Develop an Application of Foreign Language Reader with Yunmai Document OCR SDK

With the development of translation tools, reading foreign languages is easier and easier. There has PC software, mobile applications, and web translation which are able to translate foreign languages to native words. Though the translation results is not exactly correct, user can get the approximate meaning through the results. As well as the digit text, voice information also can be translated through some software.

Sometimes people would see some foreign text with their eyes, such as Chinese, Japanese, Russian, and Korean, but they neither know the pronunciation nor type the letter. This case always happen to travelers, when they visit other countries, they would meet some advertisement slogans, traffic directions, building name, and restaurant menu which are written with local languages, how do they handle the translation?

In these case, to process the translation, the key point is how to convert the text in the image to digit letters. The optical character recognition (OCR) technology can do these; this technology is able to extract text from image through capturing or scanning. Yunmai Document OCR SDK provide the character recognition feature. This SDK is developed by Yunmai Technology Company, compare with other OCR SDKs, it has more advantage on Chinese characters recognition.

The Yunmai Document OCR SDK can be integrated into mobile application to create a feature of reading foreign text. This engine processes recognition at high speed, there will take less than 1 second for a short sentence; so that the engine can be used to develop an instant translation tool, such as recorder translation. Since the foreign text recognition is no more difficult, it is easy for developers to make a translate-by-read application.

Demo application of Yunmai Document OCR SDK
CC Smart Eye - Live Text Translator

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 information is for reference:
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://en.yunmai.com/