Modified character-level deciphering algorithm for OCR in degraded documents

Modi cations to a previous character level deciphering algorithm for OCR are presented in this paper that are able to handle touching characters and are tolerant to mistakes made at the clustering stage The objective of a character level deciphering algorithm is to assign alphabetic identities to character patterns such that the character repetition pattern in an input text matches the letter repetition pattern provided by a language model Degradation in document images usually causes the occurrence of touching characters and mistakes in clustering the character patterns which pose di culties for character level deciphering algorithms The modi cations proposed in this paper tightly integrate visual constraints from characters and touching patterns with constraints from a language model This solves the problem of touching characters and reverses clustering mistakes The provides a deciphering algorithm with robust performance under image degradation