KanScan - Finally, an OCR solution to digitize printed documents in Kannada language.
There has been significant advances in OCR (Optical Character Recognition) products over the last few decades. OCR is now considered a solved problem. Many commercial OCR products are available in the market. But, these facts apply mainly to English and European languages.
What about OCR solutions for Indian languages?
What about OCR for Kannada language, which is the language of people in Karnataka and has a history of more than 2000 years? Some work is being done. But there isn't any product that is publicly available until now.
is an OCR product developed to recognize printed text documents for Kannada language.
Refer to KanScan product page to know more about this product.
See the KanScan help videos here
- Click on this link: KanScanV2.2
- This will take you to Google-Drive.
- You will be seeing zip file contents for KanScanV2.2.013.zip
- Click on Download link ( Down arrow )
- Save the file kanscanV2.2.013.zip to D:\kanscan folder on your desktop.
- Extract the zip file with WinZIP or WinRAR into folder kanscan
- Make sure you have already installed Java Runtime Environment ( version 6 or higher is preferrable )
- Go to kanscan folder and click on file kanscanv2.2.013.jar OR kanscanv2.2.013.bat to run the application.
- KanScan user guide is here
- For more instructions on installation refer to Installation-Steps
KanScan made compatible with NVDA
Template-Matching functionality included
KanScan 2.2 User Guide released
KanScanV2.2.007 (Spell Checker included)
More OCR Algorithms incorporated to improve OCR quality
Image pre-processing utilities added to GUI. OCR