A Word & Character N-Gram based Arabic OCR Error Simulation model

Mostafa Ezzat; Tarek Ahmed ElGhazaly; Mervat Gheith

doi:10.24297/ijct.v12i8.2999

Authors

Mostafa Ezzat Institute of Statistical Studies & Research, Cairo University, EGYPT
Tarek Ahmed ElGhazaly Institute of Statistical Studies & Research, Cairo University, EGYPT
Mervat Gheith Institute of Statistical Studies & Research, Cairo University, EGYPT

DOI:

https://doi.org/10.24297/ijct.v12i8.2999

Keywords:

Arabic OCR Degraded Text Retrieval, Arabic OCR-Degrade Text, Orthographic Query Expansion, Synthesize OCR-Degraded Text.

Abstract

This paper provides a new model aimed to enhanceArabic OCR degraded text retrieval effectiveness. The proposed model based onsimulating the Arabic OCR recognition mistakesbased on both, word based and Character N-Gram approaches. Then we expand the user search query using the expected OCR errors. The resulting search query expanded gives high precision and recall values in searching Arabic OCR-Degraded text rather than the original query. The proposed model showed a significant increase in the degraded text retrieval effectiveness over the previous models. The retrieval effectiveness of the newmodel is %93, while the best effectiveness published for word based approach was %84 and the best effectiveness for character based approach was %56.