def replay(self, dev: device.Device, state, observer, tlib, states=None):
for test in self.steps:
try:
ret = test.attempt(dev, observer, state, tlib)
except:
progress.report_progress(" STEP %s EXCEPTION" %
test.short_name())
raise
if not ret:
progress.report_progress(" STEP %s FAILED" %
test.short_name())
return False
tlib.handle_sys_screen(state, dev, observer)
if states is not None:
states.append(copy.deepcopy(state))
return True
def pick_route(self, test, testinfo=None, unclean_change=True):
picked = None
target_state = None
for screen in self.screens:
if test.usable(screen) and (testinfo is None
or not testinfo.finished(screen)):
progress.report_progress(" consider screen %s for test %s" %
(screen, test.short_name()))
newpicked = self.pick_better_route(screen, picked,
unclean_change)
if newpicked is not None:
progress.report_progress(" select %s for %s" %
(newpicked, self.better_reason))
picked = newpicked
target_state = screen
if picked is not None:
return (picked.route, target_state)
else:
return (None, None)
def report_prog(self, prog):
progress.report_progress(prog)
def report_prog(self, prog):
self.progress = "R.%d %s" % (self.round_no, prog)
progress.report_progress(self.progress)
def main(args):
print(f'Source region extraction tool version {__version__}')
a = ArgumentParser()
a.add_argument(
'input',
help=
'figure image file or image folder path or semicolon separated list of files or meta json lines file'
)
a.add_argument(
'--demo',
help='highlight source region on input images and save separately',
default=False,
action='store_true')
a.add_argument('-out', help='source regions output dir', default='out')
a.add_argument('-meta_out',
help='source regions output JSONL file',
default='regions.json')
args = a.parse_args(args)
demo_dir = args.out + '/demo'
print('Building a list of source files...')
if os.path.exists(demo_dir):
shutil.rmtree(demo_dir, ignore_errors=True)
if args.demo:
os.makedirs(demo_dir + '/', exist_ok=True)
if args.out:
if os.path.exists(args.out):
shutil.rmtree(args.out, ignore_errors=True)
try:
os.makedirs(args.out, exist_ok=True)
if args.demo:
os.makedirs(demo_dir + '/', exist_ok=True) # andrey
except:
pass
#if (args.input[-1]!='\\'):
articles = get_articles(args.input)
file_mapping = get_file_mapping(articles)
#else:
# file_mapping = {}
# for (dirpath, dirnames, filenames) in os.walk(args.input):
# for fnam in filenames:
# file_mapping[args.input+fnam] = ArticleImage(id=1,chain_id='0',filename=args.input+fnam,title='',page=1,idx_on_page=1,regions=[])
# break
if len(file_mapping) == 0:
print('No files found in specified sources')
exit(-1)
reg_id = 0
for i, filename in enumerate(file_mapping.keys()):
src_img = cv2.imread(filename)
if src_img is None:
print(f'Error reading file, skipping: {filename}')
continue
cur_id = 1
# extract with default settings
boxes, boxes2, boxes3, boxes3a, boxes4 = [], [], [], [], []
PerformDebug = False
annotations, boxes = get_region_boxes(src_img,
bin_thresh=5,
debug=PerformDebug)
cur_id = annotate_boxes(cur_id, boxes, (255, 0, 0))
# preset 2 to extract bordered regions
annotations2, boxes2 = get_region_boxes(src_img,
erode_iters=0,
bin_thresh=50,
debug=PerformDebug)
cur_id = annotate_boxes(cur_id, boxes2, (0, 255, 0))
# preset 3 with another threshold
annotations3, boxes3 = get_region_boxes(src_img,
erode_iters=0,
bin_thresh=100,
debug=PerformDebug)
cur_id = annotate_boxes(cur_id, boxes3, (0, 0, 255))
# preset 3a with another threshold
annotations3a, boxes3a = get_region_boxes(src_img,
erode_iters=0,
bin_thresh=150,
debug=PerformDebug)
cur_id = annotate_boxes(cur_id, boxes3a, (0, 0, 255))
# preset 4 - low threshold no morph
annotations4, boxes4 = get_region_boxes(src_img,
erode_iters=0,
debug=PerformDebug)
cur_id = annotate_boxes(cur_id, boxes4, (255, 0, 255))
#boxes = filter_boxes(boxes + boxes2 + boxes3 + boxes3a + boxes4)
all_boxes = boxes + boxes2 + boxes3 + boxes3a + boxes4
# Check the number of all boxes
if len(all_boxes) == 1: # add the entire image as a box
box = Box(0, 0, src_img.shape[1] - 1, src_img.shape[0] - 1)
box.img_data = src_img
all_boxes.append(box)
PerformDebug = False
updated_boxes = filter_boxes_updated(all_boxes,
src_img,
debug=PerformDebug)
# boxes = boxes + boxes2 + boxes3
if len(updated_boxes) == 0:
print(
f'Warning: {filename} no source regions detected, assuming single source region'
)
box = Box(0,
0,
src_img.shape[1] - 1,
src_img.shape[0] - 1,
id=cur_id)
box.img_data = src_img
updated_boxes.append(box)
# remove borders from regions
print(f'{filename} number of source regions: {len(updated_boxes)}')
for b in updated_boxes:
src_reg = b.img_data
assert src_reg.shape[:2] == b.img_data.shape[:2]
# crop borders on normalized reg (white/black borders)
PerformDebug = False
x1, x2, y1, y2 = crop_border(preprocess_image(b.img_data,
150,
otsu=True),
src_reg,
debug=PerformDebug)
sr = src_reg[y1:y2, x1:x2]
# sr = src_img[b.y1:b.y2, b.x1:b.x2]
reg_path = os.path.join(
args.out,
'.'.join(os.path.basename(filename).split('.')[:-1]) + '_' +
'R' + str(b.id) + '.png')
article_image = file_mapping[filename]
article_image.regions.append(
Region(id=reg_id,
chain_id=article_image.chain_id,
filename=os.path.abspath(reg_path),
box=(b.x1, b.y1, b.x2, b.y2),
matches=[],
title=os.path.basename(reg_path)))
reg_id += 1
#cv2.imshow('subimage', sr) # andrey
#cv2.waitKey(0)
cv2.imwrite(reg_path, sr)
if args.demo:
ref = src_img.copy()
for b in updated_boxes:
cv2.rectangle(ref, (b.x1, b.y1), (b.x2, b.y2),
color=(b.meta if b.meta is not None else
(255, 128, 100)),
thickness=2)
ResultImagePathToSave = os.path.join(
demo_dir,
'.'.join(os.path.basename(filename).split('.')[:-1]) + '.png')
cv2.imwrite(ResultImagePathToSave, ref)
cv2.imshow('image with bounding box', ref) # andrey
cv2.waitKey(0)
progress.report_progress(i + 1, len(file_mapping),
'Extracting regions')
#show(ref_imgs=annotations, title=f'{filename}')
#show(ref_imgs=annotations2, title=f'{filename} pass 2')
#show(ref_imgs=annotations3, title=f'{filename} pass 3')
#show(ref_imgs=annotations4, title=f'{filename} pass 4')
with open(args.meta_out, mode='w') as meta_file:
for a in articles:
meta_file.write(a.toJSON() + os.linesep)