ajmc.ocr package

ajmc.ocr is a package for optical character recognition (OCR) of historical documents. It is very work-in-progress and is not meant to be used as a library yet. Methods, classes and functions are subject to change at any time and are mainly implemented around experiments (notably in ocr.pytorch and ocr.tesseract).

Subpackages

• ajmc.ocr.preprocessing package
  • Submodules
  • ajmc.ocr.preprocessing.data_augmentation module
  • ajmc.ocr.preprocessing.data_preparation module
  • ajmc.ocr.preprocessing.get_source_datasets module
  • ajmc.ocr.preprocessing.pagify_dataset module
• ajmc.ocr.pytorch package
  • Submodules
  • ajmc.ocr.pytorch.config module
  • ajmc.ocr.pytorch.ctc_decoder_torch module
    • BeamCTCDecoder
      • BeamCTCDecoder.convert_tensor()
      • BeamCTCDecoder.convert_to_strings()
      • BeamCTCDecoder.decode()
    • Decoder
      • Decoder.decode()
    • GreedyDecoder
      • GreedyDecoder.decode()
      • GreedyDecoder.process_string()
  • ajmc.ocr.pytorch.data_generation module
  • ajmc.ocr.pytorch.data_processing module
  • ajmc.ocr.pytorch.datasets module
  • ajmc.ocr.pytorch.model module
  • ajmc.ocr.pytorch.train_parallel module
• ajmc.ocr.tesseract package
  • Submodules
  • ajmc.ocr.tesseract.dictionaries module
  • ajmc.ocr.tesseract.experiments module
  • ajmc.ocr.tesseract.models module
  • ajmc.ocr.tesseract.pipeline module
  • ajmc.ocr.tesseract.tesseract_utils module

Submodules

ajmc.ocr.config module

ajmc.ocr.evaluation module

ajmc.ocr.font_utils module

ajmc.ocr.utils module

ajmc.ocr.variables module