A vast collection of Arabic historical document has been digitalized by national archive and museums. Despite being in digital form, the study of historical documents is still difficult, because historical document image doesn’t benefit from high level features such as word search. Deciphering old manuscript is a difficult task because of degradations that may alter the document content, the use of calligraphic styles that are no longer employed, in addition to the large handwriting variability.
The shape analysis of Arabic word is an interesting avenue for their recognition in ancient document. The field of shape analysis studies the geometry of a shape for modeling as in biomedical field or for recognition as in computer vision. The shape is usually represented by its outer contour or its surface and the shape is considered as a whole. In the context of word recognition, it has the advantages to avoid the difficult task of character segmentation and of feature selection, and to be closer to the human perception.