Table transformer : Extract information from detected table

[tzktz]

Hi bro @NielsRogge while extracting information from detected table are not accurate..

The table which is correctly find..

The output i get..for above table

Max number of columns: 4
['OEAMCGOAEAR', 'CaQ .', 'Darosit', '']
['Balect', '0.0d', '0 . 00', '119.08']
['0i-Jan 2019', 'PRCR/843', '', '']
['0_-Jan-2019', 'DRCR 444', '100-00', '219']
['2019', 'ERcdeay', '100-00', '']
['ane 2019', '@Rcn/aas', '100_00', '1.9  03']
['2019', 'EFTAIC BaK RSINrRD BE;', 'J0j', '100122 .']
['02-Jan-2019', 'PRCR 095', '100.00', '10,022-']
['20| 0', 'PRCR/9', '100-00', '922 .74']
['Jen-2019', 'CrdR /Yokxa-MODIR Tower', '500 _', '']
['07-Jan-?019', 'EET/IC/BANK AS14/FRD BEET;', '913 .6.', '']
['Di-Jan-7019', 'Cade *orie #odit Totrd', '0oo-00', '"413']
['10-Jan-2019', 'CD? /Kor KODIA TC3r3', 'S0o.0q', '']
['', '', '', '']

you can see the words difference from table image and extract information..

code i have used for this..

import numpy as np
import csv
import easyocr
from tqdm.auto import tqdm

reader = easyocr.Reader(['en']) # this needs to run only once to load the model into memory

def apply_ocr(cell_coordinates):
    # let's OCR row by row
    data = dict()
    max_num_columns = 0
    for idx, row in enumerate(tqdm(cell_coordinates)):
      row_text = []
      for cell in row["cells"]:
        # crop cell out of image
        cell_image = np.array(cropped_table.crop(cell["cell"]))
        # apply OCR
        result = reader.readtext(np.array(cell_image))
        if len(result) > 0:
          # print([x[1] for x in list(result)])
          text = " ".join([x[1] for x in result])
          row_text.append(text)

      if len(row_text) > max_num_columns:
          max_num_columns = len(row_text)

      data[idx] = row_text

    print("Max number of columns:", max_num_columns)

    # pad rows which don't have max_num_columns elements
    # to make sure all rows have the same number of columns
    for row, row_data in data.copy().items():
        if len(row_data) != max_num_columns:
          row_data = row_data + ["" for _ in range(max_num_columns - len(row_data))]
        data[row] = row_data

    return data

data = apply_ocr(cell_coordinates)

for row, row_data in data.items():
    print(row_data)