Optical character recognition software for the Khmer language. It is only trained for Limon R1 (you can try it with other fonts, but it might not be accurate). PAN Cambodia has since ceased to develop this software, but you can use it as is. Optical character recognition, usually abbreviated to OCR, is the mechanical or electronic conversion of scanned or photographed images of typewritten or printed text into machine-encoded/computer-readable text (source: Wikipedia).

Download “KhmerOCR.zip”

KhmerOCR.zip – Downloaded 10759 times – 27.42 MB

UPDATE (6-26-2014):

There are a few projects in the works concerning Khmer OCR:
  • A 1 year project funded by the World Bank for the Department of Computer Science of Institute of Technology of Cambodia (ITC) to improve this software so that it is usable by public users. However, this project did not start yet. This project is expected to start in few months. After the end of this project, the software will be available for download.
  • A 2 year project between ITC and Open Institute to develop Khmer OCR software. This project too is expected to begin in few months.
(Thanks to Long Seangmeng for this information).

17 Comments. Leave new

  • PAN Khmer Collation and Sorting Program ដំណើរការបានតែលើ Word & Excel, តើធ្វើដូចម្តេច​ ឬ​មានកម្មវិធីណា ដែលអាច តម្រៀប និង ស្រង់ទិន្នន័យ ពុម្ភអក្សរខ្មែរយូនីកូដក្នុងកម្មវិធី MS.Access 2010 បាន?​ សូមជួយខ្ញុំផង ! សូមអរគុណជាអនេក

    Reply
    • Nathan Wells
      June 29, 2014 10:25 pm

      I believe MS Access supports sorting Khmer Unicode in the program itself. You don’t need an external program (the PAN Khmer collation and sorting program was for 2003 and below). This is true for Excel. I don’t use Access much, but I would assume it can sort Khmer just as Excel does.

      Reply
  • You don’t us Access much, but I do, It can’t sort can’t filter and don’t support with VBA.

    Reply
  • I try to use it but It show me error while recognize. I use my cannon scan document to jpg. and I take it to photoshop covert to image mode bmp and I save as bmp for window and 1 bit color. after I open it with khmerocr for recognize but it error. could you please guide me how to use it?

    Reply
    • Nathan Wells
      July 8, 2014 3:41 pm

      Try to unzip the example text in the file Sample Text(Limon R1).zip and see if those work for you. If they do, try to format your scans to be the same size as the examples and see if that works. Unfortunately this program was not fully developed, and so it has many errors.

      Reply
  • ចង់បានកម្មវិធីដែលយើងសរសរជាលេខហើយអោយវាស្វ័យប្រវត្តសរសេរជាអក្សរសម្រាប់limon or khmer unicode.

    Reply
    • អាចចូល https://budhivithyasastra.wordpress.com/ រួចចូល របៀបបំប្លែងតម្លៃលេខ ទៅជាអក្សរ ជាភាសាខ្មែរ (លីម៉ូន និង យូនីកូដ) និងអង់គ្លេស-SPELL NUMBER IN KHMER AND ENGLISH។ សូមជួយ share បន្ត ដើម្បីមានអ្នកប្រើបានច្រើនគ្នា។

      Reply
  • file រូបភាពរបស់ខ្ញុំជា jpg ។ តើយើងធ្វើយ៉ាងម៉េចបានអាច convert file នេះបាន បើកម្មវិធីនេះ support តែ file .bmp

    Reply
  • I used to found one advantage web app to convert unicode to limon on Khunicode but unlucky their webpage down now and I couldn’t find any webapp that beable to instantly convert like before. It really helpful for many software than unknown unicode.

    Reply
  • does it work with khmer unicode font like “khmer os system” “khmer os moul light” ?

    Reply
  • cant use it why does it need bmp

    Reply

Leave a Reply

Your email address will not be published. Required fields are marked *

Fill out this field
Fill out this field
Please enter a valid email address.
You need to agree with the terms to proceed

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Menu