You need to have installed the following libraries
\n", "\n", "- numpy\n", "- matplotlib\n", "- scikit-image\n", "- scipy\n", "- Pillow" ], "metadata": { "id": "HOmELdih4eSM" } }, { "cell_type": "markdown", "source": [ "# Imports" ], "metadata": { "id": "vy2f9IlA3HHs" } }, { "cell_type": "code", "execution_count": 92, "metadata": { "id": "Jkq7SyO_2o-O" }, "outputs": [], "source": [ "import matplotlib.pyplot as plot\n", "import matplotlib.image as image\n", "import numpy as np\n", "from skimage import io\n", "from skimage.transform import rescale, resize, downscale_local_mean\n", "from skimage.color import rgb2gray, rgb2hsv\n", "from skimage.filters import threshold_otsu\n", "from PIL import Image" ] }, { "cell_type": "markdown", "source": [ "# Read Image (local directory)\n", "\n", "- With matplotlib\n", "- With skimage\n", "- With Pillow" ], "metadata": { "id": "6OuEh_Yu4D6V" } }, { "cell_type": "code", "source": [ "# read an image with matplotlib\n", "img = image.imread('cameraman.tif'); # GrayScale image\n", "# read image with skimage lib\n", "img2 = io.imread('cameraman.tif'); # GrayScale image\n", "# read image with Pillow\n", "imgP = Image.open(\"cameraman.tif\")" ], "metadata": { "id": "Cbh-A08C3v-e" }, "execution_count": 93, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Image attributes\n", "\n", "- object type\n", "- image size\n", "- image shape" ], "metadata": { "id": "OFcNlYjfZOrV" } }, { "cell_type": "code", "source": [ "# type\n", "type(img)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "4frc-HKFZTpW", "outputId": "5a741fe7-2c6f-45ec-b4be-216fedbd69c2" }, "execution_count": 94, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "numpy.ndarray" ] }, "metadata": {}, "execution_count": 94 } ] }, { "cell_type": "code", "source": [ "# size\n", "img.size" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "IgBzXuVJZ7ol", "outputId": "22ad017a-a772-4a7f-e9b7-c4cbdef9b523" }, "execution_count": 95, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "65536" ] }, "metadata": {}, "execution_count": 95 } ] }, { "cell_type": "code", "source": [ "# shape\n", "img.shape" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "0JeHWv6YaAVQ", "outputId": "1345f6b4-83b4-4825-f1aa-93185b3020d0" }, "execution_count": 96, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "(256, 256)" ] }, "metadata": {}, "execution_count": 96 } ] }, { "cell_type": "markdown", "source": [ "# Display Image\n", "\n", "- With default RGB 256 levels\n", "- With Grascale" ], "metadata": { "id": "fo8SA_vA5dA1" } }, { "cell_type": "markdown", "source": [ "## matplotlib.pyplot.imshow(f,cmap=“String” )\n", "\n", "where f is an image matrix and cmap=“String” is the number of intensity levels. If cmap is omitted the default is RGB 256 levels.\n", "\n", "With the following structure:\n", "plt.imshow(f,cmap = \"gray\",vmin=NUMBER, vmax=NUMBER)\n", "- All values less than vmin are shown in black\n", "- All values greater than vmax are displayed in white\n", "- Intermediate values with shades of gray (8bit->256 shades)\n", "- In this way we can display images with a low dynamic range or with positive and negative matrix values." ], "metadata": { "id": "zuiqpGtIcOIN" } }, { "cell_type": "code", "source": [ "plot.imshow(img) # default cmap RGB 256" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 287 }, "id": "a6iQpLGh54UK", "outputId": "8e2f33b3-9a0a-4538-ca28-68a4a2208871" }, "execution_count": 97, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Rescale operation resizes an image by a given scaling factor. The scaling factoe can either be a floating point value, or multiple values - ine along each axis.
" ], "metadata": { "id": "g3WjguO067FQ" } }, { "cell_type": "markdown", "source": [ "### Distortion\n", "anti-aliasing = false
" ], "metadata": { "id": "M6JR3_vE8p4o" } }, { "cell_type": "code", "source": [ "image_rescaled = rescale(img, 0.2, anti_aliasing=False)\n", "plot.imshow(image_rescaled, cmap='gray')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 285 }, "id": "hwV6DRpD64MN", "outputId": "8515512c-e1e7-4ff7-e587-73d206fcae4d" }, "execution_count": 104, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "anti-aliasing = true
" ], "metadata": { "id": "yKTx_ykl9ERA" } }, { "cell_type": "code", "source": [ "image_rescaled = rescale(img, 0.2, anti_aliasing=True)\n", "plot.imshow(image_rescaled, cmap='gray')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 285 }, "id": "aiwC0Qmu82S9", "outputId": "03f8d3ac-8b33-43de-e784-bb3393bb166a" }, "execution_count": 105, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Downscale serves the purpose of down-sampling an n-dimensional image by integer factors using local mean on the elements of each block of the size factors given as a parameter to the function
" ], "metadata": { "id": "T9OlUFVj9o3e" } }, { "cell_type": "code", "source": [ "image_downscaled = downscale_local_mean(img, (4, 3))\n", "\n", "plot.imshow(image_downscaled, cmap='gray')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 286 }, "id": "ECQO1J2b-KE9", "outputId": "bfb06935-8198-4db4-86f5-c86b78dfec46" }, "execution_count": 106, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Computes the bit-wise NOT of the underlying binary representation of the integers in the input arrays.
" ], "metadata": { "id": "m7vPEw0u-nDY" } }, { "cell_type": "code", "source": [ "negative_img=np.invert(img)\n", "plot.suptitle(\"Inverted Image\")\n", "plot.imshow(negative_img, cmap = \"gray\")" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 312 }, "id": "SGLG_Y4J-Sqs", "outputId": "a01b9c78-5802-4661-e7f8-07577b60e5ed" }, "execution_count": 107, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "To be able to convert an RGB image to grayscale, we need to\n", "follow the following procedure (Custom Function)
\n", "\n", "- Through scikit-image\n", "from skimage.color import rgb2gray
\n" ], "metadata": { "id": "rFtsOV2tfEiE" } }, { "cell_type": "code", "source": [ "# RGB to Grayscale\n", "def rgb2gray_(rgbImage):\n", " \"\"\"\n", " print('RGB IMAGE')\n", " print(rgbImage)\n", " \"\"\"\n", " r, g, b = rgbImage[:,:,0], rgbImage[:,:,1], rgbImage[:,:,2]\n", " \"\"\"\n", " print('\\nR VALUES')\n", " print(r)\n", " print('\\nG VALUES')\n", " print(g)\n", " print('\\nB VALUES')\n", " print(b)\n", " \"\"\"\n", " grayImage = 0.2989 * r + 0.5870 * g + 0.1140 * b\n", " return grayImage" ], "metadata": { "id": "xBl4GV3cfDuy" }, "execution_count": 109, "outputs": [] }, { "cell_type": "markdown", "source": [ "### Read an RGB Image" ], "metadata": { "id": "Rs_x4ioGuZae" } }, { "cell_type": "code", "source": [ "RGB_image = image.imread('football.jpg')" ], "metadata": { "id": "KekdDaO6uYRH" }, "execution_count": 110, "outputs": [] }, { "cell_type": "code", "source": [ "Grayscale__image = rgb2gray_(RGB_image) # custom function \n", "Grayscale__image_scikit_image = rgb2gray(RGB_image) # scikit image function" ], "metadata": { "id": "EtkBa-ncibKC" }, "execution_count": 111, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Setup Grayscale image matrix" ], "metadata": { "id": "5NV51-O7v6eX" } }, { "cell_type": "code", "source": [ "# Evenly round to the given number of decimals.\n", "Grayscale__image = np.around(Grayscale__image)\n", "# convert to unsigned 8bit int\n", "Grayscale__image = np.uint8(Grayscale__image)" ], "metadata": { "id": "Lv7SJ5Erv6FA" }, "execution_count": 112, "outputs": [] }, { "cell_type": "markdown", "source": [ "# Display RGB Image matrix" ], "metadata": { "id": "ZVk5fCRqurl5" } }, { "cell_type": "code", "source": [ "RGB_image" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "qGInmkm8i1gd", "outputId": "f2c63f36-6376-4706-98aa-8b336f628334" }, "execution_count": 113, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "array([[[ 47, 87, 113],\n", " [ 41, 81, 107],\n", " [ 33, 73, 99],\n", " ...,\n", " [ 39, 82, 114],\n", " [ 32, 75, 107],\n", " [ 27, 71, 100]],\n", "\n", " [[ 36, 73, 100],\n", " [ 38, 75, 102],\n", " [ 39, 79, 105],\n", " ...,\n", " [ 33, 76, 108],\n", " [ 29, 73, 102],\n", " [ 34, 78, 107]],\n", "\n", " [[ 34, 71, 98],\n", " [ 30, 67, 94],\n", " [ 36, 73, 100],\n", " ...,\n", " [ 36, 79, 111],\n", " [ 32, 76, 105],\n", " [ 36, 77, 107]],\n", "\n", " ...,\n", "\n", " [[ 39, 84, 107],\n", " [ 23, 68, 91],\n", " [ 16, 61, 84],\n", " ...,\n", " [ 34, 76, 100],\n", " [ 31, 76, 99],\n", " [ 27, 72, 95]],\n", "\n", " [[ 21, 66, 89],\n", " [ 18, 63, 86],\n", " [ 31, 76, 99],\n", " ...,\n", " [ 31, 73, 97],\n", " [ 32, 77, 100],\n", " [ 27, 72, 95]],\n", "\n", " [[ 24, 70, 93],\n", " [ 31, 76, 99],\n", " [ 24, 69, 90],\n", " ...,\n", " [ 23, 65, 89],\n", " [ 28, 73, 96],\n", " [ 24, 69, 92]]], dtype=uint8)" ] }, "metadata": {}, "execution_count": 113 } ] }, { "cell_type": "markdown", "source": [ "# Display Grayscale Image matrix" ], "metadata": { "id": "xd2vjnXFvhvy" } }, { "cell_type": "code", "source": [ "Grayscale__image" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "ETe8sMtcvarS", "outputId": "902c971f-8f64-4f28-dacf-39c33bde956e" }, "execution_count": 114, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "array([[78, 72, 64, ..., 73, 66, 61],\n", " [65, 67, 70, ..., 67, 63, 68],\n", " [63, 59, 65, ..., 70, 66, 68],\n", " ...,\n", " [73, 57, 50, ..., 66, 65, 61],\n", " [55, 52, 65, ..., 63, 66, 61],\n", " [59, 65, 58, ..., 55, 62, 58]], dtype=uint8)" ] }, "metadata": {}, "execution_count": 114 } ] }, { "cell_type": "markdown", "source": [ "# Display RGB and Grayscale Image Comparison" ], "metadata": { "id": "F3YrDokUwVpf" } }, { "cell_type": "code", "source": [ "plot.figure(1)\n", "\n", "subplot_1 = plot.subplot(1,2,1)\n", "plot.imshow(RGB_image)\n", "subplot_1.set_title('RGB Image')\n", "\n", "subplot_1 = plot.subplot(1,2,2)\n", "plot.imshow(Grayscale__image, cmap=\"gray\")\n", "subplot_1.set_title('Grayscale Image')" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 204 }, "id": "40iXf6P7vePZ", "outputId": "27c3b7dd-1305-474a-be7e-ba0db6365531" }, "execution_count": 115, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "Text(0.5, 1.0, 'Grayscale Image')" ] }, "metadata": {}, "execution_count": 115 }, { "output_type": "display_data", "data": { "text/plain": [ "