OCR (Optical Character Recognition) is the technology that can extract text from images. The images can be pictures taken from your mobile device or scanned copies of paper document.
The recognition rate of modern OCR engine is reaching more than 90% for well formatted printed fonts. The problems encountered are mostly due to bad image: the image is too skewed, too dark or blurry, or a combination of this problems.
Some engines are dedicated to certain type of languages: most European languages are based on Latin alphabet which limits the difficulty of number of characters. (~25/30 letters + accentuation).
Chinese language on the other hand comports more than ten thousands of characters in both traditional and simplified. Some big OCR companies, like ABBYY, I.R.I.S and Google included some Chinese Character Recognition but the results are not on part with their European language recognition.
Yunmai Technology is a Chinese company dedicated in OCR SDK: we have developed Documents, Business Card, ID Card and Banking Card recognition SDK. Our performance handling Chinese Characters is over 95%.
We are also developing Mobile and PC applications:
Docs Matter – Document Reader
SmartEye – LiveTextTranslator
BizCards Matter – Business Card Reader
If you want to develop your own application using our Chinese OCR Engine, please contact one of our sale representative by email (email@example.com).