A collaborative enhancement-compression approach for historical document images based on PDE-analysis

Historical document images suffer from several kinds of degradation affecting their readability and increase their sizes when digitizing. Indeed, preserving the old document heritage requires an important storage infrastructures, while this space could be significantly reduced if one manages to safeguard these documents without their considerable amount of artifacts which increasing their entropy. We present in this work a new and more advantageous solution for the document image compression technology dedicated to National Archives and Libraries. The aim of this work is to propose a novel historical document compression scheme judiciously combined with a novel automatic enhancement scheme, both based on PDE-Analysis applied in an innovative way, to face this challenging issue without affecting the look and feel of the historical document image. Throughout experiment, the proposal is fairly evaluated on overall DIBCO datasets and some historical documents collected from the web by means of objective measures and perceptual judgment against the most used enhancement algorithms, the most robust compression standards such as JPEG-XR and the most used sequential compression-enhancement combinations techniques to proof the robustness of the proposed collaborative approach against classic sequential approaches.