Yunmai Document OCR SDK Help You Create an E-Library

Optical Character Recognition (OCR) is usually used for digitizing paper document. this technology has been widely applied in data entry at business offices and government bureaus. Yunmai Document OCR SDK is a character identification engine for document recognition, which is developed by Yunmai Technology company. This OCR SDK recognizes more than 14 languages, it has advantage of identifying the characters of English, European and Chinese, the accuracy rate might reach 99%. Docs Matter is one of the mobile applications that is integrated with Yunmai Document recognition engine, the app achieves high recognition accuracy, and has gained large number of users.
The Yunmai Document OCR SDK is able to convert printed document to editable PDF file. This feature let us conceive an idea of cloning an electric version library. As you know, e-library is more convenient than traditional library, it allow readers access the required information anytime and anywhere. The physical library always store thousands of books, though most of them have computer management, but it is not easy to find some small articles or chips from the great book house. If integrate Yunmai Document OCR engine into a software to convert a paper book to PDF file by capturing, the engine would recognize the text on the image captured and make a searchable PDF file. So that readers can find any content by keyword search, it will make a library more valuable and serve more people.

How the OCR engine works
- Get image
- Blur detection
- Text lines segmentation
- Chracters segmentation
- Chracter feature extraction
- Chracters matching
- Handling End of line
- Automatic words segmentation
- Chracters detection

Character recognition results
The following are the average recognition accuracy for different languages:
English characters: 97%
European characters: 99%
Chinese characters: 92%
These data are obtained on recognizing an 8 pixel megabytes image of a document with 800 characters, and the font size is 12.

Character recognition speed
The recognition speed is based on hardware and the document captured, the following is an example:
Hardware: 1.7GHz CPU / 1GB RAM smart phone or higher
Capturing object: a paper document with about 800 characters
Recognition speed: OCR process will take about 7 seconds.

Programming language supported
The SDK is available for different programming languages: Java, C++, C, Object Pascal, Objective-C.

Other recognition SDKs we developed
Business card recognition SDK
Bank card recognition SDK
Chinese citizen ID card recognition SDK

Contact information
Tel: +86 592 6301858
Email: sales@yunmai.com
Website: http://www.yunmai.com/en/home.html