Handwriting documents denoising and indexing using Hermite transform

This paper presents a new system for handwriting documents denoising and indexing. This work is based on the Hermite Transform, which is a polynomial transform and a good model of the human visual system (HVS). We use this transformation to decompose handwriting documents into local frequencies and using this decomposition, we analyze the visual aspect of handwritings to compute similarity measures. A direct application is the management of document databases, allowing to find documents coming from the same author or to classify documents containing handwritings that have similar visual aspect. Moreover, ancient documents can contain degradations from different origins. It is often necessary to clean the backgrounds of those degraded documents before analysing them. The current results are very promising and show that it is possible to characterize handwritten drawings without any a priori graphemes segmentation.