Zur Hauptnavigation / To main navigation

Zur Sekundärnavigation / To secondary navigation

Zum Inhalt dieser Seite / To the content of this page

Sekundärnavigation / Secondary navigation

Inhaltsbereich / Content

EMS and Xilinx release demo for hardware accelerated OCR on Xilinx PYNQ

Microelectronic Systems Design Research Group in cooperation with Xilinx Inc. has released a demo of FPGA-accelerated quantized Long Short-Term Memory recurrent neural network for highly accurate Optical Character Recognition of old German Fraktur text.

Optical Character Recognition is conversion of printed or handwritten text images into machine-encoded text. It is a building block of many processes such as machine translation, text-to-speech conversion and text mining.

The demo is a pip installable package for Xilinx PYNQ and is now publicly available as a Github repository.