post_process_dictionary library
Dictionary-based near-miss correction for OCR post-processing.
Corrects single-character OCR confusions in non-dictionary words using edit-distance matching.
Functions
-
correctNearMissDictionaryWords(
String line) → String - Corrects near-miss dictionary words with strict edit-distance limits.
-
splitConcatenatedDictionaryWords(
String line) → String - Splits concatenated words that are not in the dictionary.