differences for PR #315

07-thresholding.md

@@ -348,13 +348,17 @@ plt.xlim(0, 1.0)
 ![](fig/maize-root-cluster-histogram.png){alt='Grayscale histogram of the maize root image'}
 
 The histogram has a significant peak around 0.2, and a second,
-smaller peak very near 1.0.
+shallower peak near 0.6.
 Thus, this image is a good candidate for thresholding with Otsu's method.
 The mathematical details of how this works are complicated (see
 [the scikit-image documentation](https://scikit-image.org/docs/dev/api/skimage.filters.html#threshold-otsu)
 if you are interested),
 but the outcome is that Otsu's method finds a threshold value between
 the two peaks of a grayscale histogram.
+Note there is a third peak very close to 1.0 which corresponds to the white label and disk on the 
+left hand side of the image. It would be a good idea to remove these white pixels 
+before calculating the Otsu threshold. We will discuss how to do this later in the episode but for 
+now we will continue without removing them.
 
 The `ski.filters.threshold_otsu()` function can be used to determine
 the threshold automatically via Otsu's method.
@@ -462,10 +466,10 @@ def measure_root_mass(filename, sigma=1.0):
     binary_mask = blurred_image > t
 
     # determine root mass ratio
-    rootPixels = np.count_nonzero(binary_mask)
+    root_pixels = np.count_nonzero(binary_mask)
     w = binary_mask.shape[1]
     h = binary_mask.shape[0]
-    density = rootPixels / (w * h)
+    density = root_pixels / (w * h)
 
     return density
 ```
@@ -612,9 +616,8 @@ and label from the image before applying Otsu's method.
 ## Solution
 
 We can apply a simple binary thresholding with a threshold
-`t=0.95` to remove the label and circle from the image. We use the
-binary mask to set the pixels in the blurred image to zero
-(black).
+`t=0.95` to remove the label and circle from the image. We can then use the
+binary mask to calculate the Otsu threshold without the pixels from the label and circle.
 
 ```python
 def enhanced_root_mass(filename, sigma):
@@ -627,21 +630,22 @@ def enhanced_root_mass(filename, sigma):
 
     # perform binary thresholding to mask the white label and circle
     binary_mask = blurred_image < 0.95
-    # use the mask to remove the circle and label from the blurred image
-    blurred_image[~binary_mask] = 0
-
-    # perform automatic thresholding to produce a binary image
-    t = ski.filters.threshold_otsu(blurred_image)
-    binary_mask = blurred_image > t
+
+    # perform automatic thresholding using only the pixels with value True in the binary mask
+    t = ski.filters.threshold_otsu(blurred_image[binary_mask])
+
+    # update binary mask to identify pixels which are both less than 0.95 and greater than t
+    binary_mask = np.logical_and(binary_mask, blurred_image > t)
 
     # determine root mass ratio
-    rootPixels = np.count_nonzero(binary_mask)
+    root_pixels = np.count_nonzero(binary_mask)
     w = binary_mask.shape[1]
     h = binary_mask.shape[0]
-    density = rootPixels / (w * h)
+    density = root_pixels / (w * h)
 
     return density
 
+
 all_files = glob.glob("data/trial-*.jpg")
 for filename in all_files:
     density = enhanced_root_mass(filename=filename, sigma=1.5)
@@ -653,10 +657,10 @@ The output of the improved program does illustrate that the white circles
 and labels were skewing our root mass ratios:
 
 ```output
-data/trial-016.jpg,0.045935837765957444
-data/trial-020.jpg,0.058800033244680854
-data/trial-216.jpg,0.13705003324468085
-data/trial-293.jpg,0.13164461436170213
+data/trial-016.jpg,0.046250166223404256
+data/trial-020.jpg,0.05886968085106383
+data/trial-216.jpg,0.13712117686170214
+data/trial-293.jpg,0.13190342420212767
 ```
 
 Here are the binary images produced by the additional thresholding.

md5sum.txt

@@ -9,7 +9,7 @@
 "episodes/04-drawing.md" "9d78a765f5e9747ffc2aa43a4a5a414d" "site/built/04-drawing.md" "2023-09-05"
 "episodes/05-creating-histograms.md" "59c07192c0a6217e8a42d3e7365025f9" "site/built/05-creating-histograms.md" "2023-12-08"
 "episodes/06-blurring.md" "8d109bb4c49f27f54857f6d35b4c6b9a" "site/built/06-blurring.md" "2023-12-08"
-"episodes/07-thresholding.md" "7ae5260f90e1df8e20a6226cce8ec6b6" "site/built/07-thresholding.md" "2023-09-05"
+"episodes/07-thresholding.md" "f0e0f3b873b02661f14f8dd4945c6d97" "site/built/07-thresholding.md" "2023-12-11"
 "episodes/08-connected-components.md" "59d42797208c5bf569da2fa2e4dd05df" "site/built/08-connected-components.md" "2023-09-09"
 "episodes/09-challenges.md" "a3ace24af8f5cb0bda1e9379a688ad4c" "site/built/09-challenges.md" "2023-09-05"
 "instructors/instructor-notes.md" "b1c166a544eb4b9b91f3ac8f2dafd549" "site/built/instructor-notes.md" "2023-05-12"