Reading order detection on handwritten documents

Abstract Recent advances in Handwritten Text Recognition and Document Layout Analysis have made it possible to convert digital images of manuscripts into electronic text. However, providing this text with the correct structure context is still an open problem that needs be solved actually enable extracting relevant information conveyed by The most important needed for a set elements their reading order. Most studies on order are rule-based approaches focus printed documents. Much less attention has been paid so far handwritten documents, where becomes particularly important—and challenging. In work, we propose new approach automatically determine regions lines task approached as sorting order-relation operator learned from examples. We experimentally demonstrate effectiveness our method three different datasets at hierarchical levels.