diff --git a/pdf_table_extraction_and_ocr.org b/pdf_table_extraction_and_ocr.org
index b929d92..3d2f117 100644
--- a/pdf_table_extraction_and_ocr.org
+++ b/pdf_table_extraction_and_ocr.org
@@ -3,7 +3,7 @@
 #+TITLE: PDF Parsing
 #+PROPERTY: header-args :session *Python*
 #+STARTUP: inlineimages
-#+OPTIONS: ^:nil
+#+OPTIONS: ^:nil H:4
 
 #+BEGIN_COMMENT
 Some notes about the header for those not familiar with Org Mode:
@@ -659,13 +659,13 @@ setuptools.setup(
 
 ** table_ocr
 *** table_ocr/__init__.py
-#+BEGIN_SRC python :tangle table_ocr/__init__.py :mkdirp yes :results none
+#+BEGIN_SRC python :tangle table_ocr/__init__.py :results none :exports none
 
 #+END_SRC
 
 *** table_ocr/util.py
 
-#+BEGIN_SRC python :tangle table_ocr/util.py :mkdirp yes :results none
+#+BEGIN_SRC python :tangle table_ocr/util.py :results none
 from contextlib import contextmanager
 import functools
 import logging
@@ -687,11 +687,12 @@ def working_dir(directory):
 def make_tempdir(identifier):
     return tempfile.mkdtemp(prefix="{}_".format(identifier))
 #+END_SRC
+
 *** table_ocr/pdf_to_images/
 **** table_ocr/pdf_to_images/__init__.py
 #+NAME: pdf_to_images/__init__.py
-#+HEADER: :mkdirp yes :tangle table_ocr/pdf_to_images/__init__.py
-#+BEGIN_SRC python :noweb strip-export :results none
+#+HEADER: :tangle table_ocr/pdf_to_images/__init__.py
+#+BEGIN_SRC python :results none
 import os
 import re
 import subprocess
@@ -764,14 +765,22 @@ import cv2
 
 **** table_ocr/extract_tables/__main__.py
 
-#+BEGIN_SRC shell
-. ~/.virtualenvs/lotto_odds/bin/activate
-python -m pdf.extract_tables "resources/examples/example-page.png"
-#+END_SRC
+Takes 1 or more image paths as arguments.
 
-#+RESULTS:
-| resources/examples/example-page.png           |
-| resources/examples/example-page-table-000.png |
+Images are opened and read with OpenCV.
+
+Tables are detected and extracted to a new subdirectory of the given image. The
+subdirectory will be the filename sans the extension. The tables inside that
+directory will be named ~table-000.png~.
+
+If you want to do something with the output, like pipe the paths of the
+extracted tables into some other utility, here is a description of the output.
+
+For each image path given as an agument, outputs:
+
+1. The given image path
+2. Paths of extracted tables; seperated by newlines
+3. Empty newline
 
 #+NAME: extract_tables/__main__.py
 #+BEGIN_SRC python :tangle table_ocr/extract_tables/__main__.py :results none
@@ -816,19 +825,25 @@ if __name__ == "__main__":
     main(files)
 #+END_SRC
 
-*** table_ocr/extract_cells_from_table.py
+*** table_ocr/extract_cells/
 
-#+BEGIN_SRC shell :results none
-. ~/.virtualenvs/lotto_odds/bin/activate
-python -m pdf.extract_cells_from_table "resources/examples/example-table.png"
+**** table_ocr/extract_cells/__init__.py
+
+#+BEGIN_SRC python :tangle table_ocr/extract_cells/__init__.py
+import cv2
+
+<<extract-cells-from-table>>
 #+END_SRC
 
-#+BEGIN_SRC python :noweb yes :tangle table_ocr/extract_cells_from_table.py :results none
+**** table_ocr/extract_cells/__main__.py
+
+#+BEGIN_SRC python :tangle table_ocr/extract_cells/__main__.py :results none
 import os
 import sys
 
 import cv2
-import pytesseract
+
+from table_ocr.extract_cells import extract_cell_images_from_table
 
 def main(f):
     results = []
diff --git a/table_ocr/extract_cells/__init__.py b/table_ocr/extract_cells/__init__.py
new file mode 100644
index 0000000..4fed823
--- /dev/null
+++ b/table_ocr/extract_cells/__init__.py
@@ -0,0 +1,97 @@
+import cv2
+
+def extract_cell_images_from_table(image):
+    BLUR_KERNEL_SIZE = (17, 17)
+    STD_DEV_X_DIRECTION = 0
+    STD_DEV_Y_DIRECTION = 0
+    blurred = cv2.GaussianBlur(image, BLUR_KERNEL_SIZE, STD_DEV_X_DIRECTION, STD_DEV_Y_DIRECTION)
+    MAX_COLOR_VAL = 255
+    BLOCK_SIZE = 15
+    SUBTRACT_FROM_MEAN = -2
+    
+    img_bin = cv2.adaptiveThreshold(
+        ~blurred,
+        MAX_COLOR_VAL,
+        cv2.ADAPTIVE_THRESH_MEAN_C,
+        cv2.THRESH_BINARY,
+        BLOCK_SIZE,
+        SUBTRACT_FROM_MEAN,
+    )
+    vertical = horizontal = img_bin.copy()
+    SCALE = 5
+    image_width, image_height = horizontal.shape
+    horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (int(image_width / SCALE), 1))
+    horizontally_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, horizontal_kernel)
+    vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, int(image_height / SCALE)))
+    vertically_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, vertical_kernel)
+    
+    horizontally_dilated = cv2.dilate(horizontally_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (40, 1)))
+    vertically_dilated = cv2.dilate(vertically_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (1, 60)))
+    
+    mask = horizontally_dilated + vertically_dilated
+    contours, heirarchy = cv2.findContours(
+        mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE,
+    )
+    
+    perimeter_lengths = [cv2.arcLength(c, True) for c in contours]
+    epsilons = [0.05 * p for p in perimeter_lengths]
+    approx_polys = [cv2.approxPolyDP(c, e, True) for c, e in zip(contours, epsilons)]
+    
+    # Filter out contours that aren't rectangular. Those that aren't rectangular
+    # are probably noise.
+    approx_rects = [p for p in approx_polys if len(p) == 4]
+    bounding_rects = [cv2.boundingRect(a) for a in approx_polys]
+    
+    # Filter out rectangles that are too narrow or too short.
+    MIN_RECT_WIDTH = 40
+    MIN_RECT_HEIGHT = 10
+    bounding_rects = [
+        r for r in bounding_rects if MIN_RECT_WIDTH < r[2] and MIN_RECT_HEIGHT < r[3]
+    ]
+    
+    # The largest bounding rectangle is assumed to be the entire table.
+    # Remove it from the list. We don't want to accidentally try to OCR
+    # the entire table.
+    largest_rect = max(bounding_rects, key=lambda r: r[2] * r[3])
+    bounding_rects = [b for b in bounding_rects if b is not largest_rect]
+    
+    cells = [c for c in bounding_rects]
+    def cell_in_same_row(c1, c2):
+        c1_center = c1[1] + c1[3] - c1[3] / 2
+        c2_bottom = c2[1] + c2[3]
+        c2_top = c2[1]
+        return c2_top < c1_center < c2_bottom
+    
+    orig_cells = [c for c in cells]
+    rows = []
+    while cells:
+        first = cells[0]
+        rest = cells[1:]
+        cells_in_same_row = sorted(
+            [
+                c for c in rest
+                if cell_in_same_row(c, first)
+            ],
+            key=lambda c: c[0]
+        )
+    
+        row_cells = sorted([first] + cells_in_same_row, key=lambda c: c[0])
+        rows.append(row_cells)
+        cells = [
+            c for c in rest
+            if not cell_in_same_row(c, first)
+        ]
+    
+    # Sort rows by average height of their center.
+    def avg_height_of_center(row):
+        centers = [y + h - h / 2 for x, y, w, h in row]
+        return sum(centers) / len(centers)
+    
+    rows.sort(key=avg_height_of_center)
+    cell_images_rows = []
+    for row in rows:
+        cell_images_row = []
+        for x, y, w, h in row:
+            cell_images_row.append(image[y:y+h, x:x+w])
+        cell_images_rows.append(cell_images_row)
+    return cell_images_rows
diff --git a/table_ocr/extract_cells/__main__.py b/table_ocr/extract_cells/__main__.py
new file mode 100644
index 0000000..f1daee2
--- /dev/null
+++ b/table_ocr/extract_cells/__main__.py
@@ -0,0 +1,120 @@
+import os
+import sys
+
+import cv2
+
+from table_ocr.extract_cells import extract_cell_images_from_table
+
+def main(f):
+    results = []
+    directory, filename = os.path.split(f)
+    table = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
+    rows = extract_cell_images_from_table(table)
+    cell_img_dir = os.path.join(directory, "cells")
+    os.makedirs(cell_img_dir, exist_ok=True)
+    for i, row in enumerate(rows):
+        for j, cell in enumerate(row):
+            cell_filename = "{:03d}-{:03d}.png".format(i, j)
+            path = os.path.join(cell_img_dir, cell_filename)
+            cv2.imwrite(path, cell)
+            print(path)
+
+
+def extract_cell_images_from_table(image):
+    BLUR_KERNEL_SIZE = (17, 17)
+    STD_DEV_X_DIRECTION = 0
+    STD_DEV_Y_DIRECTION = 0
+    blurred = cv2.GaussianBlur(image, BLUR_KERNEL_SIZE, STD_DEV_X_DIRECTION, STD_DEV_Y_DIRECTION)
+    MAX_COLOR_VAL = 255
+    BLOCK_SIZE = 15
+    SUBTRACT_FROM_MEAN = -2
+    
+    img_bin = cv2.adaptiveThreshold(
+        ~blurred,
+        MAX_COLOR_VAL,
+        cv2.ADAPTIVE_THRESH_MEAN_C,
+        cv2.THRESH_BINARY,
+        BLOCK_SIZE,
+        SUBTRACT_FROM_MEAN,
+    )
+    vertical = horizontal = img_bin.copy()
+    SCALE = 5
+    image_width, image_height = horizontal.shape
+    horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (int(image_width / SCALE), 1))
+    horizontally_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, horizontal_kernel)
+    vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, int(image_height / SCALE)))
+    vertically_opened = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, vertical_kernel)
+    
+    horizontally_dilated = cv2.dilate(horizontally_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (40, 1)))
+    vertically_dilated = cv2.dilate(vertically_opened, cv2.getStructuringElement(cv2.MORPH_RECT, (1, 60)))
+    
+    mask = horizontally_dilated + vertically_dilated
+    contours, heirarchy = cv2.findContours(
+        mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE,
+    )
+    
+    perimeter_lengths = [cv2.arcLength(c, True) for c in contours]
+    epsilons = [0.05 * p for p in perimeter_lengths]
+    approx_polys = [cv2.approxPolyDP(c, e, True) for c, e in zip(contours, epsilons)]
+    
+    # Filter out contours that aren't rectangular. Those that aren't rectangular
+    # are probably noise.
+    approx_rects = [p for p in approx_polys if len(p) == 4]
+    bounding_rects = [cv2.boundingRect(a) for a in approx_polys]
+    
+    # Filter out rectangles that are too narrow or too short.
+    MIN_RECT_WIDTH = 40
+    MIN_RECT_HEIGHT = 10
+    bounding_rects = [
+        r for r in bounding_rects if MIN_RECT_WIDTH < r[2] and MIN_RECT_HEIGHT < r[3]
+    ]
+    
+    # The largest bounding rectangle is assumed to be the entire table.
+    # Remove it from the list. We don't want to accidentally try to OCR
+    # the entire table.
+    largest_rect = max(bounding_rects, key=lambda r: r[2] * r[3])
+    bounding_rects = [b for b in bounding_rects if b is not largest_rect]
+    
+    cells = [c for c in bounding_rects]
+    def cell_in_same_row(c1, c2):
+        c1_center = c1[1] + c1[3] - c1[3] / 2
+        c2_bottom = c2[1] + c2[3]
+        c2_top = c2[1]
+        return c2_top < c1_center < c2_bottom
+    
+    orig_cells = [c for c in cells]
+    rows = []
+    while cells:
+        first = cells[0]
+        rest = cells[1:]
+        cells_in_same_row = sorted(
+            [
+                c for c in rest
+                if cell_in_same_row(c, first)
+            ],
+            key=lambda c: c[0]
+        )
+    
+        row_cells = sorted([first] + cells_in_same_row, key=lambda c: c[0])
+        rows.append(row_cells)
+        cells = [
+            c for c in rest
+            if not cell_in_same_row(c, first)
+        ]
+    
+    # Sort rows by average height of their center.
+    def avg_height_of_center(row):
+        centers = [y + h - h / 2 for x, y, w, h in row]
+        return sum(centers) / len(centers)
+    
+    rows.sort(key=avg_height_of_center)
+    cell_images_rows = []
+    for row in rows:
+        cell_images_row = []
+        for x, y, w, h in row:
+            cell_images_row.append(image[y:y+h, x:x+w])
+        cell_images_rows.append(cell_images_row)
+    return cell_images_rows
+
+if __name__ == "__main__":
+    main(sys.argv[1])
diff --git a/table_ocr/extract_cells_from_table.py b/table_ocr/extract_cells_from_table.py
index 6d2cc4a..393a4d3 100644
--- a/table_ocr/extract_cells_from_table.py
+++ b/table_ocr/extract_cells_from_table.py
@@ -2,7 +2,8 @@ import os
 import sys
 
 import cv2
-import pytesseract
+
+from table_ocr.extract_cells import extract_cells_from_table
 
 def main(f):
     results = []