Read data inside documents
Export found data into Applications, files or databases
Speed up manual processing with automation
C2S are Platinum Partners with ABBYY UK
OCR - Optical Character Recognition has been around for years. It was a subject in the 80s for O'Level computer studies. So it's not new. The established use has been to take a page of text from a scan and convert it to editable text in say Word. There is also zonal OCR where we can read a specific area of the page that perhaps has a delivery note number. This can be limited though as the value might move or bounce around from one document to the next.
With intelligent OCR we are looking for a value or values on the page that could be anywhere but might say be close to the words "order number" or might be a 5 digit number with a capital letter prefix. With this approach we can find any value, and then critically, make sense of it. So this approach to OCR works brilliantly for all types of documents - whether scanned or PDF, where you want the values from a document like a sales order or a supplier Invoice.
One of the main bottlenecks in scanning high volumes of documents is the indexing. Making sure every document or every page is collated against the correct entity, and therefore can be found again for review. Intelligent OCR can be used to assist the scanning process. From simple barcode recognition all the way up to finding keywords that help indentify the document or the section inside the document.
Intelligent OCR will allow the values you find to be checked and verified. This could be a user step to confirm whether a character is an 8 or a B but could also be to check what looks to be a vehicle registartion number and to check it against your list of owned vehicles.
When your documents are being processed the data can be exported in many different ways. It could be found values are passed over to a database and the PDF of the document is auto-filed in a document management system or with a naming convention on your network.
We can help provide a solution that scales for the volume of pages you need to process. Under 100,000 pages a year might just require a desktop edition of the Intelligent OCR software. 2 million pages per year will require a certain amount of processing power and a number of verification users. We will help design the implementation for the volume you need to handle.
Our client is a logistics company and wanted to scan and file a range of delivery notes with minimal user intervention. We provide the software for the scanning and intelligent OCR, so hundreds of logistics documents are easily scanned and filed each day with just a few minutes verification from the scanning operator.