Updated tutorial

soilwater · Apr 10, 2024 · fc53dce · fc53dce
1 parent 7230e70
commit fc53dce
Show file tree

Hide file tree

Showing 10 changed files with 151 additions and 140 deletions.
diff --git a/docs/exercises/count_seeds.html b/docs/exercises/count_seeds.html
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-11-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-11-output-1.png
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-13-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-13-output-1.png
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-15-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-15-output-1.png
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-16-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-16-output-1.png
diff --git a/...eds_files/figure-html/cell-5-output-1.png → ...eds_files/figure-html/cell-6-output-1.png b/...eds_files/figure-html/cell-5-output-1.png → ...eds_files/figure-html/cell-6-output-1.png
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-7-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-7-output-1.png
diff --git a/docs/exercises/count_seeds_files/figure-html/cell-8-output-1.png b/docs/exercises/count_seeds_files/figure-html/cell-8-output-1.png
diff --git a/docs/search.json b/docs/search.json
@@ -2188,7 +2188,7 @@
     "href": "exercises/count_seeds.html",
     "title": "76  Count seeds",
     "section": "",
-    "text": "In this exercise we will learn how to use image analysis to identify and count seeds from an image collected with a mobile device.\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom skimage.filters import threshold_otsu\nfrom skimage.morphology import area_opening, disk, binary_closing\nfrom skimage.measure import find_contours, label\nfrom skimage.color import rgb2gray, label2rgb\n\n\n# Read color image\nimage_rgb = mpimg.imread('../datasets/images/rice_seeds.jpg')\n\n\n# Convert image to grayscale\nimage_gray = rgb2gray(image_rgb)\n\n\n# Visualize rgb and grayscale images\nplt.figure(figsize=(8,4))\n\nplt.subplot(1,2,1)\nplt.imshow(image_rgb)\nplt.axis('off')\nplt.title('RGB')\nplt.tight_layout()\n\nplt.subplot(1,2,2)\nplt.imshow(image_gray, cmap='gray')\nplt.axis('off')\nplt.title('Gray scale')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Segment seeds using a global automated threshold\nglobal_thresh = threshold_otsu(image_gray)\nimage_binary = image_gray &gt; global_thresh\n\n\n# Display classified seeds and grayscale threshold\nplt.figure(figsize=(12,4))\n\nplt.subplot(1,3,1)\nplt.imshow(image_gray, cmap='gray')\nplt.axis('off')\nplt.title('Original grayscale')\nplt.tight_layout()\n\nplt.subplot(1,3,2)\nplt.hist(image_gray.ravel(), bins=256)\nplt.axvline(global_thresh, color='r', linestyle='--')\nplt.title('Otsu threshold')\nplt.xlabel('Grayscale')\nplt.ylabel('Counts')\n\nplt.subplot(1,3,3)\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.title('Binary')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Invert image\nimage_binary = ~image_binary\n\n\n# Remove small areas (remove noise)\nimage_binary = area_opening(image_binary, area_threshold=1000, connectivity=2)\n\n\n# Closing (performs a dilation followed by an erosion. Connect small bright patches)\nimage_binary = binary_closing(image_binary, disk(5))\n\n# Let's inspect the structuring element\nprint(disk(5))\n\n[[0 0 0 0 0 1 0 0 0 0 0]\n [0 0 1 1 1 1 1 1 1 0 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [1 1 1 1 1 1 1 1 1 1 1]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 0 1 1 1 1 1 1 1 0 0]\n [0 0 0 0 0 1 0 0 0 0 0]]\n\n\n\n# Display inverted and denoised binary image\nplt.figure(figsize=(4,4))\n\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.title('Binary')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Identify seed boundaries\ncontours = find_contours(image_binary, 0)\n\n# Print number of seeds in image\nprint('Image contains',len(contours),'seeds')\n\nImage contains 41 seeds\n\n\n\n# Plot seed contours\nplt.figure(figsize=(4,4))\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.tight_layout()\n\nfor contour in contours:\n    plt.plot(contour[:, 1], contour[:, 0], '-r', linewidth=1.5)\n    \n\n\n\n\n\n# Label image regions\nlabel_image = label(image_binary)\nimage_label_overlay = label2rgb(label_image, image=image_binary)\n\n\n# Display image regions on top of original image\nplt.figure(figsize=(4, 4))\nplt.imshow(image_label_overlay)\nplt.tight_layout()\nplt.axis('off')\nplt.show()\n\n\n\n\n\n# Display contour for a single seed\nplt.figure(figsize=(12, 8))\n\nfor seed in range(36):\n    plt.subplot(6,6,seed+1)\n    plt.plot(contours[seed][:, 1], contours[seed][:, 0], '-r', linewidth=2)\n    plt.tight_layout()\nplt.show()"
+    "text": "In this exercise we will learn how to use image analysis to identify and count seeds from an image collected with a mobile device.\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport matplotlib.image as mpimg\n\nfrom skimage.filters import threshold_otsu\nfrom skimage.morphology import area_opening, disk, binary_closing\nfrom skimage.measure import find_contours, label\nfrom skimage.color import rgb2gray, label2rgb\n\n\n# Read color image\nimage_rgb = mpimg.imread('../datasets/images/rice_seeds.jpg')\n\n\n# Inspect image size\nprint(image_rgb.shape)\n\n(1622, 1563, 3)\n\n\n\n# Convert image to grayscale\nimage_gray = rgb2gray(image_rgb)\n\n\n# Visualize rgb and grayscale images\nplt.figure(figsize=(8,4))\n\nplt.subplot(1,2,1)\nplt.imshow(image_rgb)\nplt.axis('off')\nplt.title('RGB')\nplt.tight_layout()\n\nplt.subplot(1,2,2)\nplt.imshow(image_gray, cmap='gray')\nplt.axis('off')\nplt.title('Gray scale')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Segment seeds using a global automated threshold\nglobal_thresh = threshold_otsu(image_gray)\nimage_binary = image_gray &lt; global_thresh\n\n\n# Display classified seeds and grayscale threshold\nplt.figure(figsize=(12,4))\n\nplt.subplot(1,3,1)\nplt.imshow(image_gray, cmap='gray')\nplt.axis('off')\nplt.title('Original grayscale')\nplt.tight_layout()\n\nplt.subplot(1,3,2)\nplt.hist(image_gray.ravel(), bins=256)\nplt.axvline(global_thresh, color='r', linestyle='--')\nplt.title('Otsu threshold')\nplt.xlabel('Grayscale')\nplt.ylabel('Counts')\n\nplt.subplot(1,3,3)\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.title('Binary')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Remove small areas (remove noise)\nimage_binary = area_opening(image_binary, area_threshold=1000, connectivity=2)\n\n\n# Closing (performs a dilation followed by an erosion. Connect small bright patches)\nimage_binary = binary_closing(image_binary, disk(5))\n\n# Let's inspect the structuring element\nprint(disk(5))\n\n[[0 0 0 0 0 1 0 0 0 0 0]\n [0 0 1 1 1 1 1 1 1 0 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [1 1 1 1 1 1 1 1 1 1 1]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 1 1 1 1 1 1 1 1 1 0]\n [0 0 1 1 1 1 1 1 1 0 0]\n [0 0 0 0 0 1 0 0 0 0 0]]\n\n\n\n# Display inverted and denoised binary image\nplt.figure(figsize=(4,4))\n\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.title('Binary')\nplt.tight_layout()\n\nplt.show()\n\n\n\n\n\n# Identify seed boundaries\ncontours = find_contours(image_binary, 0)\n\n# Print number of seeds in image\nprint('Image contains',len(contours),'seeds')\n\nImage contains 41 seeds\n\n\n\n# Plot seed contours\nplt.figure(figsize=(4,4))\nplt.imshow(image_binary, cmap='gray')\nplt.axis('off')\nplt.tight_layout()\n\nfor contour in contours:\n    plt.plot(contour[:, 1], contour[:, 0], '-r', linewidth=1.5)\n    \n\n\n\n\n\n# Label image regions\nlabel_image = label(image_binary)\nimage_label_overlay = label2rgb(label_image, image=image_binary)\n\n\n# Display image regions on top of original image\nplt.figure(figsize=(4, 4))\nplt.imshow(image_label_overlay)\nplt.tight_layout()\nplt.axis('off')\nplt.show()\n\n\n\n\n\n# Display contour for a single seed\nplt.figure(figsize=(12, 8))\n\nfor seed in range(36):\n    plt.subplot(6,6,seed+1)\n    plt.plot(contours[seed][:, 1], contours[seed][:, 0], '-r', linewidth=2)\n    plt.tight_layout()\nplt.show()"
   },
   {
     "objectID": "exercises/canopy_cover.html#read-and-process-a-single-image",

diff --git a/exercises/count_seeds.ipynb b/exercises/count_seeds.ipynb