Merge 9161ef3822 into 644bbe7c6d

camelot/cli.py

@@ -100,6 +100,9 @@ def cli(ctx, *args, **kwargs):
 @click.option(
     "-back", "--process_background", is_flag=True, help="Process background lines."
 )
+@click.option(
+    "-color", "--process_color_background", is_flag=True, help="Increase contrast for better background line processing."
+)
 @click.option(
     "-scale",
     "--line_scale",

camelot/image_processing.py

@@ -4,7 +4,7 @@ import cv2
 import numpy as np
 
 
-def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2):
+def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2, process_color_background=False, saturation_threshold=5):
     """Thresholds an image using OpenCV's adaptiveThreshold.
 
     Parameters
@@ -36,6 +36,17 @@ def adaptive_threshold(imagename, process_background=False, blocksize=15, c=-2):
     gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
 
     if process_background:
+        if process_color_background:
+            hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
+            initial = hsv[:, :, 1]
+            hsv[initial > saturation_threshold, 0] = 0
+            hsv[initial > saturation_threshold, 1] = 255
+            hsv[initial > saturation_threshold, 2] = 0
+            hsv[initial <= saturation_threshold, 0] = 128
+            hsv[initial <= saturation_threshold, 1] = 0
+            hsv[initial <= saturation_threshold, 2] = 255
+            hsv[initial == 255, 1] = 0
+            gray = cv2.cvtColor(hsv, cv2.COLOR_BGR2GRAY)
         threshold = cv2.adaptiveThreshold(
             gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, blocksize, c
         )

camelot/io.py

@@ -59,6 +59,8 @@ def read_pdf(
         to generate columns.
     process_background* : bool, optional (default: False)
         Process background lines.
+    process_color_background* : bool, optional (default: False)
+        Increase contrast for better background line processing.
     line_scale* : int, optional (default: 15)
         Line size scaling factor. The larger the value the smaller
         the detected lines. Making it very large will lead to text

camelot/parsers/lattice.py

@@ -99,6 +99,7 @@ class Lattice(BaseParser):
         table_regions=None,
         table_areas=None,
         process_background=False,
+        process_color_background=False,
         line_scale=15,
         copy_text=None,
         shift_text=["l", "t"],
@@ -117,6 +118,7 @@ class Lattice(BaseParser):
         self.table_regions = table_regions
         self.table_areas = table_areas
         self.process_background = process_background
+        self.process_color_background = process_color_background
         self.line_scale = line_scale
         self.copy_text = copy_text
         self.shift_text = shift_text
@@ -255,6 +257,7 @@ class Lattice(BaseParser):
         self.image, self.threshold = adaptive_threshold(
             self.imagename,
             process_background=self.process_background,
+            process_color_background=self.process_color_background,
             blocksize=self.threshold_blocksize,
             c=self.threshold_constant,
         )

camelot/utils.py

@@ -96,6 +96,7 @@ def download_url(url):
 stream_kwargs = ["columns", "edge_tol", "row_tol", "column_tol"]
 lattice_kwargs = [
     "process_background",
+    "process_color_background",
     "line_scale",
     "copy_text",
     "shift_text",

docs/user/advanced.rst

@@ -33,6 +33,19 @@ To process background lines, you can pass ``process_background=True``.
 .. csv-table::
   :file: ../_static/csv/background_lines.csv
 
+If there's too little contrast between the table background color and the document background color, you can try combining the experimental option ``process_color_background=True``.
+
+::
+
+    >>> tables = camelot.read_pdf('background_lines.pdf', process_background=True, process_color_background=True)
+    >>> tables[1].df
+
+.. tip::
+    Here's how you can do the same with the :ref:`command-line interface <cli>`.
+    ::
+
+        $ camelot lattice -back -color background_lines.pdf
+
 Visual debugging
 ----------------