qurator-spk/sbb_pixelwise_segmentation
1
0
Fork 0
mirror of https://github.com/qurator-spk/sbb_pixelwise_segmentation.git synced 2025-08-18 06:00:04 +02:00
Code Issues Releases Wiki Activity

loading xmls with UTF-8 encoding

Browse source
This commit is contained in:
vahidrezanezhad 2025-08-07 10:32:49 +02:00
parent 1fe31bdeb3
commit ef0f08ec1f
2 changed files with 18 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

2
generate_gt_for_training.py
View file

@ -513,7 +513,7 @@ def visualize_ocr_text(xml_file, dir_xml, dir_out):
#y_bb = bb_ind[1] #y_bb = bb_ind[1]
#w_bb = bb_ind[2] #w_bb = bb_ind[2]
#h_bb = bb_ind[3] #h_bb = bb_ind[3]
if ocr_texts[index]:
font = fit_text_single_line(draw, ocr_texts[index], font_path, w, int(h*0.4) ) font = fit_text_single_line(draw, ocr_texts[index], font_path, w, int(h*0.4) )
##draw.rectangle([x_bb, y_bb, x_bb + w_bb, y_bb + h_bb], outline="red", width=2) ##draw.rectangle([x_bb, y_bb, x_bb + w_bb, y_bb + h_bb], outline="red", width=2)

10
gt_gen_utils.py
View file

@ -244,7 +244,7 @@ def update_region_contours(co_text, img_boundary, erosion_rate, dilation_rate, y
return co_text_eroded, img_boundary return co_text_eroded, img_boundary
def get_textline_contours_for_visualization(xml_file): def get_textline_contours_for_visualization(xml_file):
tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding = 'iso-8859-5')) tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding='utf-8'))
root1=tree1.getroot() root1=tree1.getroot()
alltags=[elem.tag for elem in root1.iter()] alltags=[elem.tag for elem in root1.iter()]
link=alltags[0].split('}')[0]+'}' link=alltags[0].split('}')[0]+'}'
@ -285,7 +285,7 @@ def get_textline_contours_for_visualization(xml_file):
def get_textline_contours_and_ocr_text(xml_file): def get_textline_contours_and_ocr_text(xml_file):
tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding = 'iso-8859-5')) tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding='utf-8'))
root1=tree1.getroot() root1=tree1.getroot()
alltags=[elem.tag for elem in root1.iter()] alltags=[elem.tag for elem in root1.iter()]
link=alltags[0].split('}')[0]+'}' link=alltags[0].split('}')[0]+'}'
@ -355,7 +355,7 @@ def fit_text_single_line(draw, text, font_path, max_width, max_height):
return ImageFont.truetype(font_path, 10) # Smallest font fallback return ImageFont.truetype(font_path, 10) # Smallest font fallback
def get_layout_contours_for_visualization(xml_file): def get_layout_contours_for_visualization(xml_file):
tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding = 'iso-8859-5')) tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding='utf-8'))
root1=tree1.getroot() root1=tree1.getroot()
alltags=[elem.tag for elem in root1.iter()] alltags=[elem.tag for elem in root1.iter()]
link=alltags[0].split('}')[0]+'}' link=alltags[0].split('}')[0]+'}'
@ -630,7 +630,7 @@ def get_images_of_ground_truth(gt_list, dir_in, output_dir, output_type, config_
for index in tqdm(range(len(gt_list))): for index in tqdm(range(len(gt_list))):
#try: #try:
print(gt_list[index]) print(gt_list[index])
tree1 = ET.parse(dir_in+'/'+gt_list[index], parser = ET.XMLParser(encoding = 'iso-8859-5')) tree1 = ET.parse(dir_in+'/'+gt_list[index], parser = ET.XMLParser(encoding='utf-8'))
root1=tree1.getroot() root1=tree1.getroot()
alltags=[elem.tag for elem in root1.iter()] alltags=[elem.tag for elem in root1.iter()]
link=alltags[0].split('}')[0]+'}' link=alltags[0].split('}')[0]+'}'
@ -1311,7 +1311,7 @@ def find_new_features_of_contours(contours_main):
return cx_main, cy_main, x_min_main, x_max_main, y_min_main, y_max_main, y_corr_x_min_from_argmin return cx_main, cy_main, x_min_main, x_max_main, y_min_main, y_max_main, y_corr_x_min_from_argmin
def read_xml(xml_file): def read_xml(xml_file):
file_name = Path(xml_file).stem file_name = Path(xml_file).stem
tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding = 'iso-8859-5')) tree1 = ET.parse(xml_file, parser = ET.XMLParser(encoding='utf-8'))
root1=tree1.getroot() root1=tree1.getroot()
alltags=[elem.tag for elem in root1.iter()] alltags=[elem.tag for elem in root1.iter()]
link=alltags[0].split('}')[0]+'}' link=alltags[0].split('}')[0]+'}'