Marmelator/cv-analysis-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 37 Wiki Activity

Merge remote-tracking branch 'origin/fig-detection-scanned-pdfs' into fig-detection-scanned-pdfs

Browse Source
This commit is contained in:
llocarnini 2022-04-27 11:12:43 +02:00
commit 98ed9a4220
1 changed files with 21 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
cv_analysis/table_parsing.py
View File

@ -16,8 +16,8 @@ from cv_analysis.utils.visual_logging import vizlogger
from cv_analysis.layout_parsing import parse_layout from cv_analysis.layout_parsing import parse_layout
def add_external_contours(image, img): def add_external_contours(image, contour_source_image):
contours, _ = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE) contours, _ = cv2.findContours(contour_source_image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
contours = filter(partial(is_large_enough, min_area=5000), contours) contours = filter(partial(is_large_enough, min_area=5000), contours)
for cnt in contours: for cnt in contours:
@ -27,6 +27,16 @@ def add_external_contours(image, img):
return image return image
def extend_lines():
#TODO
pass
def make_table_block_mask():
#TODO
pass
def apply_motion_blur(image: np.array, angle, size=80): def apply_motion_blur(image: np.array, angle, size=80):
"""Solidifies and slightly extends detected lines. """Solidifies and slightly extends detected lines.
@ -68,7 +78,8 @@ def isolate_vertical_and_horizontal_components(img_bin):
img_bin_h = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernel_h) img_bin_h = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernel_h)
vizlogger.debug(img_bin_h, "tables01_isolate01_img_bin_h.png") vizlogger.debug(img_bin_h, "tables01_isolate01_img_bin_h.png")
img_bin_v = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernel_v) img_bin_v = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernel_v)
vizlogger.debug(img_bin_v | img_bin_h, "tables02_isolate02_img_bin_v.png") img_lines_raw = img_bin_v | img_bin_h
vizlogger.debug(img_lines_raw, "tables02_isolate02_img_bin_v.png")
kernel_h = np.ones((1, 30), np.uint8) kernel_h = np.ones((1, 30), np.uint8)
kernel_v = np.ones((30, 1), np.uint8) kernel_v = np.ones((30, 1), np.uint8)
@ -90,16 +101,13 @@ def isolate_vertical_and_horizontal_components(img_bin):
img_bin_final = cv2.dilate(img_bin_final, np.ones((1, 1), np.uint8), iterations=1) img_bin_final = cv2.dilate(img_bin_final, np.ones((1, 1), np.uint8), iterations=1)
vizlogger.debug(img_bin_final, "tables11_isolate13_dilate.png") vizlogger.debug(img_bin_final, "tables11_isolate13_dilate.png")
# add contours before lines are extended by blurring
img_bin_final = add_external_contours(img_bin_final, img_lines_raw)
vizlogger.debug(img_bin_final, "tables11_isolate14_contours_added.png")
return img_bin_final return img_bin_final
def disconnect_non_existing_cells(img_bin, bounding_rects):
for rect in bounding_rects:
x, y, w, h = rect
img_bin = cv2.rectangle(img_bin, (x, y), (x + w, y + h), (0, 0, 0), 5)
return img_bin
def has_table_shape(rects): def has_table_shape(rects):
assert isinstance(rects, list) assert isinstance(rects, list)
@ -158,10 +166,8 @@ def parse_table(image: np.array, show=False):
table_layout_boxes = find_table_layout_boxes(image) table_layout_boxes = find_table_layout_boxes(image)
image = isolate_vertical_and_horizontal_components(image) image = isolate_vertical_and_horizontal_components(image)
image = disconnect_non_existing_cells(image, table_layout_boxes) #image = add_external_contours(image, image)
vizlogger.debug(image, "tables12_isolate14_disconnect.png") #vizlogger.debug(image, "external_contours_added.png")
image = add_external_contours(image, image)
vizlogger.debug(image, "external_contours_added.png")
_, _, stats, _ = cv2.connectedComponentsWithStats(~image, connectivity=8, ltype=cv2.CV_32S) _, _, stats, _ = cv2.connectedComponentsWithStats(~image, connectivity=8, ltype=cv2.CV_32S)