This is an experiment to see if google will perform optical character recognition on the file. They are written in Japanese. I hope to be able to recover an html version after google indexes them.
E5M_INST-Communications-Protocol
OCR and support for Japanese OCR
- Online Japanese OCR Tool
- Tesseract OCR readme
- Tesseract-ocr training data for Japanese
- OCRopus
- Article about scanning an entire book
HP abandoned the code for Tesseract and later donated it to a University who then invited Google to partake. It is probably the way to go to do OCR on Japanese. No installer for Windows so most likely easiest on a linux box
0 Comments