An Intelligent System for Digitization and Processing of Historical Arabic Documents
Moncef Charfi, Wafa Boussellaa, Adel M. Alimi · International Journal of Computer Processing Of Languages · 2007
The documentary patrimony deposited in the libraries and archives represents an essential part in the collective memory; it reflects the diversity of languages, peoples and cultures. But such memory is fragile and a part of such patrimony regularly disappears by accident, war or ageing.There exist about three million manuscripts of an Arab or Islamic origin, scattered throughout the world. They are not well preserved, that is why researchers encounter difficulty in consulting them. The digitization of such documents has become an absolute necessity for saving and preserving them for future generations.This paper presents a contribution in the domain of digitization and processing of images of historical documents stored in the Arabic libraries. After being scanned, the raw images obtained undergo a primary pre-processing treatment in order to clean them and restore them; then they go through a second phase of image analysis which consists in segmenting the documents so as to separate out texts and graphics, and in compressing the images so as to reduce their stocking cost and their communication time. All such operations are necessary for the retro conversion of the images of historical documents for the purpose of indexing and hosting them on the internet.