File size: 5,383 Bytes
a89d9fd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import random
import ast
from PIL import Image, ImageDraw, ImageFont
import numpy as np
from tools.infer.utility import draw_ocr_box_txt, str2bool, init_args as infer_args
def init_args():
parser = infer_args()
# params for output
parser.add_argument("--output", type=str, default='./output')
# params for table structure
parser.add_argument("--table_max_len", type=int, default=488)
parser.add_argument("--table_algorithm", type=str, default='TableAttn')
parser.add_argument("--table_model_dir", type=str)
parser.add_argument(
"--merge_no_span_structure", type=str2bool, default=True)
parser.add_argument(
"--table_char_dict_path",
type=str,
default="../ppocr/utils/dict/table_structure_dict_ch.txt")
# params for layout
parser.add_argument("--layout_model_dir", type=str)
parser.add_argument(
"--layout_dict_path",
type=str,
default="../ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt")
parser.add_argument(
"--layout_score_threshold",
type=float,
default=0.5,
help="Threshold of score.")
parser.add_argument(
"--layout_nms_threshold",
type=float,
default=0.5,
help="Threshold of nms.")
# params for kie
parser.add_argument("--kie_algorithm", type=str, default='LayoutXLM')
parser.add_argument("--ser_model_dir", type=str)
parser.add_argument("--re_model_dir", type=str)
parser.add_argument("--use_visual_backbone", type=str2bool, default=True)
parser.add_argument(
"--ser_dict_path",
type=str,
default="../train_data/XFUND/class_list_xfun.txt")
# need to be None or tb-yx
parser.add_argument("--ocr_order_method", type=str, default=None)
# params for inference
parser.add_argument(
"--mode",
type=str,
choices=['structure', 'kie'],
default='structure',
help='structure and kie is supported')
parser.add_argument(
"--image_orientation",
type=bool,
default=False,
help='Whether to enable image orientation recognition')
parser.add_argument(
"--layout",
type=str2bool,
default=True,
help='Whether to enable layout analysis')
parser.add_argument(
"--table",
type=str2bool,
default=True,
help='In the forward, whether the table area uses table recognition')
parser.add_argument(
"--ocr",
type=str2bool,
default=True,
help='In the forward, whether the non-table area is recognition by ocr')
# param for recovery
parser.add_argument(
"--recovery",
type=str2bool,
default=False,
help='Whether to enable layout of recovery')
parser.add_argument(
"--use_pdf2docx_api",
type=str2bool,
default=False,
help='Whether to use pdf2docx api')
return parser
def parse_args():
parser = init_args()
return parser.parse_args()
def draw_structure_result(image, result, font_path):
if isinstance(image, np.ndarray):
image = Image.fromarray(image)
boxes, txts, scores = [], [], []
img_layout = image.copy()
draw_layout = ImageDraw.Draw(img_layout)
text_color = (255, 255, 255)
text_background_color = (80, 127, 255)
catid2color = {}
font_size = 15
font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
for region in result:
if region['type'] not in catid2color:
box_color = (random.randint(0, 255), random.randint(0, 255),
random.randint(0, 255))
catid2color[region['type']] = box_color
else:
box_color = catid2color[region['type']]
box_layout = region['bbox']
draw_layout.rectangle(
[(box_layout[0], box_layout[1]), (box_layout[2], box_layout[3])],
outline=box_color,
width=3)
text_w, text_h = font.getsize(region['type'])
draw_layout.rectangle(
[(box_layout[0], box_layout[1]),
(box_layout[0] + text_w, box_layout[1] + text_h)],
fill=text_background_color)
draw_layout.text(
(box_layout[0], box_layout[1]),
region['type'],
fill=text_color,
font=font)
if region['type'] == 'table':
pass
else:
for text_result in region['res']:
boxes.append(np.array(text_result['text_region']))
txts.append(text_result['text'])
scores.append(text_result['confidence'])
im_show = draw_ocr_box_txt(
img_layout, boxes, txts, scores, font_path=font_path, drop_score=0)
return im_show
|