Develop Invoice Recognition Software with Yunmai Document OCR SDK

Optical Character Recognition (OCR) has been widely applied in data entry. This technology is able to retrieve text form images, so that some developers add OCR to some software to create a fast data entry feature, which is extracting characters from paper document by capturing.
Some companies always receive a lot of invoice every day, they need staffs to manually enter data to their information system, obviously, it will cost too much labor. The OCR technology bring innovation on the invoices data entry. Kofax company has developed KTM (Kofax Transformation Module) to enable users configure an invoice template, and then automatically transfer paper invoice data into a management system.
The KTM is a big system, its function is more than the invoice recognition. But some company only require the feature of smart data entry for invoice, if they use Kofax system, they need to pay a huge amount for the software. Yunmai company is an OCR SDK provider, the company has developed more than ten different OCR engines. Yunmai Document OCR SDK is one of the engines, developer can use this SDK to make invoice recognition software.
Normally, invoice information include company name, contact information, price, amount, item name, item description, quantity, etc. Developer need to create a template which divides the invoice into several parts, each part only contains one type of information. Use Yunmai Document OCR SDK to recognize different areas by associated parameter configuration.
If a software is to match the demand of some company’s great volume of invoices data entry, Yunmai Document OCR engine is a good choice for developers.

Demo application of Yunmai Document OCR SDK
Docs Matter - Mobile Scanner

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://www.yunmai.com/en/home.html