Authorial manuscript image analysis using markovian models: the Bovary project

In this paper, we present our recent work on the Bovary project, a manuscript digitization project of the famous French writer Gustave Flaubert, which aims at providing an online access to a hyper textual edition of “Madame Bovary” draft sets. We first describe the global context of this project, its main objectives, and then focus on the document image analysis problem for which we have developed effective and powerful page layout extraction algorithms based on Markovian generative and discriminative models such as Hidden Markov Random Fields and Conditional Random Fields. We show with some experiments that these stochastic and contextual models are able to cope with local spatial variability while taking into account some prior knowledge about the global structure of the document image, thus being well suited to the segmentation of very complex document images like authorial manuscripts or historical documents.