OCR (Optical Character Recognition)

OnBase OCR is a highly accurate and easy-to-use document recognition package integrated seamlessly with the OnBase  Document Imaging and  Document Import Processor modules. OnBase OCR recognizes and translates machine printed characters resident on a scanned image document, creating a machine-readable text document to facilitate text searching and/or full text indexing. Creating text renditions of your image documents gives you the capability to use text searches to find a particular document and to find specific content within a document. Users are then able to instantly locate specific words or phrases within a document or group of documents, dramatically streamlining even the most cumbersome of research tasks. Documents commonly scanned and then OCR'd include business correspondence, legal memoranda, contracts, specification sheets, patient EOBs and manuals.

OnBase OCR utilizes the OmniPage® OCR engine, widely praised for its high degree of accuracy and flexibility. OnBase OCR is a full-page OCR package with multiple output options. Text renditions can be stored in ASCII text, searchable PDF, Microsoft Word or HTML file formats. Formatting can be retained, preserving the original look of the image documents, or removed entirely, keeping only the document text. You can also vary the rate of the OCR process to perform for highest character recognition or for speed, depending on your needs and the quality of your original documents. OnBase OCR offers the flexibility of having different OCR settings saved for each document type you process. OCR can be performed on bi-tonal, grayscale and even color images and currently supports character recognition for 18 languages.

Most documents will be OCR'd in batches; though you can OCR documents from a list with a simple right-click option. This is important when new image pages are added to a document and it becomes necessary to re-OCR that document to ensure a complete OCR rendition of the entire document.

Application

Having the ability to search documents for an endless variety of words and/or phrases facilitates complex research that cannot be ulting batch has been indexed. The full-page OCR engine analyzes the scanned images, ignores peripheral information such as lines and graphics and creates corresponding text files for those images. The resulting text is stored into the OnBase system as a rendition of the originalperformed when users are limited to a set of keywords. In contract management, for instance, a user can search a complex agreement for references to a specific aspect that is not captured as a keyword. This eliminates the need to read through the entire contract to pinpoint a specific phrase or to search through a library of contracts to recall how a section had been worded in the past.

Document Imaging
The OCR process is initiated after documents have been scanned into OnBase and the res image document.

Full Text Searching
OnBase OCR becomes even more powerful when complemented by OnBase full-text indexing functionality, available with the Verity Full-Text Indexing Server  and  Microsoft Full-Text Indexing Server modules. These modules provide accelerated and flexible search capabilities, making it extremely easy to find the document you are looking for by searching for particular text strings or variations of characters.

Document Import Processor
The OnBase Document Import Processor also integrates with the OCR module. Images brought in with this processor can be OCR'd as part of the commit process, offering all of the same search and retrieval capabilities.

Core Features

• Seamlessly integrated with OnBase Document Imaging, Document Import Processor and Full-Text Indexing

• Utilizes the accurate and configurable OmniPage® OCR engines

• Full-page batch OCR of image documents

• Converts non-searchable image documents into searchable text documents

• Configurable engine settings per document type

• Select from multiple file type options for output