Jump to content
Chinese-Forums
  • Sign Up

Chinese OCR


techie

Recommended Posts

I would like to hear feedback from other experienced users of scan software which allows you to input Chinese and English documents on the same page to latter allow you to edit text.

I have heard of Dang Chin Chinese/English scanner software which handles simplified and Traditional Chinese.

Is the process straight forward? How much editing is required after the input?

Any information or feedback would be appreciated.

Thanks.

Besides the prices and site addresses the most important feedback to me is your own personal experience with the product.

Link to comment
Share on other sites

  • 4 weeks later...

Ordered Dan ching last night. Decided to go for the real deal. Was impressed with the trial and have heard good things. I will let you know more later.

Has anyone tried 清華紫光? How effective is it? Is it just Simplified Chinese recognition?

Kong

Link to comment
Share on other sites

Back to the topic. I tried out that Danching available on that website, now deleted. It seems to be the "Jianti" bundled version that is sometimes sold with scanners here in China and Taiwan. Not too impressed. This copy has no dictionaries to work from. My full version arrives tomorrow. I have heard it is much better than this slimmed down version. Later

Kong

Link to comment
Share on other sites

At what price did you find the sofware? Where are you getting it from?

I tend to agree with you , Konglong, that the bundled version, though it does the job, still needs a lot to be desire!

Regards.

(Which is the site for the page that has been deleted? Or, where did you get your bundled package from?)

Link to comment
Share on other sites

Google cached your old page with the link. (Got to love Google) I bought it from 三井 here in Taiwan for about $100. Got the good old academic discount. It usually runs for about $200 US, but also saw a downloadable full version for around $160 US. Supposdly this fun versions dictionary comparision capibilities have a much better result than the bundled.

Later

Link to comment
Share on other sites

  • 2 years later...

I currently own 丹青文件辨識4.50. (Danching, Danqing) Though it was the Chinese version of the software, NewSoft finally came out with an update (Danqing v4.50.x to v4.50.09) that if you update it over the top of your Chinese version, it will then add an English interface. This can be changed in the Multilingual User Interface menu. Version 5.0 was released late last year (2005). It already includes the English interface. Retail runs about $250 US, but if you can get the Academic discount, you can pick it up for about $100 US.

One nice thing about Danqing are the customized dictionaries you can create. The advantage to using these are if the program can not distinguish a character in the jpg/tiff/bmp, it will compare it to the dic files to see if there is a match. This is helpful in getting a more accurate OCR result.

There are 10 traditional, 10 simplified, and 10 Japanese dictionaries. The traditional are in Big5 encoding and simplified GB.

Traditional - PCCRDIC#.DIC

Simplified - PSCRDIC#.DIC

Japanese - PJCRDIC#.DIC

If you've been adding words to the M$ Chinese IME, you can export these words to a file with the User Defined Phrase Tool.

langbar.jpg

udpt.jpg

Use a text editor to remove the pinyin entries, convert it to Big5 and paste them into one of the DIC files. If not, you can create your own word list. One word per line.

Instead of exporting to word or PDF, I prefer Wenlin 文林. This way I can control the encoding after making changes. You can specifically pick other programs to export to. If you don't have the full Wenlin, it doesn't matter. Even the demo allows you to save in many different encodings.

I haven't used any other Chinese OCR programs out there so it would be hard for me to compare. But I know it is much faster for me to go through and edit the document after using Danqing rather than typing up the same text. Hope others find this useful information. I've noticed lately there have been some posts on OCR software available. The only thing I have not liked about the software is NewSoft's support. They spent more effort trying to get me to hang up rather than answering my questions. Other than that I like the software.

Josh

-Danqing product info Also 中文版

-Danqing 5.0 30 Day Trial

box_danching.jpg

Link to comment
Share on other sites

  • 7 months later...

Hi there anyone can advice where I could purchase Cheaper price for Dan Ching version 5.0 English interface or download for free. Currently there is a link http://ckarea.com/bbs/viewthread.php?tid=19532 mention for giving free Dan Ching 5.0, but I am not sure how to do that, any advice? Currently I have Dan Ching ver 4.0 comes with Umax Scanner bundle... but I have a lot of Chinese book to scan... I have old version of 清華紫光 Th-ocr 7.5 running in Window 95 & 98. And I also have Th-ocr 2000 Edition, but I still prefer the Dan Ching after using the Ver 4.0. Appreciate any advice.:roll:

Link to comment
Share on other sites

I have a ton of Chinese language learning material I'd like to scan. Does anyone knows of a Chinese OCR program that can handle Chinese traditional, simplified, pinyin with tone marks and English all on the same page?

Thanks, tom

Link to comment
Share on other sites

Does anyone knows of a Chinese OCR program that can handle Chinese traditional, simplified, pinyin with tone marks and English all on the same page?

I think the Asian version of Readiris can handle Chinese & English, not sure about pinyin, but perhaps you could build a custom dictionary or something...

Link to comment
Share on other sites

Hi Tom,

Please check out a OC Software Sunmipage Chinese/English Bilingual OCR Engine, it will do the trick.. check out at the website htp://www.cyberway.com.sg/~computek/index.htm

I have never try it, you could ask the company for more detail for purchase.

Link to comment
Share on other sites

Thanks Mirgcine for your advice, but I am really interested in Dan Ching 5.0, compare to Th-ocr 2000, or Th-ocr 7.5, it has much more accurancy input the Th-ocr. Moreover, it will not leave additional mess once it is convert and save into RTF or Ms word file. When you open up the Th-ocr file.. you will see many trail files left after converting to Text. You need to manully delete it, otherwise it will eat up your Harddisk space. Using the same Tiff file for conversion, Dan Ching can read almost 98% and convert into text file but Th-ocr 2000 doesn't come close.

Link to comment
Share on other sites

  • 3 weeks later...

Hi All, Finally I have found a Link to download Dan Ching 5.0.. no Kidding. I just want to share with the desperate folks out there who are just like me seeking one. Download before the link disappear. Well ... I can give 95% satisfaction using this OCR compare to Th-OCR Ver 7.5 and Th-OCR 2000. However.. I wish some kind folks out there could share either "Oriental Express Enterprise 6.0" or Transwhiz 9.0 Professional. I have use both Trial program.. they are quite useful and handy 60% accuracy.. although human still need to Foolproof and edit to make it perfect. I have try Dr 6.0.. but still couldn't compare to Oriental & Transwhiz. Dr 6.0 could also download at this link too.:wink:

Link to comment
Share on other sites

  • 1 year later...

Since technology and prices can change fast in this field I thought I'd raise this question again: What's currently (2008 summer) the best software to get for OCR of Chinese characters? Preferably this will be something that can handle English and Pinyin in documents as well.

Also, much of the previous parts of this thread have dealt with freeware or trial versions. But I'd be willing to pay more for a good-quality product.

(What, BTW, is the current standard for highest quality when it comes to OCR of real-world Hanzi documents? 80% accuracy? 90%?)

ABBYY's just-released edition of FineReader (9.0) adds support for "Chinese, Japanese, Thai, and Hebrew." As ABBYY has a very good reputation for getting English and other languages right, I'm considering this for a big scanning project I have in mind (Hanzi, Pinyin with tone marks, and English). The program's not cheap: US$400. How does that compare with other commercial products?

Link to comment
Share on other sites

  • 1 month later...

I have used ReadIrisPro 11 for converting images of simplified characters into digitized text. Generally, it works pretty well. If the document is scanned as a .pdf, it will retain the original formatting most of the time.

As anyone tried using a Chinese version of Adobe Professional? The English version has an OCR function that works well with English and I've heard that the Chinese version has Chinese OCR capability, but I have been unable to verify this feature.

Link to comment
Share on other sites

  • 2 months later...

Can anyone recommend an OCR program that will scan Chinese handwriting and convert it into editable word processor files?

I have Windows XP and have been using an OCR program from ABBYY successfully. It came with my Lexmark printer. But the ABBYY version that I have does not recognize Chinese.

Thanks for your help.

Berni R.

Link to comment
Share on other sites

  • 3 weeks later...

Help!

I am in way over my head! I am in a Chinese class, which is already above my skill level, to make matters worse the book we are using is strictly traditional, not what I learned in my time in China. Can anybody suggest a method to convert this, probably digitally, into simplified. Preferably this can be done on a Mac, which is why I don't think previous posts will help.

Thanks for any help!

Link to comment
Share on other sites

Join the conversation

You can post now and select your username and password later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Unfortunately, your content contains terms that we do not allow. Please edit your content to remove the highlighted words below.
Click here to reply. Select text to quote.

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...