def boundary_detection(binary,
min_obj_area=C.THRESHOLD_OBJ_MIN_AREA, min_obj_perimeter=C.THRESHOLD_OBJ_MIN_PERIMETER,
line_thickness=C.THRESHOLD_LINE_THICKNESS, min_rec_evenness=C.THRESHOLD_REC_MIN_EVENNESS,
max_dent_ratio=C.THRESHOLD_REC_MAX_DENT_RATIO, show=False, write_boundary=False):
"""
:param binary: Binary image from pre-processing
:param min_obj_area: If not pass then ignore the small object
:param min_obj_perimeter: If not pass then ignore the small object
:param line_thickness: If not pass then ignore the slim object
:param min_rec_evenness: If not pass then this object cannot be rectangular
:param max_dent_ratio: If not pass then this object cannot be rectangular
:return: boundary: [top, bottom, left, right]
-> up, bottom: list of (column_index, min/max row border)
-> left, right: list of (row_index, min/max column border) detect range of each row
"""
mark = np.full(binary.shape, 0, dtype=np.uint8)
boundary_all = []
boundary_rec = []
boundary_nonrec = []
row, column = binary.shape[0], binary.shape[1]
for i in range(row):
for j in range(column):
if binary[i, j] == 255 and mark[i, j] == 0:
# get connected area
area = util.boundary_bfs_connected_area(binary, i, j, mark)
# ignore small area
if len(area) < min_obj_area:
continue
# calculate the boundary of the connected area
boundary = util.boundary_get_boundary(area)
# ignore small area
perimeter = np.sum([len(b) for b in boundary])
if perimeter < min_obj_perimeter:
continue
# check if it is line by checking the length of edges
if util.boundary_is_line(boundary, line_thickness):
continue
# rectangle check
if util.boundary_is_rectangle(boundary, min_rec_evenness, max_dent_ratio):
boundary_rec.append(boundary)
else:
boundary_nonrec.append(boundary)
boundary_all.append(boundary)
if show:
print('Area:%d, Perimeter:%d' % (len(area), perimeter))
draw.draw_boundary(boundary_all, binary.shape, show=True)
if write_boundary:
cv2.imwrite('data/output/boundary.png', draw.draw_boundary(boundary_all, binary.shape))
return boundary_rec, boundary_nonrec
line=-1)
if is_ocr:
draw_bounding, word = ocr.text_detection(org, img_clean)
else:
draw_bounding = org
img_clean = draw.draw_bounding_box(img_clean,
corners_compo,
color=(255, 255, 255),
line=-1)
# *** Step 6 *** post-processing: remove img elements from original image and segment into smaller size
if is_segment:
seg.segment_img(img_clean, 600, 'output/segment')
# draw results
draw_bounding = draw.draw_bounding_box_class(
draw_bounding, corners_block, ['block' for i in range(len(corners_block))])
draw_bounding = draw.draw_bounding_box_class(
draw_bounding, corners_img, ['img' for j in range(len(corners_img))])
draw_bounding = draw.draw_bounding_box_class(
draw_bounding, corners_compo, ['compo' for j in range(len(corners_compo))])
draw_boundary = draw.draw_boundary(boundary_rec, org.shape)
# save results
if is_save:
cv2.imwrite('output/org.png', org)
cv2.imwrite('output/labeled.png', draw_bounding)
cv2.imwrite('output/boundary.png', draw_boundary)
cv2.imwrite('output/gradient.png', binary)
cv2.imwrite('output/clean.png', img_clean)
end = file.timer(start)