Versatile Search of Scanned Arabic Handwriting

Abstract

Searching scanned handwritten documents is a relatively unexplored frontier for documents in any language. In the general search literature retrieval methods are described as being either image-based or text-based with the corresponding algorithms being quite different. Versatile search is defined as a framework where the query can be either a textual string or an image snippet in any language and the retrieval method is a fusion of text-and imageretrieval methods. An end-to-end versatile system known as CEDARABIC is described for searching a repository of scanned handwritten Arabic documents; in addition to being a search engine it includes several tools for image processing such as line removal, line segmentation, creating ground-truth, etc. In the search process of CEDARABIC the query can be either in English or Arabic. A UNICODE and an image query are maintained throughout the search, with the results being combined by an artificial neural network. The combination results are better than each approach alone. The results can be further improved by refining the component pieces of the framework (text transcription and image search).

A review of feature extraction techniques for handwritten Arabic text recognition

“…Most data from insurance companies or banks are confidential for non-lucrative research. Moreover, many works in the Arabic handwritten text recognition field have used databases that are not available to the public [7] [8] . However, over the past decade, several large standard databases have been developed.…”

Recognition of off-line printed Arabic text using Hidden Markov Models

“…Arabic text recognition, which was not researched as thoroughly as Latin, Japanese, or Chinese, is receiving a renewed interest not only from Arabic-speaking researchers but also from non-Arabic-speaking researchers. Samples of this research work are given in the references [1][2][3][4][5][6][7][8][9][10]. This has resulted in the improvement of the state of the art in Arabic text recognition in recent years.…”