def uied():
start = time.clock()
models, input_path, output_root, note_success_file, note_fail_file, uied_params = params.get_params(
)
print("UIED Running on:", input_path, " Write to:", output_root)
resized_height = resize_height_by_longest_edge(input_path)
if is_ocr:
import ocr_east as ocr
os.makedirs(pjoin(output_root, 'ocr'), exist_ok=True)
ocr.east(input_path,
output_root,
models['text'],
resize_by_height=resized_height,
show=False)
if is_ip:
os.makedirs(pjoin(output_root, 'ip'), exist_ok=True)
ip.compo_detection(input_path,
output_root,
uied_params=uied_params,
classifier=models['compo'],
resize_by_height=resized_height,
show=False)
if is_merge:
# os.makedirs(pjoin(output_root, 'merge'), exist_ok=True)
import merge
name = input_path.split('/')[-1][:-4]
compo_path = pjoin(output_root, 'ip', str(name) + '.json')
ocr_path = pjoin(output_root, 'ocr', str(name) + '.json')
merge.incorporate(input_path,
compo_path,
ocr_path,
output_root,
resize_by_height=resized_height,
show=False)
open(note_success_file, 'a').write(output_root + '\n')
print("[UIED complete in %.3fs]" % (time.clock() - start))
print(time.ctime(), '\n')
import glob
import time
import json
from tqdm import tqdm
from os.path import join as pjoin, exists
ROOT_INPUT = 'E:\\Mulong\\Datasets\\rico\\combined'
ROOT_OUTPUT = 'E:\\Mulong\\Result\\east'
# set input root directory and sort all images by their indices
data = json.load(
open('E:\\Mulong\\Datasets\\rico\\instances_test_org.json', 'r'))
input_paths_img = [
pjoin(ROOT_INPUT, img['file_name'].split('/')[-1])
for img in data['images']
]
input_paths_img = sorted(
input_paths_img,
key=lambda x: int(x.split('\\')[-1][:-4])) # sorted by index
start_index = 9122
end_index = 100000
for i, input_path_img in enumerate(input_paths_img):
print(i, '/', len(input_paths_img))
index = input_path_img.split('\\')[-1][:-4]
if int(index) < start_index:
continue
if int(index) > end_index:
break
ocr.east(input_path_img, ROOT_OUTPUT, resize_by_height=None, show=True)
C.build_output_folders(is_clip)
resize_by_height = 600
# set input root directory and sort all images by their indices
input_paths_img = glob.glob(pjoin(C.ROOT_INPUT, '*.jpg'))
input_paths_img = sorted(
input_paths_img,
key=lambda x: int(x.split('\\')[-1][:-4])) # sorted by index
# set the range of target inputs' indices
start_index = 24
end_index = 50
for input_path_img in input_paths_img:
index = input_path_img.split('\\')[-1][:-4]
if int(index) < start_index:
continue
if int(index) > end_index:
break
# *** start processing ***
start = time.clock()
if is_ocr:
ocr.east(input_path_img, C.ROOT_OCR, resize_by_height)
if is_ip:
ip.compo_detection(input_path_img, C.ROOT_IP, resize_by_height)
if is_merge:
merge.incorporate(input_path_img, C.ROOT_OCR, C.ROOT_IP, C.ROOT_MERGE,
resize_by_height, is_clip)
print('*** Total Time Taken:%.3f s ***\n' % (time.clock() - start))
# set the range of target inputs' indices
num = 0
start_index = 30800 # 61728
end_index = 100000
for input_path_img in input_paths_img:
index = input_path_img.split('\\')[-1][:-4]
if int(index) < start_index:
continue
if int(index) > end_index:
break
if is_ocr:
import ocr_east as ocr
ocr.east(input_path_img,
output_root,
resize_by_height=None,
show=False,
write_img=True)
if is_ip:
ip.compo_detection(input_path_img,
output_root,
num,
resize_by_height=resize_by_height,
show=True,
classifier=classifier)
if is_merge:
import merge
compo_path = pjoin(output_root, 'ip', str(index) + '.json')
ocr_path = pjoin(output_root, 'ocr', str(index) + '.json')
import time
is_ocr = False
is_ip = True
is_merge = False
resize_by_height = 800
# set input image path
PATH_IMG_INPUT = 'data\\input\\1.jpg'
PATH_OUTPUT_ROOT = 'data\\output'
start = time.clock()
if is_ocr:
# import ocr_ctpn as ocr
# ocr.ctpn(PATH_IMG_INPUT, PATH_OUTPUT_ROOT, resize_by_height)
import ocr_east as ocr
ocr.east(PATH_IMG_INPUT, PATH_OUTPUT_ROOT, resize_by_height)
if is_ip:
import ip
ip.compo_detection(PATH_IMG_INPUT, PATH_OUTPUT_ROOT, resize_by_height)
if is_merge:
import merge
merge.incorporate(PATH_IMG_INPUT, PATH_OUTPUT_ROOT, resize_by_height)
print('Time Taken:%.3f s\n' % (time.clock() - start))
resized_height = resize_height_by_longest_edge(input_path_img)
is_ip = True
is_clf = False
is_ocr = False
is_merge = False
if is_ocr:
os.makedirs(pjoin(output_root, 'ocr'), exist_ok=True)
import ocr_east as ocr
import lib_east.eval as eval
models = eval.load()
ocr.east(input_path_img,
output_root,
models,
resize_by_height=resized_height,
show=False)
if is_ip:
os.makedirs(pjoin(output_root, 'ip'), exist_ok=True)
# switch of the classification func
classifier = None
if is_clf:
classifier = {}
from cnn.CNN import CNN
# classifier['Image'] = CNN('Image')
classifier['Elements'] = CNN('Elements')
# classifier['Noise'] = CNN('Noise')
ip.compo_detection(input_path_img,
output_root,
# set the range of target inputs' indices
num = 0
start_index = 30800 # 61728
end_index = 100000
for input_img in input_imgs:
resized_height = resize_height_by_longest_edge(input_img)
index = input_img.split('/')[-1][:-4]
if int(index) < start_index:
continue
if int(index) > end_index:
break
if is_ocr:
ocr.east(input_img,
output_root,
ocr_model,
resize_by_height=resized_height,
show=False)
if is_ip:
ip.compo_detection(input_img,
output_root,
classifier=compo_classifier,
resize_by_height=resized_height,
show=True)
if is_merge:
import merge
compo_path = pjoin(output_root, 'ip', str(index) + '.json')
ocr_path = pjoin(output_root, 'ocr', str(index) + '.json')
merge.incorporate(input_img,
def uied(input_path,
output_root,
params=None,
is_ip=True,
is_clf=False,
is_ocr=True,
is_merge=True):
'''
ele:min-grad: gradient threshold to produce binary map
ele:ffl-block: fill-flood threshold
ele:min-ele-area: minimum area for selected elements
ele:merge-contained-ele: if True, merge elements contained in others
text:max-word-inline-gap: words with smaller distance than the gap are counted as a line
text:max-line-gap: lines with smaller distance than the gap are counted as a paragraph
Tips:
1. Larger *min-grad* produces fine-grained binary-map while prone to over-segment element to small pieces
2. Smaller *min-ele-area* leaves tiny elements while prone to produce noises
3. If not *merge-contained-ele*, the elements inside others will be recognized, while prone to produce noises
4. The *max-word-inline-gap* and *max-line-gap* should be dependent on the input image size and resolution
mobile: {'min-grad':4, 'ffl-block':5, 'min-ele-area':25, 'max-word-inline-gap':6, 'max-line-gap':1}
web : {'min-grad':3, 'ffl-block':5, 'min-ele-area':25, 'max-word-inline-gap':4, 'max-line-gap':4}
'''
if params is None:
params = {
'min-grad': 4,
'ffl-block': 5,
'min-ele-area': 25,
'merge-contained-ele': True,
'max-word-inline-gap': 4,
'max-line-gap': 4
}
else:
params = json.loads(params)
for i in params:
if params[i] == 'True':
params[i] = True
elif params[i] == 'False':
params[i] = False
else:
params[i] = int(params[i])
print(params)
start = time.clock()
resized_height = resize_height_by_longest_edge(input_path)
if is_ocr:
import ocr_east as ocr
import lib_east.eval as eval
os.makedirs(pjoin(output_root, 'ocr'), exist_ok=True)
models = eval.load()
ocr.east(input_path,
output_root,
models,
params['max-word-inline-gap'],
resize_by_height=resized_height,
show=False)
if is_ip:
import detect_compo.ip_region_proposal as ip
os.makedirs(pjoin(output_root, 'ip'), exist_ok=True)
# switch of the classification func
classifier = None
if is_clf:
classifier = {}
from CNN import CNN
# classifier['Image'] = CNN('Image')
classifier['Elements'] = CNN('Elements')
# classifier['Noise'] = CNN('Noise')
ip.compo_detection(input_path,
output_root,
uied_params=params,
classifier=classifier,
resize_by_height=resized_height,
show=False)
if is_merge:
import merge
# os.makedirs(pjoin(output_root, 'merge'), exist_ok=True)
name = input_path.split('/')[-1][:-4]
compo_path = pjoin(output_root, 'ip', str(name) + '.json')
ocr_path = pjoin(output_root, 'ocr', str(name) + '.json')
merge.incorporate(input_path,
compo_path,
ocr_path,
output_root,
params=params,
resize_by_height=resized_height,
show=False)
print("[UIED complete in %.3fs]" % (time.clock() - start))
print(time.ctime(), '\n')
