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

[WIP] Refactoring meta-detection

Browse Source
This commit is contained in:
Matthias Bisping 2023-01-09 12:03:50 +01:00
parent b540cfd0f2
commit 557d091a54
1 changed files with 13 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
cv_analysis/layout_parsing.py
View File

@ -19,7 +19,6 @@ from cv_analysis.utils.rectangle import Rectangle
def parse_layout(image: np.array):
rectangles = find_segments(image)
rectangles = remove_included(rectangles)
rectangles = lmap(rectangle_to_box, rectangles)
rectangles = connect_related_rects2(rectangles)
@ -31,25 +30,27 @@ def parse_layout(image: np.array):
def find_segments(image, meta=1):
if meta:
original = image.copy()
image = normalize_to_gray_scale(image)
image = dilate_page_components(image)
preprocess = compose(dilate_page_components, normalize_to_gray_scale)
contours, hierarchies = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
mask1 = map(is_likely_segment, contours)
mask2 = map(has_no_parent, hierarchies[0])
mask = map(__and__, mask1, mask2)
contours = compress(contours, mask)
contours, hierarchies = find_contours(preprocess(image) if meta else image)
likely_segments = map(is_likely_segment, contours)
without_parents = map(has_no_parent, hierarchies[0])
valid_contours = map(__and__, likely_segments, without_parents)
contours = compress(contours, valid_contours)
rectangles = lmap(compose(box_to_rectangle, cv2.boundingRect), contours)
if meta:
image = meta_detection(original, rectangles)
rectangles = find_segments(image, 0)
preprocessed = meta_detection(image.copy(), rectangles)
rectangles = find_segments(preprocessed, 0)
return rectangles
def find_contours(image):
contours, hierarchies = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
return contours, hierarchies
def is_likely_segment(rect, min_area=100):
return cv2.contourArea(rect, False) > min_area