NN/FST - Unsupervised OCR-Postcorrection based on Neural Networks and Finite-state Transducers

点击翻译按钮获取中文摘要

The project aims to develop a ready to use software für modul 3 (text optimization) of the OCR-D architecture. The focus of development is in area 3.B (postcorrection) where we plan to also evaluate some up-to-date OCR systems (area 3.A). The main technologies that we plan to use are neural nets (NN) combined with finite-state transducers (FST) to decode recognized lines of text within a noisy-channel model.