This chapter addresses automatic printed Arabic text recognition. Ara- bic text recognition has its own difficulties due to the cursive nature of the scripts, overlapping characters, large number of dots and diacritics, etc. In this chapter, we present a general framework for a printed Arabic text recognition system.We then discuss different phases of such a system, e.g., pre-processing, feature extraction, and classification.We present different reported techniques for each phase. In addi- tion, different databases for printed Arabic text recognition are discussed here. We conclude this chapter by presenting several experimental results for hidden Markov model (HMM)-based printed Arabic text recognition.
CITATION STYLE
Ahmed, I., Mahmoud, S. A., & Parvez, M. T. (2012). Printed Arabic Text Recognition. In Guide to OCR for Arabic Scripts (pp. 147–168). Springer London. https://doi.org/10.1007/978-1-4471-4072-6_7
Mendeley helps you to discover research relevant for your work.