The content of scanned documents (or faxes) is readable only by humans. For computer applications, they are merely a collection of meaningless pixels. In order to facilitate the automatic storage of documents within a repository and provide correct attributes for those documents, the type of document and relevant metadata have to be known. In order to automatically trigger business processes and populate business transactions with information, relevant data from the documents must be available.
OpenText is known for its exceptionally advanced recognition technology all the way through the technology stack. More than 35 years of experience in the field with large-scale operations (like the U.S. census or the German tax authorities) are the foundation of the product.
OpenText Capture Center (formerly DOKuStar Capture Suite) uses the most advanced document and character recognition capabilities available to turn documents into machine-readable information. Capture Center captures the data “stored” in scanned images and faxes and interprets it using OCR, ICR, IDR, adaptive reading and other technologies.
In business-to-consumer businesses, it is critical to maintain customer records accurately and completely. Customers often send paper documents (e.g., application forms, claim forms, complaint letters, salary certificates, etc.) that must be filed in the right customer record. Capture Center applies document recognition functionality first to classify the document type (to determine if it’s an invoice, insurance claim, order entry, application form, customer feedback, or other defined document type). It then extracts business data from the digital image using Optical Character Recognition (OCR), Intelligent Character Recognition (ICR) and Intelligent Document Recognition (IDR).
Using OCC, your organization saves money from reduced manual keying and paper handling, speeds up business processes by using digital workflow right from the start, improves data quality by capturing all relevant data from documents, and reduces compliance risks by keeping track of document-related activities.
Intelligent Character Recognition
Adaptive classification technology (ACT) is a learning algorithm. ACT uses several samples from each document class (e.g., several orders, claims, or applications),and extracts the characteristic features of these documents (like specific keywords or phrases) based on OCR content. Each document that is to be classified is compared against these features and classified accordingly. This method is well-suited for unstructured documents.
