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.

Goal

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).

Workflow

Literature review
Data preparation
Implementation
Written Report/Thesis and final presentation

References

[1] Lucas N. Kirsten, Ricardo Piccoli, Ricardo Ribani: Evaluating Deep Neural Networks for Image Document Enhancement. CoRR abs/2106.15286 (2021)