I may need to do a lot of scanning of texts that could include Hanzi (both simplified and traditional), Pinyin, and English (sometimes all three together). What’s good these days for that (emphasis on simplified characters)? And how good is good when it comes to OCR with Chinese characters? 80% accuracy? 90%?
Although free or inexpensive is always good, I might be willing to pay up to, say, NT$13,000, if the results would justify this.
ABBYY just came out with a version that’s supposed to handle Chinese characters. Perhaps that?
I’d prefer to have the program also work within PDF documents, such that I could run OCR on the PDF and have the OCR version work in a text search of the PDF while leaving the original scanned image alone (i.e., I can live with some mistakes in the OCR but not mistakes in the PDF image).
I’ve been using ReadIris with the Asian add-on pack. Results are pretty good thus far. I used to use Danqing but this was cheaper. I didn’t buy the latest version either – so I got a pretty good deal on Ebay. However, if you download the ReadIris demo and then don’t respond and don’t purchase it for 30 days or whatever it is, they will probably send you a coupon for about the same amount off the newest version as I got as a discount by buying the older version (not knowing they would send the stupid coupon).
Thanks, Ironlady. Someone at an online software store just ran a few sample pages for me through the latest ReadIris Asian edition. The results with the Hanzi are quite good. The English is also pretty good. The Pinyin, however, is FUBAR. Maybe if I told the program it’s really in Czech or something…
The latest ABBYY doesn’t seem to want to recognize my scanner, so I’m still trying to get that to work.
I’m looking for exactly the same thing and found this thread. I would love to be able to use Acrobat to scan pages with hanzi and get a pinyin transcription. Is there any updated information on pdf-based or other software that will do this and produce non-FUBAR pinyin?
I’d be surprised if there’s one program that does that, or at least does it well.
As for getting good Pinyin texts from Hanzi, at present the best program for this is Key. H2P, a much more focused converter than the full Key program, should work just as well since it’s from the same company; but I haven’t tried it out myself.
It looks like H2P will only convert Word documents to Pinyin. So there’s nothing that will convert scanned images?