DocEng 2022

Conference: Symposium on Document Engineering 2022

Speaker: Philipp Hildebrandt

Abstract:Recognizing disturbed text in real-life images is a difficult problem, as information that is missing due to low resolution or out-of-focus text has to be recreated. Combining text super-resolution and optical character recognition deep learning models can be a valuable tool to enlarge and enhance text images for better readability, as well as recognize text automatically afterwards. We achieve improved peak signal-to-noise ratio and text recognition accuracy scores over a state-of-the-art text super-resolution model TBSRN on the real-world low-resolution dataset TextZoom while having a smaller theoretical model size due to the usage of quantization techniques. In addition, we show how different training strategies influence the performance of the resulting model.

This is joint work with Maximilian Schulze, Sarel Cohen, Vanja Doskoč, Raid Saabni and Tobias Friedrich.