The enhancement of document images describes the task of improving the visual quality of document images. Thus, degradations (like background clutter or uneven illumination) can be removed. Enhancement can be used as a preprocessing step for further document image analysis methods – including text recognition.
The aim of this internship is to select an existing method or to create a new method for document image enhancement. The method should make use of deep learning, whereby the overall aim is to generate a lightweight model that can be applied on mobile phones (via the DocScan app).
Written Report/Thesis and final presentation
 Lucas N. Kirsten, Ricardo Piccoli, Ricardo Ribani: Evaluating Deep Neural Networks for Image Document Enhancement. CoRR abs/2106.15286 (2021)