def pretrain(product):
from CONFIG import Config
import gensim
conf=Config(product)
model=gensim.models.Word2Vec.load(conf.WORD2VEC_PATH)
ent_set=read_set(conf.WHOLE_PART_PATH)
attr_set=read_set(conf.ENTITY_ATTRIBUTE_PATH)-ent_set
similarity_ent=pretrain_set(model, ent_set)
similarity_attr=pretrain_set(model, attr_set)
write_dict(conf.SIMILARITY_ENTITY_PATH,similarity_ent)
write_dict(conf.SIMILARITY_ATTRIBUTE_PATH,similarity_attr)
from keras.models import Sequential, load_model
from keras.layers import Conv2D, MaxPool2D, Dense, Flatten, Dropout
from sklearn.metrics import confusion_matrix
import cv2
import numpy as np
from CONFIG import Config
cfg = Config()
class CNN:
def __init__(self):
self.data = None
self.model = None
self.image_shape = cfg.image_shape
self.class_number = cfg.class_number
self.class_map = cfg.class_map
self.MODEL_PATH = cfg.MODEL_PATH
def network(self):
# block 1
self.model.add(Conv2D(64, (3, 3), activation='relu', input_shape=self.image_shape, padding='same'))
self.model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
self.model.add(MaxPool2D(pool_size=(2, 2)))
self.model.add(Dropout(0.25))
# block 2
self.model.add(Flatten())
self.model.add(Dense(128, activation='relu'))
self.model.add(Dropout(0.5))
import cv2
import numpy as np
import ip_draw as draw
import ip_detection_utils as util
import ocr_classify_text as ocr
from CONFIG import Config
C = Config()
def get_corner(boundaries):
"""
Get the top left and bottom right points of boundary
:param boundaries: boundary: [top, bottom, left, right]
-> up, bottom: (column_index, min/max row border)
-> left, right: (row_index, min/max column border) detect range of each row
:return: corners: [(top_left, bottom_right)]
-> top_left: (column_min, row_min)
-> bottom_right: (column_max, row_max)
"""
corners = []
for boundary in boundaries:
top_left = (min(boundary[0][0][0], boundary[1][-1][0]),
min(boundary[2][0][0], boundary[3][-1][0]))
bottom_right = (max(boundary[0][0][0], boundary[1][-1][0]),
max(boundary[2][0][0], boundary[3][-1][0]))
corner = (top_left, bottom_right)
corners.append(corner)
return corners
from os.path import join as pjoin, exists
import time
import ocr_east as ocr
import ip
import merge
from CONFIG import Config
# choose functionality
is_ocr = True
is_ip = True
is_merge = True
# initialization
is_clip = False
C = Config()
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
import cv2
import numpy as np
import tensorflow as tf
from tensorflow.python.platform import gfile
sys.path.append(os.getcwd())
from lib_ctpn.fast_rcnn.config import cfg, cfg_from_file
from lib_ctpn.fast_rcnn.test import _get_blobs
from lib_ctpn.text_connector.detectors import TextDetector
from lib_ctpn.text_connector.text_connect_cfg import Config as TextLineCfg
from lib_ctpn.rpn_msr.proposal_layer_tf import proposal_layer
from CONFIG import Config
UI2CODECfg = Config()
def resize_im(im, scale, max_scale=None):
f = float(scale) / min(im.shape[0], im.shape[1])
if max_scale != None and f * max(im.shape[0], im.shape[1]) > max_scale:
f = float(max_scale) / max(im.shape[0], im.shape[1])
return cv2.resize(im, None, None, fx=f, fy=f, interpolation=cv2.INTER_LINEAR), f
def draw_boxes(img, boxes, scale, output_path_label, output_path_img):
with open(output_path_label, 'w') as f:
for box in boxes:
if np.linalg.norm(box[0] - box[1]) < 5 or np.linalg.norm(box[3] - box[0]) < 5:
continue
if box[8] >= 0.9:
import body
import ip_preprocessing as pre
import ip_draw as draw
import file_utils as file
from CONFIG import Config
from MODEL import CNN
import cv2
import time
import glob
from os.path import join as pyjoin
# initialization
C = Config()
C.build_output_folders(False)
input_root = C.ROOT_INPUT
input_paths = glob.glob(pyjoin(input_root, '*.png'))
input_paths = sorted(input_paths, key=lambda x: int(x.split('\\')[-1][:-4])) # sorted by index
def save(index, org, binary, corners_block, corners_img, corners_compo, compos_class, corners_text):
out_img_gradient = pyjoin(C.ROOT_IMG_GRADIENT, index + '.png')
out_img_draw = pyjoin(C.ROOT_IMG_DRAWN, index + '.png')
out_img_clean = pyjoin(C.ROOT_IMG_CLEAN, index + '.png')
out_label = pyjoin(C.ROOT_LABEL, index + '.json')
# *** Step 7 *** post-processing: remove img elements from original image and segment into smaller size
img_clean = draw.draw_bounding_box(org, corners_img, color=(255, 255, 255), line=-1)
# draw results
draw_bounding = draw.draw_bounding_box_class(org, corners_compo, compos_class)
import time
import glob
from os.path import join as pyjoin
# choose functionality
is_merge_img = True
is_shrink_img = True
is_detect_compo_in_img = True
is_classify = True
is_ocr = True
is_segment = False
is_save = True
is_clip = False
# initialization
C = Config()
C.build_output_folders(is_segment)
input_root = C.ROOT_INPUT
input_paths = glob.glob(pyjoin(input_root, '*.png'))
input_paths = sorted(
input_paths, key=lambda x: int(x.split('\\')[-1][:-4])) # sorted by index
CNN = CNN()
CNN.load()
# start image and end image
start_index = 20
end_index = 100
for input_path in input_paths:
index = input_path.split('\\')[-1][:-4]
if int(index) < start_index:
