refactored figure detection once

vidocp/figure_detection.py

@@ -18,11 +18,29 @@ def is_likely_figure(cont, min_area=5000, max_width_to_hight_ratio=6):
     return is_large_enough(cont, min_area) and has_acceptable_format(cont, max_width_to_hight_ratio)
 
 
-def detect_figures(image: np.array):
+def remove_primary_text_regions(image):
+    """Removes regions of primary text, meaning no figure descriptions for example, but main text body paragraphs.
+
+    Args:
+        image: Image to remove primary text from.
+
+    Returns:
+        Image with primary text removed.
+
+    References:
+        https://stackoverflow.com/questions/58349726/opencv-how-to-remove-text-from-background
+    """
+
+    def filter_likely_primary_text_segments(cnts):
+        for c in cnts:
+            area = cv2.contourArea(c)
+            if area > 800 and area < 15000:
+                yield cv2.boundingRect(c)
 
     image = image.copy()
 
     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
     thresh = cv2.threshold(gray, 253, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
 
     close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20, 3))
@@ -33,16 +51,19 @@ def detect_figures(image: np.array):
 
     cnts, _ = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
 
-    def filter_rects():
-        for c in cnts:
-            area = cv2.contourArea(c)
-            if area > 800 and area < 15000:
-                yield cv2.boundingRect(c)
-
-    for rect in filter_rects():
+    for rect in filter_likely_primary_text_segments(cnts):
         x, y, w, h = rect
         cv2.rectangle(image, (x, y), (x + w, y + h), (255, 255, 255), -1)
 
+    return image
+
+
+def __detect_large_coherent_structures(image: np.array):
+    """Detects large coherent structures on an image.
+   
+    References:
+         https://stackoverflow.com/questions/60259169/how-to-group-nearby-contours-in-opencv-python-zebra-crossing-detection
+    """
     gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
 
     thresh = cv2.threshold(gray, 253, 255, cv2.THRESH_BINARY)[1]
@@ -55,8 +76,18 @@ def detect_figures(image: np.array):
 
     cnts, _ = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
 
+    return cnts
+
+
+def detect_figures(image: np.array):
+
+    image = image.copy()
+
+    image = remove_primary_text_regions(image)
+    cnts = __detect_large_coherent_structures(image)
+
     cnts = filter(is_likely_figure, cnts)
-    rects = [cv2.boundingRect(c) for c in cnts]
+    rects = map(cv2.boundingRect, cnts)
     rects = remove_included(rects)
 
     return rects