This paper presents preliminary results for document classification of ancient Hebrew manuscripts. The main goal is to discriminate between documents of different writing styles, locations and dates. This classification depends crucially on good binarization of the corrupted manuscripts. We propose an accurate method for binarization of the manuscripts. We further propose and test topological features for document classification based on the document characters, which, at this stage, we apply only on the character Aleph. Our results so far yield 100% correct classification of the documents.