Pre-processing of scanned documents is a necessary first step in the process cycle of any document processing application. While pre-processing methods are generally language independent, the effectiveness of downstream OCR processes can often be improved by language/script specific adaptations, particularly in the case of non-Latin scripts such as Arabic and Indic scripts. In this chapter, we present some techniques that have proven effective for the pre-processing of handwritten Arabic documents.
CITATION STYLE
Shi, Z., Setlur, S., & Govindaraju, V. (2012). Pre-processing Issues in Arabic OCR. In Guide to OCR for Arabic Scripts (pp. 79–102). Springer London. https://doi.org/10.1007/978-1-4471-4072-6_4
Mendeley helps you to discover research relevant for your work.