qurator-spk/eynollah
1
0
Fork 0
mirror of https://github.com/qurator-spk/eynollah.git synced 2025-07-01 15:09:54 +02:00
Code Issues Projects Releases Wiki Activity

In the context of OCR, if Page-XML files already contain text, the new predicted text will replace the existing text.

Browse source
This commit is contained in:
vahidrezanezhad 2025-03-26 18:42:06 +01:00
parent 370d44a66b
commit 7df0427b04
1 changed files with 36 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

31
src/eynollah/eynollah.py
View file

@ -4965,7 +4965,7 @@ class Eynollah_ocr:
self.model_ocr.to(self.device)
else:
self.model_ocr_dir = dir_models + "/model_step_100000_ocr"#"/model_0_ocr_cnnrnn"#"/model_23_ocr_cnnrnn"
self.model_ocr_dir = dir_models + "/model_step_150000_ocr"#"/model_0_ocr_cnnrnn"#"/model_23_ocr_cnnrnn"
model_ocr = load_model(self.model_ocr_dir , compile=False)
self.prediction_model = tf.keras.models.Model(
@ -5358,6 +5358,13 @@ class Eynollah_ocr:
indexer = 0
indexer_textregion = 0
for nn in root1.iter(region_tags):
is_textregion_text = False
for childtest in nn:
if childtest.tag.endswith("TextEquiv"):
is_textregion_text = True
if not is_textregion_text:
text_subelement_textregion = ET.SubElement(nn, 'TextEquiv')
unicode_textregion = ET.SubElement(text_subelement_textregion, 'Unicode')
@ -5365,12 +5372,34 @@ class Eynollah_ocr:
has_textline = False
for child_textregion in nn:
if child_textregion.tag.endswith("TextLine"):
is_textline_text = False
for childtest2 in child_textregion:
if childtest2.tag.endswith("TextEquiv"):
is_textline_text = True
if not is_textline_text:
text_subelement = ET.SubElement(child_textregion, 'TextEquiv')
unicode_textline = ET.SubElement(text_subelement, 'Unicode')
unicode_textline.text = extracted_texts_merged[indexer]
else:
for childtest3 in child_textregion:
if childtest3.tag.endswith("TextEquiv"):
for child_uc in childtest3:
if child_uc.tag.endswith("Unicode"):
child_uc.text = extracted_texts_merged[indexer]
indexer = indexer + 1
has_textline = True
if has_textline:
if is_textregion_text:
for child4 in nn:
if child4.tag.endswith("TextEquiv"):
for childtr_uc in child4:
if childtr_uc.tag.endswith("Unicode"):
childtr_uc.text = text_by_textregion[indexer_textregion]
else:
unicode_textregion.text = text_by_textregion[indexer_textregion]
indexer_textregion = indexer_textregion + 1