Apport du traitement des images à la numérisation des documents manuscrits anciens

Image processing is often necessary for extracting the content of ancient documents. We present here techniques for restoring images and removing noise, extracting document structures (separating graphical elements and illustrations from text, extracting text lines) and, when possible, recognizing the textual or musical symbols which may be present in the image. These techniques, which are classified into three processing levels : preprocessing, segmentation, analysis and recognition, are described and some of them are illustrated on images of ‘ Lettres de Rémission’ of the 16 century. MOTS-CLÉS : prétraitements – segmentation – binarisation – extraction de lignes – structure graphique