Remove unused files, finish refactor of structure
Eric Ihli
5 years ago
parent
b911f87126
commit
4eca593944
@ -1,120 +0,0 @@
|
|||||||
import os
|
|
||||||
import sys
|
|
||||||
|
|
||||||
import cv2
|
|
||||||
|
|
||||||
from table_ocr.extract_cells import extract_cells_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])
|
|
||||||
@ -1,39 +0,0 @@
|
|||||||
import argparse
|
|
||||||
import os
|
|
||||||
|
|
||||||
import cv2
|
|
||||||
|
|
||||||
from table_ocr.extract_tables import find_tables
|
|
||||||
|
|
||||||
parser = argparse.ArgumentParser()
|
|
||||||
parser.add_argument("files", nargs="+")
|
|
||||||
|
|
||||||
|
|
||||||
def main(files):
|
|
||||||
results = []
|
|
||||||
for f in files:
|
|
||||||
directory, filename = os.path.split(f)
|
|
||||||
image = cv2.imread(f, cv2.IMREAD_GRAYSCALE)
|
|
||||||
tables = find_tables(image)
|
|
||||||
files = []
|
|
||||||
filename_sans_extension = os.path.splitext(filename)[0]
|
|
||||||
if tables:
|
|
||||||
os.makedirs(os.path.join(directory, filename_sans_extension), exist_ok=True)
|
|
||||||
for i, table in enumerate(tables):
|
|
||||||
table_filename = "table-{:03d}.png".format(i)
|
|
||||||
table_filepath = os.path.join(
|
|
||||||
directory, filename_sans_extension, table_filename
|
|
||||||
)
|
|
||||||
files.append(table_filepath)
|
|
||||||
cv2.imwrite(table_filepath, table)
|
|
||||||
if tables:
|
|
||||||
results.append((f, files))
|
|
||||||
|
|
||||||
for image_filename, table_filenames in results:
|
|
||||||
print("\n".join(table_filenames))
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
args = parser.parse_args()
|
|
||||||
files = args.files
|
|
||||||
main(files)
|
|
||||||
@ -0,0 +1,53 @@
|
|||||||
|
import math
|
||||||
|
|
||||||
|
import cv2
|
||||||
|
|
||||||
|
def crop_to_text(image):
|
||||||
|
MAX_COLOR_VAL = 255
|
||||||
|
BLOCK_SIZE = 15
|
||||||
|
SUBTRACT_FROM_MEAN = -2
|
||||||
|
|
||||||
|
img_bin = cv2.adaptiveThreshold(
|
||||||
|
~image,
|
||||||
|
MAX_COLOR_VAL,
|
||||||
|
cv2.ADAPTIVE_THRESH_MEAN_C,
|
||||||
|
cv2.THRESH_BINARY,
|
||||||
|
BLOCK_SIZE,
|
||||||
|
SUBTRACT_FROM_MEAN,
|
||||||
|
)
|
||||||
|
|
||||||
|
img_h, img_w = image.shape
|
||||||
|
horizontal_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (int(img_w * 0.5), 1))
|
||||||
|
vertical_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, int(img_h * 0.7)))
|
||||||
|
horizontal_lines = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, horizontal_kernel)
|
||||||
|
vertical_lines = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, vertical_kernel)
|
||||||
|
both = horizontal_lines + vertical_lines
|
||||||
|
cleaned = img_bin - both
|
||||||
|
|
||||||
|
# Get rid of little noise.
|
||||||
|
kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (3, 3))
|
||||||
|
opened = cv2.morphologyEx(cleaned, cv2.MORPH_OPEN, kernel)
|
||||||
|
|
||||||
|
contours, hierarchy = cv2.findContours(opened, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
|
||||||
|
bounding_rects = [cv2.boundingRect(c) for c in contours]
|
||||||
|
NUM_PX_COMMA = 6
|
||||||
|
MIN_CHAR_AREA = 5 * 9
|
||||||
|
if bounding_rects:
|
||||||
|
minx, miny, maxx, maxy = math.inf, math.inf, 0, 0
|
||||||
|
for x, y, w, h in [(x, y, w, h) for x, y, w, h in bounding_rects if w * h > MIN_CHAR_AREA]:
|
||||||
|
minx = min(minx, x)
|
||||||
|
miny = min(miny, y)
|
||||||
|
maxx = max(maxx, x + w)
|
||||||
|
maxy = max(maxy, y + h)
|
||||||
|
x, y, w, h = minx, miny, maxx - minx, maxy - miny
|
||||||
|
cropped = image[y:min(img_h, y+h+NUM_PX_COMMA), x:min(img_w, x+w)]
|
||||||
|
else:
|
||||||
|
# If we morphed out all of the text, fallback to using the unmorphed image.
|
||||||
|
cropped = image
|
||||||
|
bordered = cv2.copyMakeBorder(cropped, 5, 5, 5, 5, cv2.BORDER_CONSTANT, None, 255)
|
||||||
|
return bordered
|
||||||
|
def ocr_image(image, config):
|
||||||
|
return pytesseract.image_to_string(
|
||||||
|
image,
|
||||||
|
config=config
|
||||||
|
)
|
||||||
@ -0,0 +1,18 @@
|
|||||||
|
import argparse
|
||||||
|
import os
|
||||||
|
|
||||||
|
from table_ocr.ocr_to_csv import text_files_to_csv
|
||||||
|
|
||||||
|
parser = argparse.ArgumentParser()
|
||||||
|
parser.add_argument("files", nargs="+")
|
||||||
|
|
||||||
|
|
||||||
|
def main(files):
|
||||||
|
print(text_files_to_csv(files))
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
args = parser.parse_args()
|
||||||
|
files = args.files
|
||||||
|
files.sort()
|
||||||
|
main(files)
|
||||||
@ -1,105 +0,0 @@
|
|||||||
import argparse
|
|
||||||
import logging
|
|
||||||
import os
|
|
||||||
import re
|
|
||||||
import subprocess
|
|
||||||
import sys
|
|
||||||
|
|
||||||
from table_ocr.util import working_dir, make_tempdir
|
|
||||||
|
|
||||||
|
|
||||||
def get_logger(name):
|
|
||||||
logger = logging.getLogger(name)
|
|
||||||
lvl = os.environ.get("PY_LOG_LVL", "info").upper()
|
|
||||||
handler = logging.StreamHandler()
|
|
||||||
formatter = logging.Formatter(logging.BASIC_FORMAT)
|
|
||||||
handler.setFormatter(formatter)
|
|
||||||
logger.addHandler(handler)
|
|
||||||
handler.setLevel(lvl)
|
|
||||||
logger.setLevel(lvl)
|
|
||||||
return logger
|
|
||||||
|
|
||||||
logger = get_logger()
|
|
||||||
|
|
||||||
parser = argparse.ArgumentParser()
|
|
||||||
parser.add_argument("files", nargs="+")
|
|
||||||
|
|
||||||
def main(files):
|
|
||||||
pdf_images = []
|
|
||||||
for f in files:
|
|
||||||
pdf_images.append((f, pdf_to_images(f)))
|
|
||||||
|
|
||||||
for pdf, images in pdf_images:
|
|
||||||
for image in images:
|
|
||||||
preprocess_img(image)
|
|
||||||
|
|
||||||
for pdf, images in pdf_images:
|
|
||||||
print("{}\n{}\n".format(pdf, "\n".join(images)))
|
|
||||||
|
|
||||||
|
|
||||||
def pdf_to_images(pdf_filepath):
|
|
||||||
"""
|
|
||||||
Turn a pdf into images
|
|
||||||
"""
|
|
||||||
directory, filename = os.path.split(pdf_filepath)
|
|
||||||
with working_dir(directory):
|
|
||||||
image_filenames = pdfimages(pdf_filepath)
|
|
||||||
|
|
||||||
# Since pdfimages creates a number of files named each for there page number
|
|
||||||
# and doesn't return us the list that it created
|
|
||||||
return [os.path.join(directory, f) for f in image_filenames]
|
|
||||||
|
|
||||||
|
|
||||||
def pdfimages(pdf_filepath):
|
|
||||||
"""
|
|
||||||
Uses the `pdfimages` utility from Poppler
|
|
||||||
(https://poppler.freedesktop.org/). Creates images out of each page. Images
|
|
||||||
are prefixed by their name sans extension and suffixed by their page number.
|
|
||||||
|
|
||||||
This should work up to pdfs with 999 pages since find matching files in dir
|
|
||||||
uses 3 digits in its regex.
|
|
||||||
"""
|
|
||||||
directory, filename = os.path.split(pdf_filepath)
|
|
||||||
filename_sans_ext = filename.split(".pdf")[0]
|
|
||||||
subprocess.run(["pdfimages", "-png", pdf_filepath, filename.split(".pdf")[0]])
|
|
||||||
image_filenames = find_matching_files_in_dir(filename_sans_ext, directory)
|
|
||||||
logger.debug(
|
|
||||||
"Converted {} into files:\n{}".format(pdf_filepath, "\n".join(image_filenames))
|
|
||||||
)
|
|
||||||
return image_filenames
|
|
||||||
|
|
||||||
|
|
||||||
def find_matching_files_in_dir(file_prefix, directory):
|
|
||||||
files = [
|
|
||||||
filename
|
|
||||||
for filename in os.listdir(directory)
|
|
||||||
if re.match(r"{}-\d{{3}}.*\.png".format(re.escape(file_prefix)), filename)
|
|
||||||
]
|
|
||||||
return files
|
|
||||||
def preprocess_img(filepath):
|
|
||||||
"""
|
|
||||||
Processing that involves running shell executables,
|
|
||||||
like mogrify to rotate.
|
|
||||||
"""
|
|
||||||
rotate = get_rotate(filepath)
|
|
||||||
logger.debug("Rotating {} by {}.".format(filepath, rotate))
|
|
||||||
mogrify(filepath, rotate)
|
|
||||||
|
|
||||||
|
|
||||||
def get_rotate(image_filepath):
|
|
||||||
output = (
|
|
||||||
subprocess.check_output(["tesseract", "--psm", "0", image_filepath, "-"])
|
|
||||||
.decode("utf-8")
|
|
||||||
.split("\n")
|
|
||||||
)
|
|
||||||
output = next(l for l in output if "Rotate: " in l)
|
|
||||||
output = output.split(": ")[1]
|
|
||||||
return output
|
|
||||||
|
|
||||||
|
|
||||||
def mogrify(image_filepath, rotate):
|
|
||||||
subprocess.run(["mogrify", "-rotate", rotate, image_filepath])
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
args = parser.parse_args()
|
|
||||||
main(args.files)
|
|
||||||
Loading…
Reference in New Issue