File size: 21,309 Bytes
cebb0c1
 
 
 
4c41a36
cebb0c1
 
 
 
 
 
 
 
 
 
 
4c41a36
cebb0c1
 
 
 
 
4c41a36
7361420
 
cebb0c1
 
efed173
cebb0c1
4c41a36
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed173
 
 
 
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7361420
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed173
 
 
 
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed173
 
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed173
cebb0c1
 
efed173
cebb0c1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed173
cebb0c1
 
 
 
 
 
 
 
 
 
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
import asyncio
import string
from collections import Counter
from itertools import count, tee

import cv2
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import streamlit as st
import torch
from PIL import Image
from transformers import (DetrImageProcessor,
                          TableTransformerForObjectDetection)
from vietocr.tool.config import Cfg
from vietocr.tool.predictor import Predictor

st.set_option('deprecation.showPyplotGlobalUse', False)
st.set_page_config(layout='wide')
st.title("Table Detection and Table Structure Recognition")
st.write(
    "Implemented by MSFT team: https://github.com/microsoft/table-transformer")

# config = Cfg.load_config_from_name('vgg_transformer')
config = Cfg.load_config_from_name('vgg_seq2seq')
config['cnn']['pretrained'] = False
config['device'] = 'cpu'
config['predictor']['beamsearch'] = False
detector = Predictor(config)

table_detection_model = TableTransformerForObjectDetection.from_pretrained(
    "microsoft/table-transformer-detection")

table_recognition_model = TableTransformerForObjectDetection.from_pretrained(
    "microsoft/table-transformer-structure-recognition")


def PIL_to_cv(pil_img):
    return cv2.cvtColor(np.array(pil_img), cv2.COLOR_RGB2BGR)


def cv_to_PIL(cv_img):
    return Image.fromarray(cv2.cvtColor(cv_img, cv2.COLOR_BGR2RGB))


async def pytess(cell_pil_img, threshold: float = 0.5):
    text, prob = detector.predict(cell_pil_img, return_prob=True)
    if prob < threshold:
        return ""
    return text.strip()


def sharpen_image(pil_img):

    img = PIL_to_cv(pil_img)
    sharpen_kernel = np.array([[-1, -1, -1], [-1, 9, -1], [-1, -1, -1]])

    sharpen = cv2.filter2D(img, -1, sharpen_kernel)
    pil_img = cv_to_PIL(sharpen)
    return pil_img


def uniquify(seq, suffs=count(1)):
    """Make all the items unique by adding a suffix (1, 2, etc).
    Credit: https://stackoverflow.com/questions/30650474/python-rename-duplicates-in-list-with-progressive-numbers-without-sorting-list
    `seq` is mutable sequence of strings.
    `suffs` is an optional alternative suffix iterable.
    """
    not_unique = [k for k, v in Counter(seq).items() if v > 1]

    suff_gens = dict(zip(not_unique, tee(suffs, len(not_unique))))
    for idx, s in enumerate(seq):
        try:
            suffix = str(next(suff_gens[s]))
        except KeyError:
            continue
        else:
            seq[idx] += suffix

    return seq


def binarizeBlur_image(pil_img):
    image = PIL_to_cv(pil_img)
    thresh = cv2.threshold(image, 150, 255, cv2.THRESH_BINARY_INV)[1]

    result = cv2.GaussianBlur(thresh, (5, 5), 0)
    result = 255 - result
    return cv_to_PIL(result)


def td_postprocess(pil_img):
    '''
    Removes gray background from tables
    '''
    img = PIL_to_cv(pil_img)

    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    mask = cv2.inRange(hsv, (0, 0, 100),
                       (255, 5, 255))  # (0, 0, 100), (255, 5, 255)
    nzmask = cv2.inRange(hsv, (0, 0, 5),
                         (255, 255, 255))  # (0, 0, 5), (255, 255, 255))
    nzmask = cv2.erode(nzmask, np.ones((3, 3)))  # (3,3)
    mask = mask & nzmask

    new_img = img.copy()
    new_img[np.where(mask)] = 255

    return cv_to_PIL(new_img)


# def super_res(pil_img):
#     # requires opencv-contrib-python installed without the opencv-python
#     sr = dnn_superres.DnnSuperResImpl_create()
#     image = PIL_to_cv(pil_img)
#     model_path = "./LapSRN_x8.pb"
#     model_name = model_path.split('/')[1].split('_')[0].lower()
#     model_scale = int(model_path.split('/')[1].split('_')[1].split('.')[0][1])

#     sr.readModel(model_path)
#     sr.setModel(model_name, model_scale)
#     final_img = sr.upsample(image)
#     final_img = cv_to_PIL(final_img)

#     return final_img


def table_detector(image, THRESHOLD_PROBA):
    '''
    Table detection using DEtect-object TRansformer pre-trained on 1 million tables

    '''

    feature_extractor = DetrImageProcessor(do_resize=True,
                                           size=800,
                                           max_size=800)
    encoding = feature_extractor(image, return_tensors="pt")

    with torch.no_grad():
        outputs = table_detection_model(**encoding)

    probas = outputs.logits.softmax(-1)[0, :, :-1]
    keep = probas.max(-1).values > THRESHOLD_PROBA

    target_sizes = torch.tensor(image.size[::-1]).unsqueeze(0)
    postprocessed_outputs = feature_extractor.post_process(
        outputs, target_sizes)
    bboxes_scaled = postprocessed_outputs[0]['boxes'][keep]

    return (probas[keep], bboxes_scaled)


def table_struct_recog(image, THRESHOLD_PROBA):
    '''
    Table structure recognition using DEtect-object TRansformer pre-trained on 1 million tables
    '''

    feature_extractor = DetrImageProcessor(do_resize=True,
                                           size=1000,
                                           max_size=1000)
    encoding = feature_extractor(image, return_tensors="pt")

    with torch.no_grad():
        outputs = table_recognition_model(**encoding)

    probas = outputs.logits.softmax(-1)[0, :, :-1]
    keep = probas.max(-1).values > THRESHOLD_PROBA

    target_sizes = torch.tensor(image.size[::-1]).unsqueeze(0)
    postprocessed_outputs = feature_extractor.post_process(
        outputs, target_sizes)
    bboxes_scaled = postprocessed_outputs[0]['boxes'][keep]

    return (probas[keep], bboxes_scaled)


class TableExtractionPipeline():

    colors = ["red", "blue", "green", "yellow", "orange", "violet"]

    # colors = ["red", "blue", "green", "red", "red", "red"]

    def add_padding(self,
                    pil_img,
                    top,
                    right,
                    bottom,
                    left,
                    color=(255, 255, 255)):
        '''
        Image padding as part of TSR pre-processing to prevent missing table edges
        '''
        width, height = pil_img.size
        new_width = width + right + left
        new_height = height + top + bottom
        result = Image.new(pil_img.mode, (new_width, new_height), color)
        result.paste(pil_img, (left, top))
        return result

    def plot_results_detection(self, c1, model, pil_img, prob, boxes,
                               delta_xmin, delta_ymin, delta_xmax, delta_ymax):
        '''
        crop_tables and plot_results_detection must have same co-ord shifts because 1 only plots the other one updates co-ordinates 
        '''
        # st.write('img_obj')
        # st.write(pil_img)
        plt.imshow(pil_img)
        ax = plt.gca()

        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):
            cl = p.argmax()
            xmin, ymin, xmax, ymax = xmin - delta_xmin, ymin - delta_ymin, xmax + delta_xmax, ymax + delta_ymax
            ax.add_patch(
                plt.Rectangle((xmin, ymin),
                              xmax - xmin,
                              ymax - ymin,
                              fill=False,
                              color='red',
                              linewidth=3))
            text = f'{model.config.id2label[cl.item()]}: {p[cl]:0.2f}'
            ax.text(xmin - 20,
                    ymin - 50,
                    text,
                    fontsize=10,
                    bbox=dict(facecolor='yellow', alpha=0.5))
        plt.axis('off')
        c1.pyplot()

    def crop_tables(self, pil_img, prob, boxes, delta_xmin, delta_ymin,
                    delta_xmax, delta_ymax):
        '''
        crop_tables and plot_results_detection must have same co-ord shifts because 1 only plots the other one updates co-ordinates 
        '''
        cropped_img_list = []

        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):

            xmin, ymin, xmax, ymax = xmin - delta_xmin, ymin - delta_ymin, xmax + delta_xmax, ymax + delta_ymax
            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
            cropped_img_list.append(cropped_img)

        return cropped_img_list

    def generate_structure(self, c2, model, pil_img, prob, boxes,
                           expand_rowcol_bbox_top, expand_rowcol_bbox_bottom):
        '''
        Co-ordinates are adjusted here by 3 'pixels'
        To plot table pillow image and the TSR bounding boxes on the table
        '''
        # st.write('img_obj')
        # st.write(pil_img)
        plt.figure(figsize=(32, 20))
        plt.imshow(pil_img)
        ax = plt.gca()
        rows = {}
        cols = {}
        idx = 0

        for p, (xmin, ymin, xmax, ymax) in zip(prob, boxes.tolist()):

            xmin, ymin, xmax, ymax = xmin, ymin, xmax, ymax
            cl = p.argmax()
            class_text = model.config.id2label[cl.item()]
            text = f'{class_text}: {p[cl]:0.2f}'
            # or (class_text == 'table column')
            if (class_text
                    == 'table row') or (class_text
                                        == 'table projected row header') or (
                                            class_text == 'table column'):
                ax.add_patch(
                    plt.Rectangle((xmin, ymin),
                                  xmax - xmin,
                                  ymax - ymin,
                                  fill=False,
                                  color=self.colors[cl.item()],
                                  linewidth=2))
                ax.text(xmin - 10,
                        ymin - 10,
                        text,
                        fontsize=5,
                        bbox=dict(facecolor='yellow', alpha=0.5))

            if class_text == 'table row':
                rows['table row.' +
                     str(idx)] = (xmin, ymin - expand_rowcol_bbox_top, xmax,
                                  ymax + expand_rowcol_bbox_bottom)
            if class_text == 'table column':
                cols['table column.' +
                     str(idx)] = (xmin, ymin - expand_rowcol_bbox_top, xmax,
                                  ymax + expand_rowcol_bbox_bottom)

            idx += 1

        plt.axis('on')
        c2.pyplot()
        return rows, cols

    def sort_table_featuresv2(self, rows: dict, cols: dict):
        # Sometimes the header and first row overlap, and we need the header bbox not to have first row's bbox inside the headers bbox
        rows_ = {
            table_feature: (xmin, ymin, xmax, ymax)
            for table_feature, (
                xmin, ymin, xmax,
                ymax) in sorted(rows.items(), key=lambda tup: tup[1][1])
        }
        cols_ = {
            table_feature: (xmin, ymin, xmax, ymax)
            for table_feature, (
                xmin, ymin, xmax,
                ymax) in sorted(cols.items(), key=lambda tup: tup[1][0])
        }

        return rows_, cols_

    def individual_table_featuresv2(self, pil_img, rows: dict, cols: dict):

        for k, v in rows.items():
            xmin, ymin, xmax, ymax = v
            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
            rows[k] = xmin, ymin, xmax, ymax, cropped_img

        for k, v in cols.items():
            xmin, ymin, xmax, ymax = v
            cropped_img = pil_img.crop((xmin, ymin, xmax, ymax))
            cols[k] = xmin, ymin, xmax, ymax, cropped_img

        return rows, cols

    def object_to_cellsv2(self, master_row: dict, cols: dict,
                          expand_rowcol_bbox_top, expand_rowcol_bbox_bottom,
                          padd_left):
        '''Removes redundant bbox for rows&columns and divides each row into cells from columns
        Args:

        Returns:

        
        '''
        cells_img = {}
        header_idx = 0
        row_idx = 0
        previous_xmax_col = 0
        new_cols = {}
        new_master_row = {}
        previous_ymin_row = 0
        new_cols = cols
        new_master_row = master_row
        ## Below 2 for loops remove redundant bounding boxes ###
        # for k_col, v_col in cols.items():
        #     xmin_col, _, xmax_col, _, col_img = v_col
        #     if (np.isclose(previous_xmax_col, xmax_col, atol=5)) or (xmin_col >= xmax_col):
        #         print('Found a column with double bbox')
        #         continue
        #     previous_xmax_col = xmax_col
        #     new_cols[k_col] = v_col

        # for k_row, v_row in master_row.items():
        #     _, ymin_row, _, ymax_row, row_img = v_row
        #     if (np.isclose(previous_ymin_row, ymin_row, atol=5)) or (ymin_row >= ymax_row):
        #         print('Found a row with double bbox')
        #         continue
        #     previous_ymin_row = ymin_row
        #     new_master_row[k_row] = v_row
        ######################################################
        for k_row, v_row in new_master_row.items():

            _, _, _, _, row_img = v_row
            xmax, ymax = row_img.size
            xa, ya, xb, yb = 0, 0, 0, ymax
            row_img_list = []
            # plt.imshow(row_img)
            # st.pyplot()
            for idx, kv in enumerate(new_cols.items()):
                k_col, v_col = kv
                xmin_col, _, xmax_col, _, col_img = v_col
                xmin_col, xmax_col = xmin_col - padd_left - 10, xmax_col - padd_left
                xa = xmin_col
                xb = xmax_col
                if idx == 0:
                    xa = 0
                if idx == len(new_cols) - 1:
                    xb = xmax
                xa, ya, xb, yb = xa, ya, xb, yb

                row_img_cropped = row_img.crop((xa, ya, xb, yb))
                row_img_list.append(row_img_cropped)

            cells_img[k_row + '.' + str(row_idx)] = row_img_list
            row_idx += 1

        return cells_img, len(new_cols), len(new_master_row) - 1

    def clean_dataframe(self, df):
        '''
        Remove irrelevant symbols that appear with tesseractOCR
        '''
        # df.columns = [col.replace('|', '') for col in df.columns]

        for col in df.columns:

            df[col] = df[col].str.replace("'", '', regex=True)
            df[col] = df[col].str.replace('"', '', regex=True)
            df[col] = df[col].str.replace(']', '', regex=True)
            df[col] = df[col].str.replace('[', '', regex=True)
            df[col] = df[col].str.replace('{', '', regex=True)
            df[col] = df[col].str.replace('}', '', regex=True)
        return df

    @st.cache
    def convert_df(self, df):
        return df.to_csv().encode('utf-8')

    def create_dataframe(self, c3, cell_ocr_res: list, max_cols: int,
                         max_rows: int):
        '''Create dataframe using list of cell values of the table, also checks for valid header of dataframe
        Args:
            cell_ocr_res: list of strings, each element representing a cell in a table
            max_cols, max_rows: number of columns and rows
        Returns:
            dataframe : final dataframe after all pre-processing 
        '''

        headers = cell_ocr_res[:max_cols]
        new_headers = uniquify(headers,
                               (f' {x!s}' for x in string.ascii_lowercase))
        counter = 0

        cells_list = cell_ocr_res[max_cols:]
        df = pd.DataFrame("", index=range(0, max_rows), columns=new_headers)

        cell_idx = 0
        for nrows in range(max_rows):
            for ncols in range(max_cols):
                df.iat[nrows, ncols] = str(cells_list[cell_idx])
                cell_idx += 1

        ## To check if there are duplicate headers if result of uniquify+col == col
        ## This check removes headers when all headers are empty or if median of header word count is less than 6
        for x, col in zip(string.ascii_lowercase, new_headers):
            if f' {x!s}' == col:
                counter += 1
        header_char_count = [len(col) for col in new_headers]

        # if (counter == len(new_headers)) or (statistics.median(header_char_count) < 6):
        #     st.write('woooot')
        #     df.columns = uniquify(df.iloc[0], (f' {x!s}' for x in string.ascii_lowercase))
        #     df = df.iloc[1:,:]

        df = self.clean_dataframe(df)

        c3.dataframe(df)
        csv = self.convert_df(df)
        c3.download_button("Download table",
                           csv,
                           "file.csv",
                           "text/csv",
                           key='download-csv')

        return df

    async def start_process(self, image_path: str, TD_THRESHOLD, TSR_THRESHOLD,
                            OCR_THRESHOLD, padd_top, padd_left, padd_bottom,
                            padd_right, delta_xmin, delta_ymin, delta_xmax,
                            delta_ymax, expand_rowcol_bbox_top,
                            expand_rowcol_bbox_bottom):
        '''
        Initiates process of generating pandas dataframes from raw pdf-page images

        '''
        image = Image.open(image_path).convert("RGB")
        probas, bboxes_scaled = table_detector(image,
                                               THRESHOLD_PROBA=TD_THRESHOLD)

        if bboxes_scaled.nelement() == 0:
            st.write('No table found in the pdf-page image')
            return ''

        # try:
        # st.write('Document: '+image_path.split('/')[-1])
        c1, c2, c3 = st.columns((1, 1, 1))

        self.plot_results_detection(c1, table_detection_model, image, probas,
                                    bboxes_scaled, delta_xmin, delta_ymin,
                                    delta_xmax, delta_ymax)
        cropped_img_list = self.crop_tables(image, probas, bboxes_scaled,
                                            delta_xmin, delta_ymin, delta_xmax,
                                            delta_ymax)

        for unpadded_table in cropped_img_list:

            table = self.add_padding(unpadded_table, padd_top, padd_right,
                                     padd_bottom, padd_left)
            # table = super_res(table)
            # table = binarizeBlur_image(table)
            # table = sharpen_image(table) # Test sharpen image next
            # table = td_postprocess(table)

            probas, bboxes_scaled = table_struct_recog(
                table, THRESHOLD_PROBA=TSR_THRESHOLD)
            rows, cols = self.generate_structure(c2, table_recognition_model,
                                                 table, probas, bboxes_scaled,
                                                 expand_rowcol_bbox_top,
                                                 expand_rowcol_bbox_bottom)
            # st.write(len(rows), len(cols))
            rows, cols = self.sort_table_featuresv2(rows, cols)
            master_row, cols = self.individual_table_featuresv2(
                table, rows, cols)

            cells_img, max_cols, max_rows = self.object_to_cellsv2(
                master_row, cols, expand_rowcol_bbox_top,
                expand_rowcol_bbox_bottom, padd_left)

            sequential_cell_img_list = []
            for k, img_list in cells_img.items():
                for img in img_list:
                    # img = super_res(img)
                    # img = sharpen_image(img) # Test sharpen image next
                    # img = binarizeBlur_image(img)
                    # img = self.add_padding(img, 10,10,10,10)
                    # plt.imshow(img)
                    # c3.pyplot()
                    sequential_cell_img_list.append(
                        pytess(cell_pil_img=img, threshold=OCR_THRESHOLD))

            cell_ocr_res = await asyncio.gather(*sequential_cell_img_list)

            self.create_dataframe(c3, cell_ocr_res, max_cols, max_rows)
            st.write(
                'Errors in OCR is due to either quality of the image or performance of the OCR'
            )
        # except:
        #     st.write('Either incorrectly identified table or no table, to debug remove try/except')
        # break
        # break


if __name__ == "__main__":

    img_name = st.file_uploader("Upload an image with table(s)")
    st1, st2, st3 = st.columns((1, 1, 1))
    TD_th = st1.slider('Table detection threshold', 0.0, 1.0, 0.8)
    TSR_th = st2.slider('Table structure recognition threshold', 0.0, 1.0, 0.8)
    OCR_th = st3.slider("Text Probs Threshold", 0.0, 1.0, 0.5)

    st1, st2, st3, st4 = st.columns((1, 1, 1, 1))

    padd_top = st1.slider('Padding top', 0, 200, 40)
    padd_left = st2.slider('Padding left', 0, 200, 40)
    padd_right = st3.slider('Padding right', 0, 200, 40)
    padd_bottom = st4.slider('Padding bottom', 0, 200, 40)

    te = TableExtractionPipeline()
    # for img in image_list:
    if img_name is not None:
        asyncio.run(
            te.start_process(img_name,
                             TD_THRESHOLD=TD_th,
                             TSR_THRESHOLD=TSR_th,
                             OCR_THRESHOLD=OCR_th,
                             padd_top=padd_top,
                             padd_left=padd_left,
                             padd_bottom=padd_bottom,
                             padd_right=padd_right,
                             delta_xmin=0,
                             delta_ymin=0,
                             delta_xmax=0,
                             delta_ymax=0,
                             expand_rowcol_bbox_top=0,
                             expand_rowcol_bbox_bottom=0))