What is Optical Character Recognition (OCR)

OCR conversion is the process by which text from an image (a picture of a document) can be extracted, providing searchable ASCII text. The OCR text of the complete document can then be searched for key words or phrases.

Within Eureka! Central, users can locate a single page out of thousands in seconds just by entering an invoice number or key phrase from a document.

With our automated OCR capabilities, our clients have the ability to search for and locate a document based on its content in addition to locating a document based on its set index fields. Below are a few examples that selected clients of ours have used our OCR technology to locate, retrieve, and view documents:

• Stock Transaction Numbers

• Customer Account Numbers

• Invoice Numbers

• CUSIP Numbers

• Vehicle and Boat Registration Numbers

• Last Name Searches

• License Numbers

We emphasize to our customers however, that OCR conversion is not 100% accurate and the conversion results are greatly determined by the type of documents and clarity of the characters on the original document.

For instance, a 1st generation legal agreement printed on a laser printer will yield close to 99% OCR accuracy where a photocopy of a multi-part form will be less accurate.

ScanAndHost captures this text in an automated process and stores it at the database level making the retrieval of any document a breeze. Remember, ScanAndHost automatically includes OCR of all documents at no additional cost.