-
Notifications
You must be signed in to change notification settings - Fork 7.7k
/
paddleocr.py
1018 lines (948 loc) · 39.5 KB
/
paddleocr.py
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# 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 os
import sys
import importlib
__dir__ = os.path.dirname(__file__)
from paddle.utils import try_import
sys.path.append(os.path.join(__dir__, ""))
import cv2
from copy import deepcopy
import logging
import numpy as np
from pathlib import Path
import base64
from io import BytesIO
import pprint
from PIL import Image
def _import_file(module_name, file_path, make_importable=False):
spec = importlib.util.spec_from_file_location(module_name, file_path)
module = importlib.util.module_from_spec(spec)
spec.loader.exec_module(module)
if make_importable:
sys.modules[module_name] = module
return module
tools = _import_file(
"tools", os.path.join(__dir__, "tools/__init__.py"), make_importable=True
)
ppocr = importlib.import_module("ppocr", "paddleocr")
ppstructure = importlib.import_module("ppstructure", "paddleocr")
from ppocr.utils.logging import get_logger
from ppocr.utils.utility import (
check_and_read,
get_image_file_list,
alpha_to_color,
binarize_img,
)
from ppocr.utils.network import (
maybe_download,
download_with_progressbar,
is_link,
confirm_model_dir_url,
)
from tools.infer import predict_system
from tools.infer.utility import draw_ocr, str2bool, check_gpu
from ppstructure.utility import init_args, draw_structure_result
from ppstructure.predict_system import StructureSystem, save_structure_res, to_excel
from ppstructure.recovery.recovery_to_doc import sorted_layout_boxes, convert_info_docx
logger = get_logger()
__all__ = [
"PaddleOCR",
"PPStructure",
"draw_ocr",
"draw_structure_result",
"save_structure_res",
"download_with_progressbar",
"to_excel",
"sorted_layout_boxes",
"convert_info_docx",
]
SUPPORT_DET_MODEL = ["DB"]
SUPPORT_REC_MODEL = ["CRNN", "SVTR_LCNet"]
BASE_DIR = os.path.expanduser("~/.paddleocr/")
DEFAULT_OCR_MODEL_VERSION = "PP-OCRv4"
SUPPORT_OCR_MODEL_VERSION = ["PP-OCR", "PP-OCRv2", "PP-OCRv3", "PP-OCRv4"]
DEFAULT_STRUCTURE_MODEL_VERSION = "PP-StructureV2"
SUPPORT_STRUCTURE_MODEL_VERSION = ["PP-Structure", "PP-StructureV2"]
MODEL_URLS = {
"OCR": {
"PP-OCRv4": {
"det": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_det_infer.tar",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar",
},
"ml": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar"
},
},
"rec": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/chinese/ch_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/ppocr_keys_v1.txt",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/english/en_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/en_dict.txt",
},
"korean": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/korean_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/korean_dict.txt",
},
"japan": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/japan_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/japan_dict.txt",
},
"chinese_cht": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt",
},
"ta": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ta_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ta_dict.txt",
},
"te": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/te_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/te_dict.txt",
},
"ka": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/ka_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ka_dict.txt",
},
"latin": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/latin_dict.txt",
},
"arabic": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/arabic_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/arabic_dict.txt",
},
"cyrillic": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/cyrillic_dict.txt",
},
"devanagari": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv4/multilingual/devanagari_PP-OCRv4_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/devanagari_dict.txt",
},
},
"cls": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar",
}
},
},
"PP-OCRv3": {
"det": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar",
},
"ml": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar"
},
},
"rec": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/ppocr_keys_v1.txt",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/en_dict.txt",
},
"korean": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/korean_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/korean_dict.txt",
},
"japan": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/japan_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/japan_dict.txt",
},
"chinese_cht": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt",
},
"ta": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ta_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ta_dict.txt",
},
"te": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/te_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/te_dict.txt",
},
"ka": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ka_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ka_dict.txt",
},
"latin": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/latin_dict.txt",
},
"arabic": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/arabic_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/arabic_dict.txt",
},
"cyrillic": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/cyrillic_dict.txt",
},
"devanagari": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/devanagari_PP-OCRv3_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/devanagari_dict.txt",
},
},
"cls": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar",
}
},
},
"PP-OCRv2": {
"det": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar",
},
},
"rec": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar",
"dict_path": "./ppocr/utils/ppocr_keys_v1.txt",
}
},
"cls": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar",
}
},
},
"PP-OCR": {
"det": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar",
},
"structure": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar"
},
},
"rec": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/ppocr_keys_v1.txt",
},
"en": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/en_dict.txt",
},
"french": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/french_dict.txt",
},
"german": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/german_dict.txt",
},
"korean": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/korean_dict.txt",
},
"japan": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/japan_dict.txt",
},
"chinese_cht": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/chinese_cht_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/chinese_cht_dict.txt",
},
"ta": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ta_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ta_dict.txt",
},
"te": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/te_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/te_dict.txt",
},
"ka": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/ka_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/ka_dict.txt",
},
"latin": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/latin_ppocr_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/latin_dict.txt",
},
"arabic": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/arabic_ppocr_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/arabic_dict.txt",
},
"cyrillic": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/cyrillic_ppocr_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/cyrillic_dict.txt",
},
"devanagari": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/devanagari_ppocr_mobile_v2.0_rec_infer.tar",
"dict_path": "./ppocr/utils/dict/devanagari_dict.txt",
},
"structure": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar",
"dict_path": "ppocr/utils/dict/table_dict.txt",
},
},
"cls": {
"ch": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar",
}
},
},
},
"STRUCTURE": {
"PP-Structure": {
"table": {
"en": {
"url": "https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar",
"dict_path": "ppocr/utils/dict/table_structure_dict.txt",
}
}
},
"PP-StructureV2": {
"table": {
"en": {
"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar",
"dict_path": "ppocr/utils/dict/table_structure_dict.txt",
},
"ch": {
"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar",
"dict_path": "ppocr/utils/dict/table_structure_dict_ch.txt",
},
},
"layout": {
"en": {
"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_infer.tar",
"dict_path": "ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt",
},
"ch": {
"url": "https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_fgd_layout_cdla_infer.tar",
"dict_path": "ppocr/utils/dict/layout_dict/layout_cdla_dict.txt",
},
},
},
},
}
def parse_args(mMain=True):
import argparse
parser = init_args()
parser.add_help = mMain
parser.add_argument("--lang", type=str, default="ch")
parser.add_argument("--det", type=str2bool, default=True)
parser.add_argument("--rec", type=str2bool, default=True)
parser.add_argument("--type", type=str, default="ocr")
parser.add_argument("--savefile", type=str2bool, default=False)
parser.add_argument(
"--ocr_version",
type=str,
choices=SUPPORT_OCR_MODEL_VERSION,
default="PP-OCRv4",
help="OCR Model version, the current model support list is as follows: "
"1. PP-OCRv4/v3 Support Chinese and English detection and recognition model, and direction classifier model"
"2. PP-OCRv2 Support Chinese detection and recognition model. "
"3. PP-OCR support Chinese detection, recognition and direction classifier and multilingual recognition model.",
)
parser.add_argument(
"--structure_version",
type=str,
choices=SUPPORT_STRUCTURE_MODEL_VERSION,
default="PP-StructureV2",
help="Model version, the current model support list is as follows:"
" 1. PP-Structure Support en table structure model."
" 2. PP-StructureV2 Support ch and en table structure model.",
)
for action in parser._actions:
if action.dest in [
"rec_char_dict_path",
"table_char_dict_path",
"layout_dict_path",
]:
action.default = None
if mMain:
return parser.parse_args()
else:
inference_args_dict = {}
for action in parser._actions:
inference_args_dict[action.dest] = action.default
return argparse.Namespace(**inference_args_dict)
def parse_lang(lang):
latin_lang = [
"af",
"az",
"bs",
"cs",
"cy",
"da",
"de",
"es",
"et",
"fr",
"ga",
"hr",
"hu",
"id",
"is",
"it",
"ku",
"la",
"lt",
"lv",
"mi",
"ms",
"mt",
"nl",
"no",
"oc",
"pi",
"pl",
"pt",
"ro",
"rs_latin",
"sk",
"sl",
"sq",
"sv",
"sw",
"tl",
"tr",
"uz",
"vi",
"french",
"german",
]
arabic_lang = ["ar", "fa", "ug", "ur"]
cyrillic_lang = [
"ru",
"rs_cyrillic",
"be",
"bg",
"uk",
"mn",
"abq",
"ady",
"kbd",
"ava",
"dar",
"inh",
"che",
"lbe",
"lez",
"tab",
]
devanagari_lang = [
"hi",
"mr",
"ne",
"bh",
"mai",
"ang",
"bho",
"mah",
"sck",
"new",
"gom",
"sa",
"bgc",
]
if lang in latin_lang:
lang = "latin"
elif lang in arabic_lang:
lang = "arabic"
elif lang in cyrillic_lang:
lang = "cyrillic"
elif lang in devanagari_lang:
lang = "devanagari"
assert (
lang in MODEL_URLS["OCR"][DEFAULT_OCR_MODEL_VERSION]["rec"]
), "param lang must in {}, but got {}".format(
MODEL_URLS["OCR"][DEFAULT_OCR_MODEL_VERSION]["rec"].keys(), lang
)
if lang == "ch":
det_lang = "ch"
elif lang == "structure":
det_lang = "structure"
elif lang in ["en", "latin"]:
det_lang = "en"
else:
det_lang = "ml"
return lang, det_lang
def get_model_config(type, version, model_type, lang):
if type == "OCR":
DEFAULT_MODEL_VERSION = DEFAULT_OCR_MODEL_VERSION
elif type == "STRUCTURE":
DEFAULT_MODEL_VERSION = DEFAULT_STRUCTURE_MODEL_VERSION
else:
raise NotImplementedError
model_urls = MODEL_URLS[type]
if version not in model_urls:
version = DEFAULT_MODEL_VERSION
if model_type not in model_urls[version]:
if model_type in model_urls[DEFAULT_MODEL_VERSION]:
version = DEFAULT_MODEL_VERSION
else:
logger.error(
"{} models is not support, we only support {}".format(
model_type, model_urls[DEFAULT_MODEL_VERSION].keys()
)
)
sys.exit(-1)
if lang not in model_urls[version][model_type]:
if lang in model_urls[DEFAULT_MODEL_VERSION][model_type]:
version = DEFAULT_MODEL_VERSION
else:
logger.error(
"lang {} is not support, we only support {} for {} models".format(
lang,
model_urls[DEFAULT_MODEL_VERSION][model_type].keys(),
model_type,
)
)
sys.exit(-1)
return model_urls[version][model_type][lang]
def img_decode(content: bytes):
np_arr = np.frombuffer(content, dtype=np.uint8)
return cv2.imdecode(np_arr, cv2.IMREAD_UNCHANGED)
def check_img(img, alpha_color=(255, 255, 255)):
"""
Check the image data. If it is another type of image file, try to decode it into a numpy array.
The inference network requires three-channel images, So the following channel conversions are done
single channel image: Gray to RGB R←Y,G←Y,B←Y
four channel image: alpha_to_color
args:
img: image data
file format: jpg, png and other image formats that opencv can decode, as well as gif and pdf formats
storage type: binary image, net image file, local image file
alpha_color: Background color in images in RGBA format
return: numpy.array (h, w, 3) or list (p, h, w, 3) (p: page of pdf), boolean, boolean
"""
flag_gif, flag_pdf = False, False
if isinstance(img, bytes):
img = img_decode(img)
if isinstance(img, str):
# download net image
if is_link(img):
download_with_progressbar(img, "tmp.jpg")
img = "tmp.jpg"
image_file = img
img, flag_gif, flag_pdf = check_and_read(image_file)
if not flag_gif and not flag_pdf:
with open(image_file, "rb") as f:
img_str = f.read()
img = img_decode(img_str)
if img is None:
try:
buf = BytesIO()
image = BytesIO(img_str)
im = Image.open(image)
rgb = im.convert("RGB")
rgb.save(buf, "jpeg")
buf.seek(0)
image_bytes = buf.read()
data_base64 = str(base64.b64encode(image_bytes), encoding="utf-8")
image_decode = base64.b64decode(data_base64)
img_array = np.frombuffer(image_decode, np.uint8)
img = cv2.imdecode(img_array, cv2.IMREAD_COLOR)
except:
logger.error("error in loading image:{}".format(image_file))
return None, flag_gif, flag_pdf
if img is None:
logger.error("error in loading image:{}".format(image_file))
return None, flag_gif, flag_pdf
# single channel image array.shape:h,w
if isinstance(img, np.ndarray) and len(img.shape) == 2:
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
# four channel image array.shape:h,w,c
if isinstance(img, np.ndarray) and len(img.shape) == 3 and img.shape[2] == 4:
img = alpha_to_color(img, alpha_color)
return img, flag_gif, flag_pdf
class PaddleOCR(predict_system.TextSystem):
def __init__(self, **kwargs):
"""
paddleocr package
args:
**kwargs: other params show in paddleocr --help
"""
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
assert (
params.ocr_version in SUPPORT_OCR_MODEL_VERSION
), "ocr_version must in {}, but get {}".format(
SUPPORT_OCR_MODEL_VERSION, params.ocr_version
)
params.use_gpu = check_gpu(params.use_gpu)
if not params.show_log:
logger.setLevel(logging.INFO)
self.use_angle_cls = params.use_angle_cls
lang, det_lang = parse_lang(params.lang)
# init model dir
det_model_config = get_model_config("OCR", params.ocr_version, "det", det_lang)
params.det_model_dir, det_url = confirm_model_dir_url(
params.det_model_dir,
os.path.join(BASE_DIR, "whl", "det", det_lang),
det_model_config["url"],
)
rec_model_config = get_model_config("OCR", params.ocr_version, "rec", lang)
params.rec_model_dir, rec_url = confirm_model_dir_url(
params.rec_model_dir,
os.path.join(BASE_DIR, "whl", "rec", lang),
rec_model_config["url"],
)
cls_model_config = get_model_config("OCR", params.ocr_version, "cls", "ch")
params.cls_model_dir, cls_url = confirm_model_dir_url(
params.cls_model_dir,
os.path.join(BASE_DIR, "whl", "cls"),
cls_model_config["url"],
)
if params.ocr_version in ["PP-OCRv3", "PP-OCRv4"]:
params.rec_image_shape = "3, 48, 320"
else:
params.rec_image_shape = "3, 32, 320"
# download model if using paddle infer
if not params.use_onnx:
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.cls_model_dir, cls_url)
if params.det_algorithm not in SUPPORT_DET_MODEL:
logger.error("det_algorithm must in {}".format(SUPPORT_DET_MODEL))
sys.exit(0)
if params.rec_algorithm not in SUPPORT_REC_MODEL:
logger.error("rec_algorithm must in {}".format(SUPPORT_REC_MODEL))
sys.exit(0)
if params.rec_char_dict_path is None:
params.rec_char_dict_path = str(
Path(__file__).parent / rec_model_config["dict_path"]
)
logger.debug(params)
# init det_model and rec_model
super().__init__(params)
self.page_num = params.page_num
def ocr(
self,
img,
det=True,
rec=True,
cls=True,
bin=False,
inv=False,
alpha_color=(255, 255, 255),
slice={},
):
"""
OCR with PaddleOCR
Args:
img: Image for OCR. It can be an ndarray, img_path, or a list of ndarrays.
det: Use text detection or not. If False, only text recognition will be executed. Default is True.
rec: Use text recognition or not. If False, only text detection will be executed. Default is True.
cls: Use angle classifier or not. Default is True. If True, the text with a rotation of 180 degrees can be recognized. If no text is rotated by 180 degrees, use cls=False to get better performance.
bin: Binarize image to black and white. Default is False.
inv: Invert image colors. Default is False.
alpha_color: Set RGB color Tuple for transparent parts replacement. Default is pure white.
slice: Use sliding window inference for large images. Both det and rec must be True. Requires int values for slice["horizontal_stride"], slice["vertical_stride"], slice["merge_x_thres"], slice["merge_y_thres"] (See doc/doc_en/slice_en.md). Default is {}.
Returns:
If both det and rec are True, returns a list of OCR results for each image. Each OCR result is a list of bounding boxes and recognized text for each detected text region.
If det is True and rec is False, returns a list of detected bounding boxes for each image.
If det is False and rec is True, returns a list of recognized text for each image.
If both det and rec are False, returns a list of angle classification results for each image.
Raises:
AssertionError: If the input image is not of type ndarray, list, str, or bytes.
SystemExit: If det is True and the input is a list of images.
Note:
- If the angle classifier is not initialized (use_angle_cls=False), it will not be used during the forward process.
- For PDF files, if the input is a list of images and the page_num is specified, only the first page_num images will be processed.
- The preprocess_image function is used to preprocess the input image by applying alpha color replacement, inversion, and binarization if specified.
"""
assert isinstance(img, (np.ndarray, list, str, bytes))
if isinstance(img, list) and det == True:
logger.error("When input a list of images, det must be false")
exit(0)
if cls == True and self.use_angle_cls == False:
logger.warning(
"Since the angle classifier is not initialized, it will not be used during the forward process"
)
img, flag_gif, flag_pdf = check_img(img, alpha_color)
# for infer pdf file
if isinstance(img, list) and flag_pdf:
if self.page_num > len(img) or self.page_num == 0:
imgs = img
else:
imgs = img[: self.page_num]
else:
imgs = [img]
def preprocess_image(_image):
_image = alpha_to_color(_image, alpha_color)
if inv:
_image = cv2.bitwise_not(_image)
if bin:
_image = binarize_img(_image)
return _image
if det and rec:
ocr_res = []
for img in imgs:
img = preprocess_image(img)
dt_boxes, rec_res, _ = self.__call__(img, cls, slice)
if not dt_boxes and not rec_res:
ocr_res.append(None)
continue
tmp_res = [[box.tolist(), res] for box, res in zip(dt_boxes, rec_res)]
ocr_res.append(tmp_res)
return ocr_res
elif det and not rec:
ocr_res = []
for img in imgs:
img = preprocess_image(img)
dt_boxes, elapse = self.text_detector(img)
if dt_boxes.size == 0:
ocr_res.append(None)
continue
tmp_res = [box.tolist() for box in dt_boxes]
ocr_res.append(tmp_res)
return ocr_res
else:
ocr_res = []
cls_res = []
for img in imgs:
if not isinstance(img, list):
img = preprocess_image(img)
img = [img]
if self.use_angle_cls and cls:
img, cls_res_tmp, elapse = self.text_classifier(img)
if not rec:
cls_res.append(cls_res_tmp)
rec_res, elapse = self.text_recognizer(img)
ocr_res.append(rec_res)
if not rec:
return cls_res
return ocr_res
class PPStructure(StructureSystem):
"""
PPStructure class represents the structure analysis system for PaddleOCR.
"""
def __init__(self, **kwargs):
"""
Initializes the PPStructure object with the given parameters.
Args:
**kwargs: Additional keyword arguments to customize the behavior of the structure analysis system.
Raises:
AssertionError: If the structure version is not supported.
"""
params = parse_args(mMain=False)
params.__dict__.update(**kwargs)
assert (
params.structure_version in SUPPORT_STRUCTURE_MODEL_VERSION
), "structure_version must in {}, but get {}".format(
SUPPORT_STRUCTURE_MODEL_VERSION, params.structure_version
)
params.use_gpu = check_gpu(params.use_gpu)
params.mode = "structure"
if not params.show_log:
logger.setLevel(logging.INFO)
lang, det_lang = parse_lang(params.lang)
if lang == "ch":
table_lang = "ch"
else:
table_lang = "en"
if params.structure_version == "PP-Structure":
params.merge_no_span_structure = False
# init model dir
det_model_config = get_model_config("OCR", params.ocr_version, "det", det_lang)
params.det_model_dir, det_url = confirm_model_dir_url(
params.det_model_dir,
os.path.join(BASE_DIR, "whl", "det", det_lang),
det_model_config["url"],
)
rec_model_config = get_model_config("OCR", params.ocr_version, "rec", lang)
params.rec_model_dir, rec_url = confirm_model_dir_url(
params.rec_model_dir,
os.path.join(BASE_DIR, "whl", "rec", lang),
rec_model_config["url"],
)
table_model_config = get_model_config(
"STRUCTURE", params.structure_version, "table", table_lang
)
params.table_model_dir, table_url = confirm_model_dir_url(
params.table_model_dir,
os.path.join(BASE_DIR, "whl", "table"),
table_model_config["url"],
)
layout_model_config = get_model_config(
"STRUCTURE", params.structure_version, "layout", lang
)
params.layout_model_dir, layout_url = confirm_model_dir_url(
params.layout_model_dir,
os.path.join(BASE_DIR, "whl", "layout"),
layout_model_config["url"],
)
# download model
if not params.use_onnx:
maybe_download(params.det_model_dir, det_url)
maybe_download(params.rec_model_dir, rec_url)
maybe_download(params.table_model_dir, table_url)
maybe_download(params.layout_model_dir, layout_url)
if params.rec_char_dict_path is None:
params.rec_char_dict_path = str(
Path(__file__).parent / rec_model_config["dict_path"]
)
if params.table_char_dict_path is None:
params.table_char_dict_path = str(
Path(__file__).parent / table_model_config["dict_path"]
)
if params.layout_dict_path is None:
params.layout_dict_path = str(
Path(__file__).parent / layout_model_config["dict_path"]
)
logger.debug(params)
super().__init__(params)
def __call__(
self,
img,
return_ocr_result_in_table=False,
img_idx=0,
alpha_color=(255, 255, 255),
):
"""
Performs structure analysis on the input image.
Args:
img (str or numpy.ndarray): The input image to perform structure analysis on.
return_ocr_result_in_table (bool, optional): Whether to return OCR results in table format. Defaults to False.
img_idx (int, optional): The index of the image. Defaults to 0.
alpha_color (tuple, optional): The alpha color for transparent images. Defaults to (255, 255, 255).
Returns:
list or dict: The structure analysis results.
"""
img, flag_gif, flag_pdf = check_img(img, alpha_color)
if isinstance(img, list) and flag_pdf:
res_list = []
for index, pdf_img in enumerate(img):
logger.info("processing {}/{} page:".format(index + 1, len(img)))
res, _ = super().__call__(
pdf_img, return_ocr_result_in_table, img_idx=index
)
res_list.append(res)
return res_list
res, _ = super().__call__(img, return_ocr_result_in_table, img_idx=img_idx)
return res
def main():
"""
Main function for running PaddleOCR or PPStructure.
This function takes command line arguments, processes the images, and performs OCR or structure analysis based on the specified type.
Args:
None
Returns:
None
"""
# for cmd
args = parse_args(mMain=True)
image_dir = args.image_dir
if is_link(image_dir):
download_with_progressbar(image_dir, "tmp.jpg")
image_file_list = ["tmp.jpg"]
else:
image_file_list = get_image_file_list(args.image_dir)
if len(image_file_list) == 0:
logger.error("no images find in {}".format(args.image_dir))
return
if args.type == "ocr":
engine = PaddleOCR(**(args.__dict__))
elif args.type == "structure":
engine = PPStructure(**(args.__dict__))
else:
raise NotImplementedError
for img_path in image_file_list:
img_name = os.path.basename(img_path).split(".")[0]
logger.info("{}{}{}".format("*" * 10, img_path, "*" * 10))
if args.type == "ocr":
result = engine.ocr(
img_path,
det=args.det,
rec=args.rec,
cls=args.use_angle_cls,
bin=args.binarize,
inv=args.invert,
alpha_color=args.alphacolor,
)
if result is not None:
lines = []
for res in result:
for line in res:
logger.info(line)
lines.append(pprint.pformat(line) + "\n")
if args.savefile:
if os.path.exists(args.output) is False:
os.mkdir(args.output)
outfile = args.output + "/" + img_name + ".txt"
with open(outfile, "w", encoding="utf-8") as f:
f.writelines(lines)
elif args.type == "structure":
img, flag_gif, flag_pdf = check_and_read(img_path)
if not flag_gif and not flag_pdf:
img = cv2.imread(img_path)
if args.recovery and args.use_pdf2docx_api and flag_pdf:
try_import("pdf2docx")
from pdf2docx.converter import Converter
docx_file = os.path.join(args.output, "{}.docx".format(img_name))
cv = Converter(img_path)
cv.convert(docx_file)
cv.close()
logger.info("docx save to {}".format(docx_file))
continue
if not flag_pdf:
if img is None:
logger.error("error in loading image:{}".format(img_path))
continue
img_paths = [[img_path, img]]
else:
img_paths = []
for index, pdf_img in enumerate(img):
os.makedirs(os.path.join(args.output, img_name), exist_ok=True)
pdf_img_path = os.path.join(
args.output, img_name, img_name + "_" + str(index) + ".jpg"
)
cv2.imwrite(pdf_img_path, pdf_img)
img_paths.append([pdf_img_path, pdf_img])
all_res = []
for index, (new_img_path, img) in enumerate(img_paths):
logger.info("processing {}/{} page:".format(index + 1, len(img_paths)))
result = engine(img, img_idx=index)
save_structure_res(result, args.output, img_name, index)
if args.recovery and result != []:
h, w, _ = img.shape
result_cp = deepcopy(result)
result_sorted = sorted_layout_boxes(result_cp, w)