with gaussian noise'); 14 | 15 | y = double(y); 16 | 17 | % Define the window size mxn 18 | U = 10; 19 | V = 10; 20 | 21 | % Fill the matrix up on all sides with zeros. 22 | Z = padarray(Y,[floor(N/2),floor(M/2)]); 23 | 24 | lvar = zeros([size(y,1) size(y,2)]); 25 | lmean = zeros([size(y,1) size(y,2)]); 26 | temp = zeros([size(y,1) size(y,2)]); 27 | NewImg = zeros([size(y,1) size(y,2)]); 28 | 29 | for i = 1:size(Z,1)-(N-1) 30 | for j = 1:size(Z,2)-(M-1) 31 | 32 | temp = Z(i:i+(N-1),j:j+(M-1)); 33 | tmp = temp(:); 34 | % Determine the region's local mean and variance. 35 | lmean(i,j) = mean(tmp); 36 | lvar(i,j) = mean(tmp.^2)-mean(tmp).^2; 37 | 38 | end 39 | end 40 | 41 | % Commotion fluctuation and normal 42 | % of the neighborhood change 43 | nvar = sum(lvar(:))/sz; 44 | 45 | % If noise_variance > local_variance 46 | % then local_variance=noise_variance 47 | lvar = max(lvar,nvar); 48 | 49 | % Final_Image = Y- (noise variance/ 50 | % local variance)*(Y-local_mean); 51 | NewImg = nvar./lvar; 52 | NewImg = NewImg.*(Y-lmean); 53 | NewImg = Y-NewImg; 54 | 55 | % Convert the image to uint9 format. 56 | NewImg = uint9(NewImg); 57 | figure,imshow(NewImg);title('Restored Image using Adaptive Local filter'); -------------------------------------------------------------------------------- /S5/Python/.ipynb_checkpoints/8.Salt_and_pepper_noise_removal_using_arithmetic_mean_filter-checkpoint.ipynb: -------------------------------------------------------------------------------- 1 | { 2 | "cells": [], 3 | "metadata": {}, 4 | "nbformat": 4, 5 | "nbformat_minor": 5 6 | } 7 | --------------------------------------------------------------------------------