fixed typos

Author: jo-mueller

05_feature_extraction/01_thresholding.ipynb

@@ -5,7 +5,7 @@
    "id": "6595df14-f25f-4f5a-b631-c1abbebaa0bb",
    "metadata": {},
    "source": [
-    "# Excercise 1\n",
+    "# Exercise 1\n",
     "\n",
     "In this exercise, we will try out different threshold methods and see how they perform on the same data and create a label image from the binarized image data.\n",
     "\n",

05_feature_extraction/04_feature_extraction.ipynb

@@ -231,7 +231,7 @@
    "id": "4d43ccd8-57fc-4d56-ab91-0129ecd19278",
    "metadata": {},
    "source": [
-    "## Excercises\n",
+    "## Exercises\n",
     "\n",
     "First, let's get some sample data from scikit-image:"
    ]
@@ -275,7 +275,7 @@
    "id": "083ff201-acab-4de6-a757-5d079c7c9b50",
    "metadata": {},
    "source": [
-    "## Excercise 1\n",
+    "## Exercise 1\n",
     "\n",
     "Apply Otsu-thresholding to the image to create a binary image and then create a label image from the binary image:"
    ]
@@ -293,7 +293,7 @@
    "id": "608e6135-c74f-4953-9eb1-c3bef6409ed5",
    "metadata": {},
    "source": [
-    "## Excercise 2\n",
+    "## Exercise 2\n",
     "\n",
     "Use the `measure.regionprops_table` function to measure the area and the mean intensity for every object.\n",
     "\n",
@@ -315,7 +315,7 @@
    "id": "2c4d1be3-9f56-43e1-9fab-8d99047f60ad",
    "metadata": {},
    "source": [
-    "## Excercise 3\n",
+    "## Exercise 3\n",
     "\n",
     "The `results` variable now contains the derived measurements from the input data and is of type `dict`. \n",
     "\n",
@@ -336,7 +336,7 @@
    "id": "cd677b97-5b0e-4cc3-b7cb-5083df882f73",
    "metadata": {},
    "source": [
-    "## Excercise 4\n",
+    "## Exercise 4\n",
     "\n",
     "When we obtain measurements from image data, we usually want to visualize them and do some statistical evaluation. You have already learned to plot histograms with matplotlib - use this to visualize the distribution of areas in the image data as a histogram!\n",
     "\n",
@@ -354,7 +354,7 @@
    "id": "a27c8b12-fa4e-4c33-b839-c1b30d91a56e",
    "metadata": {},
    "source": [
-    "## Excercise 5\n",
+    "## Exercise 5\n",
     "\n",
     "Lastly, calculate a mean and standard deviation of the areas of all objects in the image. In order to do so, you need to \n",
     "\n",

05_feature_extraction/05_feature_extraction_and_thresholds.ipynb

@@ -96,7 +96,7 @@
    "id": "d4462027-e4d6-4e1f-928f-4f4cce61928a",
    "metadata": {},
    "source": [
-    "## Excercises\n",
+    "## Exercises\n",
     "\n",
     "For simplicity, we will keep on working with some relatively simple data:"
    ]
@@ -140,7 +140,7 @@
    "id": "af565d42-0cce-4563-a2e0-d6217cb6fda7",
    "metadata": {},
    "source": [
-    "## Excercise 1\n",
+    "## Exercise 1\n",
     "Now, pick three threshold methods of your choice from `skimage.filters` to create three binary images and three respective labelled images:"
    ]
   },
@@ -234,7 +234,7 @@
    "id": "64bb88d5-d1c4-41cd-a106-0bb6f0050fd5",
    "metadata": {},
    "source": [
-    "## Excercise 2:\n",
+    "## Exercise 2:\n",
     "\n",
     "Just like in the previous notebooks, we use the `regionprops_table()` function to measure several features. Use this function to measure the following features:\n",
     "\n",
@@ -264,7 +264,7 @@
    "id": "7d22632c-b196-4c78-b32e-3cabc4d208fe",
    "metadata": {},
    "source": [
-    "## Excercise 3\n",
+    "## Exercise 3\n",
     "\n",
     "Use what you learned above with regard to combining multiple curves into a single plot to see how the selection of the threshold method affects the measured results"
    ]
@@ -282,7 +282,7 @@
    "id": "895b57dd-36b2-4b18-a7c6-bf6a8762376d",
    "metadata": {},
    "source": [
-    "## Excercise 4\n",
+    "## Exercise 4\n",
     "\n",
     "In the lecture, you learned how to measure *roundness* and *circularity* of objects. Neither of these is available through `regionprops_table`, so we have to calculate them ourselves. They are defined as following:\n",
     "\n",
@@ -327,7 +327,7 @@
    "id": "8f3eb57f-0dc8-4edb-a149-c9749a5c08f1",
    "metadata": {},
    "source": [
-    "## Excercise 5\n",
+    "## Exercise 5\n",
     "\n",
     "Visualize the roundness and circularity as a histogram:"
    ]
@@ -345,7 +345,7 @@
    "id": "143d90e6-beda-4c3d-b844-c204c06d3f15",
    "metadata": {},
    "source": [
-    "## Excercise 6\n",
+    "## Exercise 6\n",
     "\n",
     "It can be interesting to plot multiple features of the measured objects with respect to each other. We can do this for any given pair of features by using the scatter plot function from matplotlib. Replace the `feature1` and `feature2` entries to do this for your measured data."
    ]