Added ability to filter out non-greys before trying to extract the

crossword.

home/views.py

@@ -15,7 +15,10 @@ class HomeView(View):
         form = CrosswordForm(request.POST, request.FILES)
         if not form.is_valid():
             return HttpResponseBadRequest('Invalid form data')
-        image, warnings = extract_crossword(form.cleaned_data['file'].temporary_file_path())
+        image, warnings = extract_crossword(
+            form.cleaned_data['file'].temporary_file_path(),
+            filter_colours=False
+        )
         return render(request, 'home/output.html', {
             'warnings': warnings,
             'image_file_name': 'xword_{}.png'.format(datetime.now().strftime('%Y%m%d_%H%M%S')),

home/xword.py

@@ -5,6 +5,25 @@ import copy
 import argparse
 
 
+def non_greys_to_white(img, threshold=48):
+    b, g, r = cv2.split(img)
+    rgb_diff = cv2.subtract(cv2.max(cv2.max(b, g), r), cv2.min(cv2.min(b, g), r))
+    filtered = img.copy()
+    filtered[np.where(rgb_diff > threshold)] = (255, 255, 255)
+    return filtered
+
+
+def load_image_as_greyscale(file_name, filter_colours, colour_filter_threshold):
+    img = cv2.imread(file_name)
+    if img is None:
+        raise RuntimeError("Failed to load image")
+
+    if filter_colours:
+        img = non_greys_to_white(img, colour_filter_threshold)
+
+    return cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+
+
 def preprocess_image(original, gaussian_blur_size, adaptive_threshold_block_size, adaptive_threshold_mean_adjustment, num_dilations):
     img = cv2.GaussianBlur(original, (gaussian_blur_size, gaussian_blur_size), 0)
     img = cv2.adaptiveThreshold(img, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, adaptive_threshold_block_size, adaptive_threshold_mean_adjustment)
@@ -179,6 +198,8 @@ def show_image(image):
 
 def extract_crossword(
     file_name,
+    filter_colours=False,
+    colour_filter_threshold=48,
     gaussian_blur_size=11,
     adaptive_threshold_block_size=11,
     adaptive_threshold_mean_adjustment=2,
@@ -196,9 +217,7 @@ def extract_crossword(
 ):
     warnings = []
 
-    original = cv2.imread(file_name, cv2.IMREAD_GRAYSCALE)
-    if original is None:
-        raise RuntimeError("Failed to load image")
+    original = load_image_as_greyscale(file_name, filter_colours, colour_filter_threshold)
 
     img = preprocess_image(original, gaussian_blur_size, adaptive_threshold_block_size, adaptive_threshold_mean_adjustment, num_dilations)