What is OCR? (Optical Character Recognition)

OCR (Optical Character Recognition) is the technology that extract text from images. You send a picture to the OCR engine that splits it into smaller parts (lines) and then compares the images to a list of potential characters. The engine returns a list of words or characters and the position of them on the original image.

We developed specific OCR engines dedicated for special recognition:

Our engine is design with Mobile devices as target; the OCR libraries have small footprint, low memory and CPU requirements.

Optical Character Recognition is used to achieve Paperless Office and fasten the workflow spent on processing paper documents.

OCR is used by different companies sectors to reduce the cost of processing documents:
  • By using Document Recognition, you create a digital version of the documents you are handling in your company, with all the adventages of computer generated files, like search, data base archive, etc.
  • With Business Card Recognition, you can let your employees populate a data base of contacts that you can easily share and search through.
  • Banking Card Recognition let you recognize and process a large amount of information contained on the Bank Cards in a minimum time.
  • Car Plate Recognition retrieves the car plates' number and let you process the information you want. Example: a parking lot management for fee handling.
  • Chinese Citizen ID Card Recognition retrieves the information on the ID and let you populate the forms when dealing with administrative procedures.

What is BCR?

BCR (Business Card Recognition) is the specific usage of OCR to read Business Cards. The OCR engine pre-process the image to recognize and locate the information on the bizcard. The information that can be extract is:

  • Name
  • Company
  • Position
  • Telphone & Fax numbers
  • Email addresses
  • Address
  • Websites

Image Processing

with our Image processing SDK, you can prepare your image for a better OCR. By removing some background noises, automatically detect the edge of the document (that allow document orientation and auto-croping), apply filters (GreyScale or Black&White) and image compression, your document images will provide a better recognition accuracy rate and speed.

Even if our Image Processing SDK is tuned to enhance the recognition result for document images (invoices, business cards and so on), you can use it for entire different cases. Let it be enhancement of travel or personal pictures, this will allow you to share sharper images.

Instant Messenger

With our Instant Messenger SDKs, you can create your communication tools for dedicated messenger mobile application and PC software. You can control where your corporate data are going without relying on public or closed source solution.