Pull request #1: added box detection logic to find previous redactions

Merge in RR/table_parsing from box_detection to master

* commit 'ed0c38e32d7add1f194ad28d848aa8b85c2a1e58':
  added box detection logic to find previous redactions

box_detection/box_detection.py

@@ -0,0 +1,42 @@
+from itertools import count
+
+import cv2
+import imutils
+import numpy as np
+import pdf2image
+from matplotlib import pyplot as plt
+
+
+def parse(image: np.array):
+    gray = ~cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    blurred = cv2.GaussianBlur(gray, (5, 5), 1)
+    thresh = cv2.threshold(blurred, 253, 255, cv2.THRESH_BINARY)[1]
+    cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+    cnts = imutils.grab_contours(cnts)
+
+    for c in cnts:
+        peri = cv2.arcLength(c, True)
+        approx = cv2.approxPolyDP(c, 0.04 * peri, True)
+        yield cv2.boundingRect(approx)
+
+
+def annotate_boxes(image, rects):
+    for rect in rects:
+        (x, y, w, h) = rect
+        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), 2)
+
+    return image
+
+
+def annotate_boxes_in_pdf(pdf_path, page_index=1):
+
+    page = pdf2image.convert_from_path(pdf_path, first_page=page_index + 1, last_page=page_index + 1)[0]
+    page = np.array(page)
+
+    asd = parse(page)
+    page = annotate_boxes(page, asd)
+
+    fig, ax = plt.subplots(1, 1)
+    fig.set_size_inches(20, 20)
+    ax.imshow(page)
+    plt.show()

requirements.txt

@@ -2,3 +2,4 @@ opencv-python~=4.5.5.62
 numpy~=1.22.1
 pdf2image~=1.16.0
 matplotlib~=3.5.1
+imutils==0.5.4

scripts/annotate.py

@@ -0,0 +1,24 @@
+import argparse
+
+from table_parsing.table_parsig import annotate_tables_in_pdf
+from box_detection.box_detection import annotate_boxes_in_pdf
+
+
+def parse_args():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("pdf_path")
+    parser.add_argument("page_index", type=int)
+    parser.add_argument("--object", choices=["table", "box"], default="table")
+
+    args = parser.parse_args()
+
+    return args
+
+
+if __name__ == "__main__":
+    args = parse_args()
+    if args.object == "table":
+        annotate_tables_in_pdf(args.pdf_path, page_index=args.page_index)
+    elif args.object == "box":
+        annotate_boxes_in_pdf(args.pdf_path, page_index=args.page_index)
+

scripts/annotate_table.py

@@ -1,18 +0,0 @@
-import argparse
-
-from table_parsing.table_parsig import annotate_tables_in_pdf
-
-
-def parse_args():
-    parser = argparse.ArgumentParser()
-    parser.add_argument("pdf_path")
-    parser.add_argument("page_index", type=int)
-
-    args = parser.parse_args()
-
-    return args
-
-
-if __name__ == "__main__":
-    args = parse_args()
-    annotate_tables_in_pdf(args.pdf_path, page_index=args.page_index)