Untitled

 avatar
unknown
plain_text
a year ago
3.9 kB
6
Indexable
res_table = [] # список строк со всеми значениями ячеек
current_row = [] # значения ячеек текущей строки
for table in extracted_tables: # цикл по всем таблицам
    for row in table.content.values(): # цикл по всем строкам
        for cell in row: # цикл по всем столбцам
            crop = table_img[cell.bbox.y1:cell.bbox.y2, cell.bbox.x1:cell.bbox.x2] # берем ячейку
            result = reader.readtext(crop) # координаты bounding boxes, распознанный текст в них и вероятность
            txt = "\n".join([elem[1] for elem in result]) # распознанный текст из всех bounding boxes
            txt_n = txt.replace('\n',' ') # распознанный текст без переноса строк
            current_row.append(txt_n)        
        res_table.append(current_row)
        current_row = []
---------------------------------------------------------------------------
error                                     Traceback (most recent call last)
Input In [175], in <cell line: 3>()
      5 for cell in row: # цикл по всем столбцам
      6     crop = table_img[cell.bbox.y1:cell.bbox.y2, cell.bbox.x1:cell.bbox.x2] # берем ячейку
----> 7     result = reader.readtext(crop) # координаты bounding boxes, распознанный текст в них и вероятность
      8     txt = "\n".join([elem[1] for elem in result]) # распознанный текст из всех bounding boxes
      9     txt_n = txt.replace('\n',' ') # распознанный текст без переноса строк

File /opt/conda/lib/python3.8/site-packages/easyocr/easyocr.py:454, in Reader.readtext(self, image, decoder, beamWidth, batch_size, workers, allowlist, blocklist, detail, rotation_info, paragraph, min_size, contrast_ths, adjust_contrast, filter_ths, text_threshold, low_text, link_threshold, canvas_size, mag_ratio, slope_ths, ycenter_ths, height_ths, width_ths, y_ths, x_ths, add_margin, threshold, bbox_min_score, bbox_min_size, max_candidates, output_format)
    440 def readtext(self, image, decoder = 'greedy', beamWidth= 5, batch_size = 1,\
    441              workers = 0, allowlist = None, blocklist = None, detail = 1,\
    442              rotation_info = None, paragraph = False, min_size = 20,\
   (...)
    448              threshold = 0.2, bbox_min_score = 0.2, bbox_min_size = 3, max_candidates = 0,
    449              output_format='standard'):
    450     '''
    451     Parameters:
    452     image: file path or numpy-array or a byte stream object
    453     '''
--> 454     img, img_cv_grey = reformat_input(image)
    456     horizontal_list, free_list = self.detect(img, 
    457                                              min_size = min_size, text_threshold = text_threshold,\
    458                                              low_text = low_text, link_threshold = link_threshold,\
   (...)
    464                                              bbox_min_size = bbox_min_size, max_candidates = max_candidates
    465                                              )
    466     # get the 1st result from hor & free list as self.detect returns a list of depth 3

File /opt/conda/lib/python3.8/site-packages/easyocr/utils.py:757, in reformat_input(image)
    755 elif len(image.shape) == 3 and image.shape[2] == 3: # BGRscale
    756     img = image
--> 757     img_cv_grey = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    758 elif len(image.shape) == 3 and image.shape[2] == 4: # RGBAscale
    759     img = image[:,:,:3]

error: OpenCV(4.9.0) /io/opencv/modules/imgproc/src/color.cpp:196: error: (-215:Assertion failed) !_src.empty() in function 'cvtColor'
Editor is loading...
Leave a Comment